diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-10-02 12:17:24 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-10-02 12:17:24 -0700 |
| commit | 3f1fe48a36b0b6722dc3fd421d93512bac138e9a (patch) | |
| tree | b767d7f6e26bc64334d3f14f8422d187239dc45d /rust/zerocopy/benches | |
| download | linux-stable-3f1fe48a36b0b6722dc3fd421d93512bac138e9a.tar.gz linux-stable-3f1fe48a36b0b6722dc3fd421d93512bac138e9a.zip | |
Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted
Pull io_uring fixes from Jens Axboe:
- Fix a task_work add use-after-free with SQPOLL.
The sqpoll thread could pop and complete the last request while
io_req_normal_work_add() was still looking at them after the mpscq
push.
Use the same approach as DEFER_TASKRUN to protect from that, holding
an RCU read lock across the add, and have exit wait for an RCU grace
period for SQPOLL rings as well.
- CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
rings
- Mark the source filter table as COW when cloning bpf filters, so
registering another filter on the source doesn't modify the shared
table in place
- Initialize the task context before running the BPF loop
- Requeue zcrx multishot receives stopped by a local resource
- End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)
* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
io_uring: fix task_work add use-after-free with SQPOLL
io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
io_uring/zcrx: requeue multishot receives stopped by a local resource
io_uring: initialize task context before running the BPF loop
io_uring: zero big_cqe for aux CQEs on CQE32 rings
io_uring: fix free entry check for 32b CQEs on CQE32 rings
io_uring: only post the dummy skip CQE on CQE_MIXED rings
io_uring/bpf_filter: mark source as COW when cloning filters
Diffstat (limited to 'rust/zerocopy/benches')
213 files changed, 6940 insertions, 0 deletions
diff --git a/rust/zerocopy/benches/as_bytes_dynamic_size.rs b/rust/zerocopy/benches/as_bytes_dynamic_size.rs new file mode 100644 index 000000000..68cd1d6f4 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_dynamic_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_as_bytes_dynamic_size(source: &format::CocoPacket) -> &[u8] { + source.as_bytes() +} diff --git a/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64 b/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64 new file mode 100644 index 000000000..f68bad612 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64 @@ -0,0 +1,5 @@ +bench_as_bytes_dynamic_size: + mov rax, rdi + lea rdx, [2*rsi + 5] + and rdx, -2 + ret diff --git a/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64.mca b/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64.mca new file mode 100644 index 000000000..c3b92a9a9 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_dynamic_size.x86-64.mca @@ -0,0 +1,47 @@ +Iterations: 100 +Instructions: 400 +Total Cycles: 137 +Total uOps: 400 + +Dispatch Width: 4 +uOps Per Cycle: 2.92 +IPC: 2.92 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.50 lea rdx, [2*rsi + 5] + 1 1 0.33 and rdx, -2 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.33 1.33 - 1.34 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.66 - 0.34 - - mov rax, rdi + - - 0.33 0.67 - - - - lea rdx, [2*rsi + 5] + - - 1.00 - - - - - and rdx, -2 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/as_bytes_static_size.rs b/rust/zerocopy/benches/as_bytes_static_size.rs new file mode 100644 index 000000000..2ad738e95 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_static_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_as_bytes_static_size(source: &format::CocoPacket) -> &[u8] { + source.as_bytes() +} diff --git a/rust/zerocopy/benches/as_bytes_static_size.x86-64 b/rust/zerocopy/benches/as_bytes_static_size.x86-64 new file mode 100644 index 000000000..213e74ab5 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_static_size.x86-64 @@ -0,0 +1,4 @@ +bench_as_bytes_static_size: + mov rax, rdi + mov edx, 6 + ret diff --git a/rust/zerocopy/benches/as_bytes_static_size.x86-64.mca b/rust/zerocopy/benches/as_bytes_static_size.x86-64.mca new file mode 100644 index 000000000..ae04a6ba9 --- /dev/null +++ b/rust/zerocopy/benches/as_bytes_static_size.x86-64.mca @@ -0,0 +1,45 @@ +Iterations: 100 +Instructions: 300 +Total Cycles: 104 +Total uOps: 300 + +Dispatch Width: 4 +uOps Per Cycle: 2.88 +IPC: 2.88 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov edx, 6 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 - 1.01 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.99 - - 0.01 - - mov rax, rdi + - - - 1.00 - - - - mov edx, 6 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/extend_vec_zeroed.rs b/rust/zerocopy/benches/extend_vec_zeroed.rs new file mode 100644 index 000000000..1fbf772d1 --- /dev/null +++ b/rust/zerocopy/benches/extend_vec_zeroed.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_extend_vec_zeroed(v: &mut Vec<format::LocoPacket>, additional: usize) -> Option<()> { + FromZeros::extend_vec_zeroed(v, additional).ok() +} diff --git a/rust/zerocopy/benches/extend_vec_zeroed.x86-64 b/rust/zerocopy/benches/extend_vec_zeroed.x86-64 new file mode 100644 index 000000000..831b2a075 --- /dev/null +++ b/rust/zerocopy/benches/extend_vec_zeroed.x86-64 @@ -0,0 +1,60 @@ +bench_extend_vec_zeroed: + push r15 + push r14 + push r13 + push r12 + push rbx + sub rsp, 32 + mov rbx, rdi + mov rax, qword ptr [rdi] + mov r12, qword ptr [rdi + 16] + mov rcx, rax + sub rcx, r12 + cmp rsi, rcx + jbe .LBB6_3 + mov r15, r12 + add r15, rsi + jae .LBB6_6 +.LBB6_2: + xor eax, eax + jmp .LBB6_5 +.LBB6_3: + mov rax, qword ptr [rbx + 8] + lea r15, [r12 + rsi] +.LBB6_4: + lea rcx, [r12 + 2*r12] + lea rdi, [rax + 2*rcx] + add rsi, rsi + lea rdx, [rsi + 2*rsi] + xor esi, esi + call qword ptr [rip + memset@GOTPCREL] + mov qword ptr [rbx + 16], r15 + mov al, 1 +.LBB6_5: + add rsp, 32 + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + ret +.LBB6_6: + mov r13, rsi + lea rcx, [rax + rax] + cmp r15, rcx + cmova rcx, r15 + cmp rcx, 5 + mov r14d, 4 + cmovae r14, rcx + mov rdx, qword ptr [rbx + 8] + lea rdi, [rsp + 8] + mov rsi, rax + mov rcx, r14 + call <alloc::raw_vec::RawVecInner>::finish_grow + cmp dword ptr [rsp + 8], 1 + je .LBB6_2 + mov rax, qword ptr [rsp + 16] + mov qword ptr [rbx + 8], rax + mov qword ptr [rbx], r14 + mov rsi, r13 + jmp .LBB6_4 diff --git a/rust/zerocopy/benches/extend_vec_zeroed.x86-64.mca b/rust/zerocopy/benches/extend_vec_zeroed.x86-64.mca new file mode 100644 index 000000000..cfab1eea8 --- /dev/null +++ b/rust/zerocopy/benches/extend_vec_zeroed.x86-64.mca @@ -0,0 +1,147 @@ +Iterations: 100 +Instructions: 5400 +Total Cycles: 6595 +Total uOps: 6800 + +Dispatch Width: 4 +uOps Per Cycle: 1.03 +IPC: 0.82 +Block RThroughput: 17.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r15 + 2 5 1.00 * push r14 + 2 5 1.00 * push r13 + 2 5 1.00 * push r12 + 2 5 1.00 * push rbx + 1 1 0.33 sub rsp, 32 + 1 1 0.33 mov rbx, rdi + 1 5 0.50 * mov rax, qword ptr [rdi] + 1 5 0.50 * mov r12, qword ptr [rdi + 16] + 1 1 0.33 mov rcx, rax + 1 1 0.33 sub rcx, r12 + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 jbe .LBB6_3 + 1 1 0.33 mov r15, r12 + 1 1 0.33 add r15, rsi + 1 1 1.00 jae .LBB6_6 + 1 0 0.25 xor eax, eax + 1 1 1.00 jmp .LBB6_5 + 1 5 0.50 * mov rax, qword ptr [rbx + 8] + 1 1 0.50 lea r15, [r12 + rsi] + 1 1 0.50 lea rcx, [r12 + 2*r12] + 1 1 0.50 lea rdi, [rax + 2*rcx] + 1 1 0.33 add rsi, rsi + 1 1 0.50 lea rdx, [rsi + 2*rsi] + 1 0 0.25 xor esi, esi + 4 7 1.00 * call qword ptr [rip + memset@GOTPCREL] + 1 1 1.00 * mov qword ptr [rbx + 16], r15 + 1 1 0.33 mov al, 1 + 1 1 0.33 add rsp, 32 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r12 + 1 6 0.50 * pop r13 + 1 6 0.50 * pop r14 + 1 6 0.50 * pop r15 + 1 1 1.00 U ret + 1 1 0.33 mov r13, rsi + 1 1 0.50 lea rcx, [rax + rax] + 1 1 0.33 cmp r15, rcx + 3 3 1.00 cmova rcx, r15 + 1 1 0.33 cmp rcx, 5 + 1 1 0.33 mov r14d, 4 + 2 2 0.67 cmovae r14, rcx + 1 5 0.50 * mov rdx, qword ptr [rbx + 8] + 1 1 0.50 lea rdi, [rsp + 8] + 1 1 0.33 mov rsi, rax + 1 1 0.33 mov rcx, r14 + 3 5 1.00 call <alloc::raw_vec::RawVecInner>::finish_grow + 2 6 0.50 * cmp dword ptr [rsp + 8], 1 + 1 1 1.00 je .LBB6_2 + 1 5 0.50 * mov rax, qword ptr [rsp + 16] + 1 1 1.00 * mov qword ptr [rbx + 8], rax + 1 1 1.00 * mov qword ptr [rbx], r14 + 1 1 0.33 mov rsi, r13 + 1 1 1.00 jmp .LBB6_4 + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 12.00 12.00 10.00 13.00 11.00 11.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - 0.49 0.51 push r15 + - - - - 1.00 - 0.51 0.49 push r14 + - - - - 1.00 - 0.50 0.50 push r13 + - - - - 1.00 - 0.50 0.50 push r12 + - - - - 1.00 - 0.50 0.50 push rbx + - - 0.01 0.99 - - - - sub rsp, 32 + - - - - - 1.00 - - mov rbx, rdi + - - - - - - 0.50 0.50 mov rax, qword ptr [rdi] + - - - - - - 0.50 0.50 mov r12, qword ptr [rdi + 16] + - - - 1.00 - - - - mov rcx, rax + - - - 0.99 - 0.01 - - sub rcx, r12 + - - - - - 1.00 - - cmp rsi, rcx + - - - - - 1.00 - - jbe .LBB6_3 + - - 0.01 0.98 - 0.01 - - mov r15, r12 + - - 0.99 0.01 - - - - add r15, rsi + - - - - - 1.00 - - jae .LBB6_6 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - jmp .LBB6_5 + - - - - - - 0.50 0.50 mov rax, qword ptr [rbx + 8] + - - 1.00 - - - - - lea r15, [r12 + rsi] + - - 0.98 0.02 - - - - lea rcx, [r12 + 2*r12] + - - 0.99 0.01 - - - - lea rdi, [rax + 2*rcx] + - - - 1.00 - - - - add rsi, rsi + - - 0.99 0.01 - - - - lea rdx, [rsi + 2*rsi] + - - - - - - - - xor esi, esi + - - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + memset@GOTPCREL] + - - - - 1.00 - 0.50 0.50 mov qword ptr [rbx + 16], r15 + - - 0.01 0.99 - - - - mov al, 1 + - - 1.00 - - - - - add rsp, 32 + - - - - - - 0.50 0.50 pop rbx + - - - - - - 0.50 0.50 pop r12 + - - - - - - 0.50 0.50 pop r13 + - - - - - - 0.50 0.50 pop r14 + - - - - - - 0.50 0.50 pop r15 + - - - - - 1.00 - - ret + - - 1.00 - - - - - mov r13, rsi + - - 0.01 0.99 - - - - lea rcx, [rax + rax] + - - 0.99 0.01 - - - - cmp r15, rcx + - - 2.00 0.01 - 0.99 - - cmova rcx, r15 + - - 0.01 0.99 - - - - cmp rcx, 5 + - - 0.01 0.99 - - - - mov r14d, 4 + - - 1.00 0.01 - 0.99 - - cmovae r14, rcx + - - - - - - 0.50 0.50 mov rdx, qword ptr [rbx + 8] + - - 0.01 0.99 - - - - lea rdi, [rsp + 8] + - - - 1.00 - - - - mov rsi, rax + - - - 0.01 - 0.99 - - mov rcx, r14 + - - - - 1.00 1.00 0.50 0.50 call <alloc::raw_vec::RawVecInner>::finish_grow + - - - 0.99 - 0.01 0.50 0.50 cmp dword ptr [rsp + 8], 1 + - - - - - 1.00 - - je .LBB6_2 + - - - - - - 0.50 0.50 mov rax, qword ptr [rsp + 16] + - - - - 1.00 - 0.49 0.51 mov qword ptr [rbx + 8], rax + - - - - 1.00 - 0.51 0.49 mov qword ptr [rbx], r14 + - - 0.99 0.01 - - - - mov rsi, r13 + - - - - - 1.00 - - jmp .LBB6_4 diff --git a/rust/zerocopy/benches/formats/coco_dynamic_padding.rs b/rust/zerocopy/benches/formats/coco_dynamic_padding.rs new file mode 100644 index 000000000..e494bce67 --- /dev/null +++ b/rust/zerocopy/benches/formats/coco_dynamic_padding.rs @@ -0,0 +1,24 @@ +use zerocopy_derive::*; + +// The only valid value of this type are the bytes `0xC0C0`. +#[derive(TryFromBytes, KnownLayout, Immutable)] +#[repr(u16)] +pub enum C0C0 { + _XC0C0 = 0xC0C0, +} + +#[derive(FromBytes, KnownLayout, Immutable, SplitAt)] +#[repr(C, align(4))] +pub struct Packet<Magic> { + magic_number: Magic, + milk: u8, + mug_size: u8, + temperature: [u8; 5], + marshmallows: [[u8; 3]], +} + +/// A packet begining with the magic number `0xC0C0`. +pub type CocoPacket = Packet<C0C0>; + +/// A packet beginning with any two initialized bytes. +pub type LocoPacket = Packet<[u8; 2]>; diff --git a/rust/zerocopy/benches/formats/coco_dynamic_size.rs b/rust/zerocopy/benches/formats/coco_dynamic_size.rs new file mode 100644 index 000000000..59364638e --- /dev/null +++ b/rust/zerocopy/benches/formats/coco_dynamic_size.rs @@ -0,0 +1,27 @@ +use zerocopy_derive::*; + +// The only valid value of this type are the bytes `0xC0C0`. +#[derive(TryFromBytes, KnownLayout, Immutable, IntoBytes)] +#[repr(u16)] +pub enum C0C0 { + _XC0C0 = 0xC0C0, +} + +macro_rules! define_packet { + ($name: ident, $trait: ident, $leading_field: ty) => { + #[derive($trait, KnownLayout, Immutable, IntoBytes, SplitAt)] + #[repr(C, align(2))] + pub struct $name { + magic_number: $leading_field, + mug_size: u8, + temperature: u8, + marshmallows: [[u8; 2]], + } + }; +} + +/// Packet begins with bytes 0xC0C0. +define_packet!(CocoPacket, TryFromBytes, C0C0); + +/// Packet begins with any two bytes. +define_packet!(LocoPacket, FromBytes, [u8; 2]); diff --git a/rust/zerocopy/benches/formats/coco_static_size.rs b/rust/zerocopy/benches/formats/coco_static_size.rs new file mode 100644 index 000000000..0839497e1 --- /dev/null +++ b/rust/zerocopy/benches/formats/coco_static_size.rs @@ -0,0 +1,27 @@ +use zerocopy_derive::*; + +// The only valid value of this type are the bytes `0xC0C0`. +#[derive(TryFromBytes, KnownLayout, Immutable, IntoBytes)] +#[repr(u16)] +pub enum C0C0 { + _XC0C0 = 0xC0C0, +} + +macro_rules! define_packet { + ($name: ident, $trait: ident, $leading_field: ty) => { + #[derive($trait, KnownLayout, Immutable, IntoBytes)] + #[repr(C, align(2))] + pub struct $name { + magic_number: $leading_field, + mug_size: u8, + temperature: u8, + marshmallows: [u8; 2], + } + }; +} + +/// Packet begins with bytes 0xC0C0. +define_packet!(CocoPacket, TryFromBytes, C0C0); + +/// Packet begins with any two bytes. +define_packet!(LocoPacket, FromBytes, [u8; 2]); diff --git a/rust/zerocopy/benches/insert_vec_zeroed.rs b/rust/zerocopy/benches/insert_vec_zeroed.rs new file mode 100644 index 000000000..a5d685c2b --- /dev/null +++ b/rust/zerocopy/benches/insert_vec_zeroed.rs @@ -0,0 +1,13 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_insert_vec_zeroed( + v: &mut Vec<format::LocoPacket>, + position: usize, + additional: usize, +) -> Option<()> { + FromZeros::insert_vec_zeroed(v, position, additional).ok() +} diff --git a/rust/zerocopy/benches/insert_vec_zeroed.x86-64 b/rust/zerocopy/benches/insert_vec_zeroed.x86-64 new file mode 100644 index 000000000..9db87403c --- /dev/null +++ b/rust/zerocopy/benches/insert_vec_zeroed.x86-64 @@ -0,0 +1,79 @@ +bench_insert_vec_zeroed: + push rbp + push r15 + push r14 + push r13 + push r12 + push rbx + sub rsp, 24 + mov r12, qword ptr [rdi + 16] + mov r13, r12 + sub r13, rsi + jb .LBB6_10 + mov rbx, rdi + mov rax, qword ptr [rdi] + mov rcx, rax + sub rcx, r12 + cmp rdx, rcx + jbe .LBB6_4 + add r12, rdx + jae .LBB6_7 +.LBB6_3: + xor eax, eax + jmp .LBB6_6 +.LBB6_4: + mov rax, qword ptr [rbx + 8] + add r12, rdx +.LBB6_5: + lea rcx, [rsi + 2*rsi] + lea r14, [rax + 2*rcx] + add rdx, rdx + lea r15, [rdx + 2*rdx] + lea rdi, [r14 + r15] + add r13, r13 + lea rdx, [2*r13] + add rdx, r13 + mov rsi, r14 + call qword ptr [rip + memmove@GOTPCREL] + mov rdi, r14 + xor esi, esi + mov rdx, r15 + call qword ptr [rip + memset@GOTPCREL] + mov qword ptr [rbx + 16], r12 + mov al, 1 +.LBB6_6: + add rsp, 24 + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB6_7: + mov r15, rsi + mov rbp, rdx + lea rcx, [rax + rax] + cmp r12, rcx + cmova rcx, r12 + cmp rcx, 5 + mov r14d, 4 + cmovae r14, rcx + mov rdx, qword ptr [rbx + 8] + mov rdi, rsp + mov rsi, rax + mov rcx, r14 + call <alloc::raw_vec::RawVecInner>::finish_grow + cmp dword ptr [rsp], 1 + je .LBB6_3 + mov rax, qword ptr [rsp + 8] + mov qword ptr [rbx + 8], rax + mov qword ptr [rbx], r14 + mov rdx, rbp + mov rsi, r15 + jmp .LBB6_5 +.LBB6_10: + lea rdi, [rip + .Lanon.HASH.1] + lea rdx, [rip + .Lanon.HASH.3] + mov esi, 37 + call qword ptr [rip + core::panicking::panic@GOTPCREL] diff --git a/rust/zerocopy/benches/insert_vec_zeroed.x86-64.mca b/rust/zerocopy/benches/insert_vec_zeroed.x86-64.mca new file mode 100644 index 000000000..665240667 --- /dev/null +++ b/rust/zerocopy/benches/insert_vec_zeroed.x86-64.mca @@ -0,0 +1,183 @@ +Iterations: 100 +Instructions: 7200 +Total Cycles: 7648 +Total uOps: 9300 + +Dispatch Width: 4 +uOps Per Cycle: 1.22 +IPC: 0.94 +Block RThroughput: 23.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push rbp + 2 5 1.00 * push r15 + 2 5 1.00 * push r14 + 2 5 1.00 * push r13 + 2 5 1.00 * push r12 + 2 5 1.00 * push rbx + 1 1 0.33 sub rsp, 24 + 1 5 0.50 * mov r12, qword ptr [rdi + 16] + 1 1 0.33 mov r13, r12 + 1 1 0.33 sub r13, rsi + 1 1 1.00 jb .LBB6_10 + 1 1 0.33 mov rbx, rdi + 1 5 0.50 * mov rax, qword ptr [rdi] + 1 1 0.33 mov rcx, rax + 1 1 0.33 sub rcx, r12 + 1 1 0.33 cmp rdx, rcx + 1 1 1.00 jbe .LBB6_4 + 1 1 0.33 add r12, rdx + 1 1 1.00 jae .LBB6_7 + 1 0 0.25 xor eax, eax + 1 1 1.00 jmp .LBB6_6 + 1 5 0.50 * mov rax, qword ptr [rbx + 8] + 1 1 0.33 add r12, rdx + 1 1 0.50 lea rcx, [rsi + 2*rsi] + 1 1 0.50 lea r14, [rax + 2*rcx] + 1 1 0.33 add rdx, rdx + 1 1 0.50 lea r15, [rdx + 2*rdx] + 1 1 0.50 lea rdi, [r14 + r15] + 1 1 0.33 add r13, r13 + 1 1 0.50 lea rdx, [2*r13] + 1 1 0.33 add rdx, r13 + 1 1 0.33 mov rsi, r14 + 4 7 1.00 * call qword ptr [rip + memmove@GOTPCREL] + 1 1 0.33 mov rdi, r14 + 1 0 0.25 xor esi, esi + 1 1 0.33 mov rdx, r15 + 4 7 1.00 * call qword ptr [rip + memset@GOTPCREL] + 1 1 1.00 * mov qword ptr [rbx + 16], r12 + 1 1 0.33 mov al, 1 + 1 1 0.33 add rsp, 24 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r12 + 1 6 0.50 * pop r13 + 1 6 0.50 * pop r14 + 1 6 0.50 * pop r15 + 1 6 0.50 * pop rbp + 1 1 1.00 U ret + 1 1 0.33 mov r15, rsi + 1 1 0.33 mov rbp, rdx + 1 1 0.50 lea rcx, [rax + rax] + 1 1 0.33 cmp r12, rcx + 3 3 1.00 cmova rcx, r12 + 1 1 0.33 cmp rcx, 5 + 1 1 0.33 mov r14d, 4 + 2 2 0.67 cmovae r14, rcx + 1 5 0.50 * mov rdx, qword ptr [rbx + 8] + 1 1 0.33 mov rdi, rsp + 1 1 0.33 mov rsi, rax + 1 1 0.33 mov rcx, r14 + 3 5 1.00 call <alloc::raw_vec::RawVecInner>::finish_grow + 2 6 0.50 * cmp dword ptr [rsp], 1 + 1 1 1.00 je .LBB6_3 + 1 5 0.50 * mov rax, qword ptr [rsp + 8] + 1 1 1.00 * mov qword ptr [rbx + 8], rax + 1 1 1.00 * mov qword ptr [rbx], r14 + 1 1 0.33 mov rdx, rbp + 1 1 0.33 mov rsi, r15 + 1 1 1.00 jmp .LBB6_5 + 1 1 0.50 lea rdi, [rip + .Lanon.HASH.1] + 1 1 0.50 lea rdx, [rip + .Lanon.HASH.3] + 1 1 0.33 mov esi, 37 + 4 7 1.00 * call qword ptr [rip + core::panicking::panic@GOTPCREL] + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 17.02 16.50 13.00 19.48 14.00 14.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - 0.98 0.02 push rbp + - - - - 1.00 - 0.02 0.98 push r15 + - - - - 1.00 - 0.99 0.01 push r14 + - - - - 1.00 - 0.01 0.99 push r13 + - - - - 1.00 - 0.99 0.01 push r12 + - - - - 1.00 - 0.01 0.99 push rbx + - - 0.49 0.51 - - - - sub rsp, 24 + - - - - - - 0.04 0.96 mov r12, qword ptr [rdi + 16] + - - 0.49 0.50 - 0.01 - - mov r13, r12 + - - 0.48 0.51 - 0.01 - - sub r13, rsi + - - - - - 1.00 - - jb .LBB6_10 + - - 0.49 0.49 - 0.02 - - mov rbx, rdi + - - - - - - 0.97 0.03 mov rax, qword ptr [rdi] + - - 0.51 0.49 - - - - mov rcx, rax + - - 0.49 0.02 - 0.49 - - sub rcx, r12 + - - 0.49 0.50 - 0.01 - - cmp rdx, rcx + - - - - - 1.00 - - jbe .LBB6_4 + - - 0.02 0.49 - 0.49 - - add r12, rdx + - - - - - 1.00 - - jae .LBB6_7 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - jmp .LBB6_6 + - - - - - - 0.97 0.03 mov rax, qword ptr [rbx + 8] + - - 0.51 0.49 - - - - add r12, rdx + - - 0.49 0.51 - - - - lea rcx, [rsi + 2*rsi] + - - 0.50 0.50 - - - - lea r14, [rax + 2*rcx] + - - 0.51 0.49 - - - - add rdx, rdx + - - 0.50 0.50 - - - - lea r15, [rdx + 2*rdx] + - - 0.49 0.51 - - - - lea rdi, [r14 + r15] + - - 0.50 0.49 - 0.01 - - add r13, r13 + - - 0.51 0.49 - - - - lea rdx, [2*r13] + - - 0.01 0.01 - 0.98 - - add rdx, r13 + - - 0.01 - - 0.99 - - mov rsi, r14 + - - - - 1.00 1.00 1.98 0.02 call qword ptr [rip + memmove@GOTPCREL] + - - 0.49 0.50 - 0.01 - - mov rdi, r14 + - - - - - - - - xor esi, esi + - - 0.50 0.50 - - - - mov rdx, r15 + - - - - 1.00 1.00 1.96 0.04 call qword ptr [rip + memset@GOTPCREL] + - - - - 1.00 - 0.01 0.99 mov qword ptr [rbx + 16], r12 + - - 0.50 - - 0.50 - - mov al, 1 + - - 0.51 0.49 - - - - add rsp, 24 + - - - - - - 0.02 0.98 pop rbx + - - - - - - 0.03 0.97 pop r12 + - - - - - - 0.03 0.97 pop r13 + - - - - - - 0.97 0.03 pop r14 + - - - - - - 0.03 0.97 pop r15 + - - - - - - 0.01 0.99 pop rbp + - - - - - 1.00 - - ret + - - 0.49 0.51 - - - - mov r15, rsi + - - 0.51 0.49 - - - - mov rbp, rdx + - - 0.49 0.51 - - - - lea rcx, [rax + rax] + - - 0.49 0.50 - 0.01 - - cmp r12, rcx + - - 1.04 0.50 - 1.46 - - cmova rcx, r12 + - - 0.49 0.49 - 0.02 - - cmp rcx, 5 + - - 0.50 - - 0.50 - - mov r14d, 4 + - - 0.50 0.51 - 0.99 - - cmovae r14, rcx + - - - - - - 0.97 0.03 mov rdx, qword ptr [rbx + 8] + - - - 0.51 - 0.49 - - mov rdi, rsp + - - 0.01 0.50 - 0.49 - - mov rsi, rax + - - 0.49 0.50 - 0.01 - - mov rcx, r14 + - - - - 1.00 1.00 0.99 0.01 call <alloc::raw_vec::RawVecInner>::finish_grow + - - 0.51 0.49 - - 0.50 0.50 cmp dword ptr [rsp], 1 + - - - - - 1.00 - - je .LBB6_3 + - - - - - - 0.50 0.50 mov rax, qword ptr [rsp + 8] + - - - - 1.00 - 0.99 0.01 mov qword ptr [rbx + 8], rax + - - - - 1.00 - 0.01 0.99 mov qword ptr [rbx], r14 + - - 0.49 0.50 - 0.01 - - mov rdx, rbp + - - 0.50 0.01 - 0.49 - - mov rsi, r15 + - - - - - 1.00 - - jmp .LBB6_5 + - - 0.01 0.99 - - - - lea rdi, [rip + .Lanon.HASH.1] + - - 0.99 0.01 - - - - lea rdx, [rip + .Lanon.HASH.3] + - - 0.02 0.49 - 0.49 - - mov esi, 37 + - - - - 1.00 1.00 0.02 1.98 call qword ptr [rip + core::panicking::panic@GOTPCREL] diff --git a/rust/zerocopy/benches/new_box_zeroed.rs b/rust/zerocopy/benches/new_box_zeroed.rs new file mode 100644 index 000000000..aa9a66cce --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_new_box_zeroed() -> Option<Box<format::LocoPacket>> { + FromZeros::new_box_zeroed().ok() +} diff --git a/rust/zerocopy/benches/new_box_zeroed.x86-64 b/rust/zerocopy/benches/new_box_zeroed.x86-64 new file mode 100644 index 000000000..ef74ea538 --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed.x86-64 @@ -0,0 +1,7 @@ +bench_new_box_zeroed: + push rax + call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + mov edi, 6 + mov esi, 2 + pop rax + jmp qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] diff --git a/rust/zerocopy/benches/new_box_zeroed.x86-64.mca b/rust/zerocopy/benches/new_box_zeroed.x86-64.mca new file mode 100644 index 000000000..05afa7feb --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed.x86-64.mca @@ -0,0 +1,51 @@ +Iterations: 100 +Instructions: 600 +Total Cycles: 1197 +Total uOps: 1100 + +Dispatch Width: 4 +uOps Per Cycle: 0.92 +IPC: 0.50 +Block RThroughput: 2.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push rax + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + 1 1 0.33 mov edi, 6 + 1 1 0.33 mov esi, 2 + 1 6 0.50 * pop rax + 2 6 1.00 * jmp qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 2.00 2.01 2.07 2.93 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - 0.93 0.07 push rax + - - - - 1.00 1.00 0.12 1.88 call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + - - 0.99 - - 0.01 - - mov edi, 6 + - - - 1.00 - - - - mov esi, 2 + - - - - - - 0.94 0.06 pop rax + - - - - - 1.00 0.08 0.92 jmp qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..0afde999b --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_new_box_zeroed_with_elems_dynamic_padding( + count: usize, +) -> Option<Box<format::LocoPacket>> { + FromZeros::new_box_zeroed_with_elems(count).ok() +} diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..22a8d048c --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,24 @@ +bench_new_box_zeroed_with_elems_dynamic_padding: + push r14 + push rbx + push rax + mov rbx, rdi + movabs rax, 3074457345618258598 + cmp rdi, rax + ja .LBB5_1 + lea r14, [rbx + 2*rbx] + or r14, 3 + add r14, 9 + call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + mov esi, 4 + mov rdi, r14 + call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + jmp .LBB5_3 +.LBB5_1: + xor eax, eax +.LBB5_3: + mov rdx, rbx + add rsp, 8 + pop rbx + pop r14 + ret diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..e6efaeded --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,81 @@ +Iterations: 100 +Instructions: 2100 +Total Cycles: 2990 +Total uOps: 3000 + +Dispatch Width: 4 +uOps Per Cycle: 1.00 +IPC: 0.70 +Block RThroughput: 7.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 2 5 1.00 * push rax + 1 1 0.33 mov rbx, rdi + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdi, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r14, [rbx + 2*rbx] + 1 1 0.33 or r14, 3 + 1 1 0.33 add r14, 9 + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + 1 1 0.33 mov esi, 4 + 1 1 0.33 mov rdi, r14 + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + 1 1 1.00 jmp .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rbx + 1 1 0.33 add rsp, 8 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.49 4.50 5.00 6.01 4.50 4.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - 0.50 0.50 push r14 + - - - - 1.00 - 0.50 0.50 push rbx + - - - - 1.00 - 0.50 0.50 push rax + - - 0.49 0.50 - 0.01 - - mov rbx, rdi + - - 0.50 0.50 - - - - movabs rax, 3074457345618258598 + - - 0.50 0.50 - - - - cmp rdi, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.50 0.50 - - - - lea r14, [rbx + 2*rbx] + - - 0.50 0.50 - - - - or r14, 3 + - - 0.50 - - 0.50 - - add r14, 9 + - - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + - - - 0.50 - 0.50 - - mov esi, 4 + - - 0.50 0.50 - - - - mov rdi, r14 + - - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + - - - - - 1.00 - - jmp .LBB5_3 + - - - - - - - - xor eax, eax + - - 0.51 0.49 - - - - mov rdx, rbx + - - 0.49 0.51 - - - - add rsp, 8 + - - - - - - 0.50 0.50 pop rbx + - - - - - - 0.50 0.50 pop r14 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.rs b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.rs new file mode 100644 index 000000000..1b12ca220 --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_new_box_zeroed_with_elems_dynamic_size(count: usize) -> Option<Box<format::LocoPacket>> { + FromZeros::new_box_zeroed_with_elems(count).ok() +} diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..bff15e55a --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64 @@ -0,0 +1,22 @@ +bench_new_box_zeroed_with_elems_dynamic_size: + push r14 + push rbx + push rax + mov rbx, rdi + movabs rax, 4611686018427387901 + cmp rdi, rax + ja .LBB5_1 + lea r14, [2*rbx + 4] + call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + mov esi, 2 + mov rdi, r14 + call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + jmp .LBB5_3 +.LBB5_1: + xor eax, eax +.LBB5_3: + mov rdx, rbx + add rsp, 8 + pop rbx + pop r14 + ret diff --git a/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..153d36c01 --- /dev/null +++ b/rust/zerocopy/benches/new_box_zeroed_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 2990 +Total uOps: 2800 + +Dispatch Width: 4 +uOps Per Cycle: 0.94 +IPC: 0.64 +Block RThroughput: 7.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 2 5 1.00 * push rax + 1 1 0.33 mov rbx, rdi + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdi, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r14, [2*rbx + 4] + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + 1 1 0.33 mov esi, 2 + 1 1 0.33 mov rdi, r14 + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + 1 1 1.00 jmp .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rbx + 1 1 0.33 add rsp, 8 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.97 3.98 5.00 5.05 4.50 4.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - 0.50 0.50 push r14 + - - - - 1.00 - 0.50 0.50 push rbx + - - - - 1.00 - 0.50 0.50 push rax + - - 0.05 0.94 - 0.01 - - mov rbx, rdi + - - 0.94 0.06 - - - - movabs rax, 4611686018427387901 + - - 0.06 0.94 - - - - cmp rdi, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.94 0.06 - - - - lea r14, [2*rbx + 4] + - - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + - - 0.98 0.02 - - - - mov esi, 2 + - - 0.02 0.94 - 0.04 - - mov rdi, r14 + - - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + - - - - - 1.00 - - jmp .LBB5_3 + - - - - - - - - xor eax, eax + - - 0.94 0.06 - - - - mov rdx, rbx + - - 0.04 0.96 - - - - add rsp, 8 + - - - - - - 0.50 0.50 pop rbx + - - - - - - 0.50 0.50 pop r14 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/new_vec_zeroed.rs b/rust/zerocopy/benches/new_vec_zeroed.rs new file mode 100644 index 000000000..3d95b2b24 --- /dev/null +++ b/rust/zerocopy/benches/new_vec_zeroed.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_new_vec_zeroed(len: usize) -> Option<Vec<format::LocoPacket>> { + FromZeros::new_vec_zeroed(len).ok() +} diff --git a/rust/zerocopy/benches/new_vec_zeroed.x86-64 b/rust/zerocopy/benches/new_vec_zeroed.x86-64 new file mode 100644 index 000000000..b5c083aa0 --- /dev/null +++ b/rust/zerocopy/benches/new_vec_zeroed.x86-64 @@ -0,0 +1,40 @@ +bench_new_vec_zeroed: + mov rax, rdi + movabs rcx, 1537228672809129301 + cmp rsi, rcx + ja .LBB5_5 + test rsi, rsi + je .LBB5_2 + push r15 + push r14 + push rbx + lea rcx, [rsi + rsi] + lea rbx, [rcx + 2*rcx] + mov r14, rax + mov r15, rsi + call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + mov esi, 2 + mov rdi, rbx + call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + mov rsi, r15 + mov rcx, rax + mov rax, r14 + test rcx, rcx + pop rbx + pop r14 + pop r15 + je .LBB5_5 + mov qword ptr [rax], rsi + mov qword ptr [rax + 8], rcx + mov qword ptr [rax + 16], rsi + ret +.LBB5_5: + movabs rcx, -9223372036854775808 + mov qword ptr [rax], rcx + ret +.LBB5_2: + mov ecx, 2 + mov qword ptr [rax], rsi + mov qword ptr [rax + 8], rcx + mov qword ptr [rax + 16], rsi + ret diff --git a/rust/zerocopy/benches/new_vec_zeroed.x86-64.mca b/rust/zerocopy/benches/new_vec_zeroed.x86-64.mca new file mode 100644 index 000000000..b4fb4544e --- /dev/null +++ b/rust/zerocopy/benches/new_vec_zeroed.x86-64.mca @@ -0,0 +1,113 @@ +Iterations: 100 +Instructions: 3700 +Total Cycles: 3486 +Total uOps: 4600 + +Dispatch Width: 4 +uOps Per Cycle: 1.32 +IPC: 1.06 +Block RThroughput: 12.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.33 movabs rcx, 1537228672809129301 + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 ja .LBB5_5 + 1 1 0.33 test rsi, rsi + 1 1 1.00 je .LBB5_2 + 2 5 1.00 * push r15 + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 1 1 0.50 lea rcx, [rsi + rsi] + 1 1 0.50 lea rbx, [rcx + 2*rcx] + 1 1 0.33 mov r14, rax + 1 1 0.33 mov r15, rsi + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + 1 1 0.33 mov esi, 2 + 1 1 0.33 mov rdi, rbx + 4 7 1.00 * call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + 1 1 0.33 mov rsi, r15 + 1 1 0.33 mov rcx, rax + 1 1 0.33 mov rax, r14 + 1 1 0.33 test rcx, rcx + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 6 0.50 * pop r15 + 1 1 1.00 je .LBB5_5 + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 * mov qword ptr [rax + 8], rcx + 1 1 1.00 * mov qword ptr [rax + 16], rsi + 1 1 1.00 U ret + 1 1 0.33 movabs rcx, -9223372036854775808 + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 U ret + 1 1 0.33 mov ecx, 2 + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 * mov qword ptr [rax + 8], rcx + 1 1 1.00 * mov qword ptr [rax + 16], rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.99 6.99 12.00 10.02 8.00 9.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.01 0.98 - 0.01 - - mov rax, rdi + - - 0.98 0.02 - - - - movabs rcx, 1537228672809129301 + - - 0.02 0.98 - - - - cmp rsi, rcx + - - - - - 1.00 - - ja .LBB5_5 + - - 0.98 - - 0.02 - - test rsi, rsi + - - - - - 1.00 - - je .LBB5_2 + - - - - 1.00 - - 1.00 push r15 + - - - - 1.00 - 1.00 - push r14 + - - - - 1.00 - - 1.00 push rbx + - - - 1.00 - - - - lea rcx, [rsi + rsi] + - - - 1.00 - - - - lea rbx, [rcx + 2*rcx] + - - 1.00 - - - - - mov r14, rax + - - 1.00 - - - - - mov r15, rsi + - - - - 1.00 1.00 2.00 - call qword ptr [rip + __rustc::__rust_no_alloc_shim_is_unstable_v2@GOTPCREL] + - - - 0.01 - 0.99 - - mov esi, 2 + - - 0.01 0.99 - - - - mov rdi, rbx + - - - - 1.00 1.00 - 2.00 call qword ptr [rip + __rustc::__rust_alloc_zeroed@GOTPCREL] + - - 0.01 - - 0.99 - - mov rsi, r15 + - - 0.99 0.01 - - - - mov rcx, rax + - - - 0.99 - 0.01 - - mov rax, r14 + - - 0.99 0.01 - - - - test rcx, rcx + - - - - - - - 1.00 pop rbx + - - - - - - 1.00 - pop r14 + - - - - - - - 1.00 pop r15 + - - - - - 1.00 - - je .LBB5_5 + - - - - 1.00 - 1.00 - mov qword ptr [rax], rsi + - - - - 1.00 - - 1.00 mov qword ptr [rax + 8], rcx + - - - - 1.00 - 1.00 - mov qword ptr [rax + 16], rsi + - - - - - 1.00 - - ret + - - 0.01 0.99 - - - - movabs rcx, -9223372036854775808 + - - - - 1.00 - - 1.00 mov qword ptr [rax], rcx + - - - - - 1.00 - - ret + - - 0.99 0.01 - - - - mov ecx, 2 + - - - - 1.00 - 1.00 - mov qword ptr [rax], rsi + - - - - 1.00 - - 1.00 mov qword ptr [rax + 8], rcx + - - - - 1.00 - 1.00 - mov qword ptr [rax + 16], rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/new_zeroed.rs b/rust/zerocopy/benches/new_zeroed.rs new file mode 100644 index 000000000..b49f62edb --- /dev/null +++ b/rust/zerocopy/benches/new_zeroed.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_new_zeroed() -> format::LocoPacket { + FromZeros::new_zeroed() +} diff --git a/rust/zerocopy/benches/new_zeroed.x86-64 b/rust/zerocopy/benches/new_zeroed.x86-64 new file mode 100644 index 000000000..b4d305e41 --- /dev/null +++ b/rust/zerocopy/benches/new_zeroed.x86-64 @@ -0,0 +1,3 @@ +bench_new_zeroed: + xor eax, eax + ret diff --git a/rust/zerocopy/benches/new_zeroed.x86-64.mca b/rust/zerocopy/benches/new_zeroed.x86-64.mca new file mode 100644 index 000000000..44583ca30 --- /dev/null +++ b/rust/zerocopy/benches/new_zeroed.x86-64.mca @@ -0,0 +1,43 @@ +Iterations: 100 +Instructions: 200 +Total Cycles: 103 +Total uOps: 200 + +Dispatch Width: 4 +uOps Per Cycle: 1.94 +IPC: 1.94 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - - - - 1.00 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/read_from_bytes.rs b/rust/zerocopy/benches/read_from_bytes.rs new file mode 100644 index 000000000..8a3baddad --- /dev/null +++ b/rust/zerocopy/benches/read_from_bytes.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_read_from_bytes_static_size(source: &[u8]) -> Option<format::LocoPacket> { + zerocopy::FromBytes::read_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/read_from_bytes.x86-64 b/rust/zerocopy/benches/read_from_bytes.x86-64 new file mode 100644 index 000000000..9082d79f1 --- /dev/null +++ b/rust/zerocopy/benches/read_from_bytes.x86-64 @@ -0,0 +1,15 @@ +bench_read_from_bytes_static_size: + mov rcx, rsi + cmp rsi, 6 + jne .LBB5_2 + mov eax, dword ptr [rdi] + movzx ecx, word ptr [rdi + 4] + shl rcx, 32 + or rcx, rax +.LBB5_2: + shl rcx, 16 + inc rcx + xor eax, eax + cmp rsi, 6 + cmove rax, rcx + ret diff --git a/rust/zerocopy/benches/read_from_bytes.x86-64.mca b/rust/zerocopy/benches/read_from_bytes.x86-64.mca new file mode 100644 index 000000000..77e787c19 --- /dev/null +++ b/rust/zerocopy/benches/read_from_bytes.x86-64.mca @@ -0,0 +1,65 @@ +Iterations: 100 +Instructions: 1300 +Total Cycles: 377 +Total uOps: 1400 + +Dispatch Width: 4 +uOps Per Cycle: 3.71 +IPC: 3.45 +Block RThroughput: 3.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rcx, rsi + 1 1 0.33 cmp rsi, 6 + 1 1 1.00 jne .LBB5_2 + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 5 0.50 * movzx ecx, word ptr [rdi + 4] + 1 1 0.50 shl rcx, 32 + 1 1 0.33 or rcx, rax + 1 1 0.50 shl rcx, 16 + 1 1 0.33 inc rcx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp rsi, 6 + 2 2 0.67 cmove rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.66 3.67 - 3.67 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.63 0.36 - 0.01 - - mov rcx, rsi + - - 0.05 0.05 - 0.90 - - cmp rsi, 6 + - - - - - 1.00 - - jne .LBB5_2 + - - - - - - - 1.00 mov eax, dword ptr [rdi] + - - - - - - 1.00 - movzx ecx, word ptr [rdi + 4] + - - 0.97 - - 0.03 - - shl rcx, 32 + - - 0.02 0.35 - 0.63 - - or rcx, rax + - - 0.98 - - 0.02 - - shl rcx, 16 + - - - 0.98 - 0.02 - - inc rcx + - - - - - - - - xor eax, eax + - - 0.03 0.93 - 0.04 - - cmp rsi, 6 + - - 0.98 1.00 - 0.02 - - cmove rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/read_from_prefix.rs b/rust/zerocopy/benches/read_from_prefix.rs new file mode 100644 index 000000000..d49bf80ab --- /dev/null +++ b/rust/zerocopy/benches/read_from_prefix.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_read_from_prefix_static_size(source: &[u8]) -> Option<format::LocoPacket> { + match zerocopy::FromBytes::read_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/read_from_prefix.x86-64 b/rust/zerocopy/benches/read_from_prefix.x86-64 new file mode 100644 index 000000000..c75b06c0c --- /dev/null +++ b/rust/zerocopy/benches/read_from_prefix.x86-64 @@ -0,0 +1,14 @@ +bench_read_from_prefix_static_size: + cmp rsi, 5 + jbe .LBB5_2 + mov eax, dword ptr [rdi] + movzx edi, word ptr [rdi + 4] + shl rdi, 32 + or rdi, rax +.LBB5_2: + shl rdi, 16 + inc rdi + xor eax, eax + cmp rsi, 6 + cmovae rax, rdi + ret diff --git a/rust/zerocopy/benches/read_from_prefix.x86-64.mca b/rust/zerocopy/benches/read_from_prefix.x86-64.mca new file mode 100644 index 000000000..04e76cdd0 --- /dev/null +++ b/rust/zerocopy/benches/read_from_prefix.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 905 +Total uOps: 1300 + +Dispatch Width: 4 +uOps Per Cycle: 1.44 +IPC: 1.33 +Block RThroughput: 3.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 cmp rsi, 5 + 1 1 1.00 jbe .LBB5_2 + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 5 0.50 * movzx edi, word ptr [rdi + 4] + 1 1 0.50 shl rdi, 32 + 1 1 0.33 or rdi, rax + 1 1 0.50 shl rdi, 16 + 1 1 0.33 inc rdi + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp rsi, 6 + 2 2 0.67 cmovae rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.32 3.32 - 3.36 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.05 0.94 - 0.01 - - cmp rsi, 5 + - - - - - 1.00 - - jbe .LBB5_2 + - - - - - - - 1.00 mov eax, dword ptr [rdi] + - - - - - - 1.00 - movzx edi, word ptr [rdi + 4] + - - 0.71 - - 0.29 - - shl rdi, 32 + - - - 0.64 - 0.36 - - or rdi, rax + - - 1.00 - - - - - shl rdi, 16 + - - 0.31 0.40 - 0.29 - - inc rdi + - - - - - - - - xor eax, eax + - - 0.34 0.35 - 0.31 - - cmp rsi, 6 + - - 0.91 0.99 - 0.10 - - cmovae rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/read_from_suffix.rs b/rust/zerocopy/benches/read_from_suffix.rs new file mode 100644 index 000000000..4eaadb0d4 --- /dev/null +++ b/rust/zerocopy/benches/read_from_suffix.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_read_from_suffix_static_size(source: &[u8]) -> Option<format::LocoPacket> { + match zerocopy::FromBytes::read_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/read_from_suffix.x86-64 b/rust/zerocopy/benches/read_from_suffix.x86-64 new file mode 100644 index 000000000..5cff2a0e2 --- /dev/null +++ b/rust/zerocopy/benches/read_from_suffix.x86-64 @@ -0,0 +1,15 @@ +bench_read_from_suffix_static_size: + mov rcx, rsi + cmp rsi, 6 + jb .LBB5_2 + mov eax, dword ptr [rdi + rsi - 6] + movzx ecx, word ptr [rdi + rsi - 2] + shl rcx, 32 + or rcx, rax +.LBB5_2: + shl rcx, 16 + inc rcx + xor eax, eax + cmp rsi, 6 + cmovae rax, rcx + ret diff --git a/rust/zerocopy/benches/read_from_suffix.x86-64.mca b/rust/zerocopy/benches/read_from_suffix.x86-64.mca new file mode 100644 index 000000000..0107de895 --- /dev/null +++ b/rust/zerocopy/benches/read_from_suffix.x86-64.mca @@ -0,0 +1,65 @@ +Iterations: 100 +Instructions: 1300 +Total Cycles: 377 +Total uOps: 1400 + +Dispatch Width: 4 +uOps Per Cycle: 3.71 +IPC: 3.45 +Block RThroughput: 3.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rcx, rsi + 1 1 0.33 cmp rsi, 6 + 1 1 1.00 jb .LBB5_2 + 1 5 0.50 * mov eax, dword ptr [rdi + rsi - 6] + 1 5 0.50 * movzx ecx, word ptr [rdi + rsi - 2] + 1 1 0.50 shl rcx, 32 + 1 1 0.33 or rcx, rax + 1 1 0.50 shl rcx, 16 + 1 1 0.33 inc rcx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp rsi, 6 + 2 2 0.67 cmovae rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.66 3.67 - 3.67 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.63 0.36 - 0.01 - - mov rcx, rsi + - - 0.05 0.05 - 0.90 - - cmp rsi, 6 + - - - - - 1.00 - - jb .LBB5_2 + - - - - - - - 1.00 mov eax, dword ptr [rdi + rsi - 6] + - - - - - - 1.00 - movzx ecx, word ptr [rdi + rsi - 2] + - - 0.97 - - 0.03 - - shl rcx, 32 + - - 0.02 0.35 - 0.63 - - or rcx, rax + - - 0.98 - - 0.02 - - shl rcx, 16 + - - - 0.98 - 0.02 - - inc rcx + - - - - - - - - xor eax, eax + - - 0.03 0.93 - 0.04 - - cmp rsi, 6 + - - 0.98 1.00 - 0.02 - - cmovae rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.rs new file mode 100644 index 000000000..29708df55 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_bytes_dynamic_padding(source: &[u8]) -> Option<&format::LocoPacket> { + zerocopy::FromBytes::ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64 new file mode 100644 index 000000000..e844a4608 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64 @@ -0,0 +1,22 @@ +bench_ref_from_bytes_dynamic_padding: + test dil, 3 + jne .LBB5_3 + movabs rax, 9223372036854775804 + and rax, rsi + cmp rax, 9 + jb .LBB5_3 + add rax, -9 + movabs rcx, -6148914691236517205 + mul rcx + shr rdx + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + cmp rsi, rax + je .LBB5_4 +.LBB5_3: + xor edi, edi + mov rdx, rsi +.LBB5_4: + mov rax, rdi + ret diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..423ed38ba --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_padding.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 645 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 3.10 +IPC: 2.95 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 test dil, 3 + 1 1 1.00 jne .LBB5_3 + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rax, rsi + 1 1 0.33 cmp rax, 9 + 1 1 1.00 jb .LBB5_3 + 1 1 0.33 add rax, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 2 4 1.00 mul rcx + 1 1 0.50 shr rdx + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 1 0.33 cmp rsi, rax + 1 1 1.00 je .LBB5_4 + 1 0 0.25 xor edi, edi + 1 1 0.33 mov rdx, rsi + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.32 6.33 - 6.35 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.64 0.35 - 0.01 - - test dil, 3 + - - - - - 1.00 - - jne .LBB5_3 + - - 0.34 0.65 - 0.01 - - movabs rax, 9223372036854775804 + - - 0.35 0.65 - - - - and rax, rsi + - - 0.33 0.34 - 0.33 - - cmp rax, 9 + - - - - - 1.00 - - jb .LBB5_3 + - - 0.35 - - 0.65 - - add rax, -9 + - - 0.97 0.01 - 0.02 - - movabs rcx, -6148914691236517205 + - - 1.00 1.00 - - - - mul rcx + - - 0.99 - - 0.01 - - shr rdx + - - 0.33 0.67 - - - - lea rax, [rdx + 2*rdx] + - - 0.34 0.66 - - - - or rax, 3 + - - 0.33 0.66 - 0.01 - - add rax, 9 + - - 0.01 0.99 - - - - cmp rsi, rax + - - - - - 1.00 - - je .LBB5_4 + - - - - - - - - xor edi, edi + - - 0.32 0.01 - 0.67 - - mov rdx, rsi + - - 0.02 0.34 - 0.64 - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_size.rs b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.rs new file mode 100644 index 000000000..4eb4f970e --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_bytes_dynamic_size(source: &[u8]) -> Option<&format::LocoPacket> { + zerocopy::FromBytes::ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64 new file mode 100644 index 000000000..cc905b76c --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64 @@ -0,0 +1,20 @@ +bench_ref_from_bytes_dynamic_size: + mov rdx, rsi + cmp rsi, 4 + setb al + or al, dil + test al, 1 + je .LBB5_2 + xor eax, eax + ret +.LBB5_2: + lea rcx, [rdx - 4] + mov rsi, rcx + and rsi, -2 + add rsi, 4 + shr rcx + xor eax, eax + cmp rdx, rsi + cmove rdx, rcx + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64.mca new file mode 100644 index 000000000..68aea583e --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_dynamic_size.x86-64.mca @@ -0,0 +1,75 @@ +Iterations: 100 +Instructions: 1800 +Total Cycles: 704 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 2.84 +IPC: 2.56 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rdx, rsi + 1 1 0.33 cmp rsi, 4 + 1 1 0.50 setb al + 1 1 0.33 or al, dil + 1 1 0.33 test al, 1 + 1 1 1.00 je .LBB5_2 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.50 lea rcx, [rdx - 4] + 1 1 0.33 mov rsi, rcx + 1 1 0.33 and rsi, -2 + 1 1 0.33 add rsi, 4 + 1 1 0.50 shr rcx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp rdx, rsi + 2 2 0.67 cmove rdx, rcx + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.97 5.98 - 6.05 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.97 0.01 - 0.02 - - mov rdx, rsi + - - 0.01 0.02 - 0.97 - - cmp rsi, 4 + - - 0.03 - - 0.97 - - setb al + - - 0.01 0.02 - 0.97 - - or al, dil + - - - 0.98 - 0.02 - - test al, 1 + - - - - - 1.00 - - je .LBB5_2 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.98 0.02 - - - - lea rcx, [rdx - 4] + - - 0.01 0.99 - - - - mov rsi, rcx + - - - 0.98 - 0.02 - - and rsi, -2 + - - 0.98 0.01 - 0.01 - - add rsi, 4 + - - 0.99 - - 0.01 - - shr rcx + - - - - - - - - xor eax, eax + - - 0.02 0.97 - 0.01 - - cmp rdx, rsi + - - 0.99 0.99 - 0.02 - - cmove rdx, rcx + - - 0.98 0.99 - 0.03 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_bytes_static_size.rs b/rust/zerocopy/benches/ref_from_bytes_static_size.rs new file mode 100644 index 000000000..3742bba07 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_static_size.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_bytes_static_size(source: &[u8]) -> Option<&format::LocoPacket> { + zerocopy::FromBytes::ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64 b/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64 new file mode 100644 index 000000000..2c8da68c8 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64 @@ -0,0 +1,8 @@ +bench_ref_from_bytes_static_size: + mov ecx, edi + and ecx, 1 + xor rsi, 6 + xor eax, eax + or rsi, rcx + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64.mca b/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64.mca new file mode 100644 index 000000000..832697801 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_static_size.x86-64.mca @@ -0,0 +1,53 @@ +Iterations: 100 +Instructions: 700 +Total Cycles: 240 +Total uOps: 800 + +Dispatch Width: 4 +uOps Per Cycle: 3.33 +IPC: 2.92 +Block RThroughput: 2.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov ecx, edi + 1 1 0.33 and ecx, 1 + 1 1 0.33 xor rsi, 6 + 1 0 0.25 xor eax, eax + 1 1 0.33 or rsi, rcx + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.33 2.33 - 2.34 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.01 0.98 - 0.01 - - mov ecx, edi + - - 0.02 0.66 - 0.32 - - and ecx, 1 + - - 0.33 0.66 - 0.01 - - xor rsi, 6 + - - - - - - - - xor eax, eax + - - 0.98 0.02 - - - - or rsi, rcx + - - 0.99 0.01 - 1.00 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..b4fea4aee --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_bytes_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + zerocopy::FromBytes::ref_from_bytes_with_elems(source, count).ok() +} diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..d579b3fae --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,19 @@ +bench_ref_from_bytes_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + seta cl + mov rax, rdi + test al, 3 + setne dil + or dil, cl + jne .LBB5_2 + lea rcx, [rdx + 2*rdx] + or rcx, 3 + add rcx, 9 + cmp rsi, rcx + je .LBB5_3 +.LBB5_2: + xor eax, eax + mov rdx, rsi +.LBB5_3: + ret diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..ea2d83dbd --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,71 @@ +Iterations: 100 +Instructions: 1600 +Total Cycles: 539 +Total uOps: 1700 + +Dispatch Width: 4 +uOps Per Cycle: 3.15 +IPC: 2.97 +Block RThroughput: 4.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 2 2 1.00 seta cl + 1 1 0.33 mov rax, rdi + 1 1 0.33 test al, 3 + 1 1 0.50 setne dil + 1 1 0.33 or dil, cl + 1 1 1.00 jne .LBB5_2 + 1 1 0.50 lea rcx, [rdx + 2*rdx] + 1 1 0.33 or rcx, 3 + 1 1 0.33 add rcx, 9 + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 je .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.33 5.32 - 5.35 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.01 0.98 - 0.01 - - movabs rax, 3074457345618258598 + - - - 1.00 - - - - cmp rdx, rax + - - 1.98 - - 0.02 - - seta cl + - - 0.02 0.98 - - - - mov rax, rdi + - - - 0.67 - 0.33 - - test al, 3 + - - 0.67 - - 0.33 - - setne dil + - - 0.99 - - 0.01 - - or dil, cl + - - - - - 1.00 - - jne .LBB5_2 + - - 0.01 0.99 - - - - lea rcx, [rdx + 2*rdx] + - - - 0.01 - 0.99 - - or rcx, 3 + - - 0.65 0.02 - 0.33 - - add rcx, 9 + - - 0.99 0.01 - - - - cmp rsi, rcx + - - - - - 1.00 - - je .LBB5_3 + - - - - - - - - xor eax, eax + - - 0.01 0.66 - 0.33 - - mov rdx, rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.rs b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.rs new file mode 100644 index 000000000..9d33a7c31 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_bytes_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + zerocopy::FromBytes::ref_from_bytes_with_elems(source, count).ok() +} diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..3d8d15b7f --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64 @@ -0,0 +1,16 @@ +bench_ref_from_bytes_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + seta cl + mov rax, rdi + or dil, cl + test dil, 1 + jne .LBB5_2 + lea rcx, [2*rdx + 4] + cmp rsi, rcx + je .LBB5_3 +.LBB5_2: + xor eax, eax + mov rdx, rsi +.LBB5_3: + ret diff --git a/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..602179f3c --- /dev/null +++ b/rust/zerocopy/benches/ref_from_bytes_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,65 @@ +Iterations: 100 +Instructions: 1300 +Total Cycles: 439 +Total uOps: 1400 + +Dispatch Width: 4 +uOps Per Cycle: 3.19 +IPC: 2.96 +Block RThroughput: 3.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 2 2 1.00 seta cl + 1 1 0.33 mov rax, rdi + 1 1 0.33 or dil, cl + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_2 + 1 1 0.50 lea rcx, [2*rdx + 4] + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 je .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.32 4.33 - 4.35 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - movabs rax, 4611686018427387901 + - - 0.33 0.67 - - - - cmp rdx, rax + - - 1.98 - - 0.02 - - seta cl + - - 0.01 0.99 - - - - mov rax, rdi + - - 1.00 - - - - - or dil, cl + - - 0.99 0.01 - - - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_2 + - - - 1.00 - - - - lea rcx, [2*rdx + 4] + - - 0.01 - - 0.99 - - cmp rsi, rcx + - - - - - 1.00 - - je .LBB5_3 + - - - - - - - - xor eax, eax + - - - 0.67 - 0.33 - - mov rdx, rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.rs new file mode 100644 index 000000000..53c707b88 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_prefix_dynamic_padding(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64 new file mode 100644 index 000000000..a58592a24 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64 @@ -0,0 +1,22 @@ +bench_ref_from_prefix_dynamic_padding: + xor edx, edx + mov eax, 0 + test dil, 3 + je .LBB5_1 + ret +.LBB5_1: + movabs rax, 9223372036854775804 + and rsi, rax + cmp rsi, 9 + jae .LBB5_3 + mov edx, 1 + xor eax, eax + ret +.LBB5_3: + add rsi, -9 + movabs rcx, -6148914691236517205 + mov rax, rsi + mul rcx + shr rdx + mov rax, rdi + ret diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..62ea4baba --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_padding.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 608 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 3.29 +IPC: 3.13 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 3 + 1 1 1.00 je .LBB5_1 + 1 1 1.00 U ret + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rsi, rax + 1 1 0.33 cmp rsi, 9 + 1 1 1.00 jae .LBB5_3 + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rsi, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 1 1 0.33 mov rax, rsi + 2 4 1.00 mul rcx + 1 1 0.50 shr rdx + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.00 6.00 - 6.00 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor edx, edx + - - 0.01 0.98 - 0.01 - - mov eax, 0 + - - 0.98 0.01 - 0.01 - - test dil, 3 + - - - - - 1.00 - - je .LBB5_1 + - - - - - 1.00 - - ret + - - 0.01 0.99 - - - - movabs rax, 9223372036854775804 + - - - 1.00 - - - - and rsi, rax + - - - 1.00 - - - - cmp rsi, 9 + - - - - - 1.00 - - jae .LBB5_3 + - - 1.00 - - - - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.02 0.02 - 0.96 - - add rsi, -9 + - - 0.99 0.01 - - - - movabs rcx, -6148914691236517205 + - - 0.01 0.99 - - - - mov rax, rsi + - - 1.00 1.00 - - - - mul rcx + - - 1.00 - - - - - shr rdx + - - 0.98 - - 0.02 - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_size.rs b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.rs new file mode 100644 index 000000000..a3f26f6b4 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_prefix_dynamic_size(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64 new file mode 100644 index 000000000..fe6332c91 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64 @@ -0,0 +1,17 @@ +bench_ref_from_prefix_dynamic_size: + xor edx, edx + mov eax, 0 + test dil, 1 + jne .LBB5_4 + cmp rsi, 4 + jae .LBB5_3 + mov edx, 1 + xor eax, eax + ret +.LBB5_3: + add rsi, -4 + shr rsi + mov rdx, rsi + mov rax, rdi +.LBB5_4: + ret diff --git a/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..3900a5946 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_dynamic_size.x86-64.mca @@ -0,0 +1,67 @@ +Iterations: 100 +Instructions: 1400 +Total Cycles: 405 +Total uOps: 1400 + +Dispatch Width: 4 +uOps Per Cycle: 3.46 +IPC: 3.46 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_4 + 1 1 0.33 cmp rsi, 4 + 1 1 1.00 jae .LBB5_3 + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rsi, -4 + 1 1 0.50 shr rsi + 1 1 0.33 mov rdx, rsi + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.99 3.99 - 4.02 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor edx, edx + - - 0.01 0.98 - 0.01 - - mov eax, 0 + - - 0.98 0.02 - - - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.02 0.98 - - - - cmp rsi, 4 + - - - - - 1.00 - - jae .LBB5_3 + - - 0.98 0.01 - 0.01 - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.01 0.99 - - - - add rsi, -4 + - - 1.00 - - - - - shr rsi + - - - 1.00 - - - - mov rdx, rsi + - - 0.99 0.01 - - - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_prefix_static_size.rs b/rust/zerocopy/benches/ref_from_prefix_static_size.rs new file mode 100644 index 000000000..834fa3928 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_static_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_prefix_static_size(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64 b/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64 new file mode 100644 index 000000000..7c1bf45bb --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64 @@ -0,0 +1,8 @@ +bench_ref_from_prefix_static_size: + xor eax, eax + cmp rsi, 6 + mov rcx, rdi + cmovb rcx, rax + test dil, 1 + cmove rax, rcx + ret diff --git a/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64.mca b/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64.mca new file mode 100644 index 000000000..9691b88fe --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_static_size.x86-64.mca @@ -0,0 +1,53 @@ +Iterations: 100 +Instructions: 700 +Total Cycles: 274 +Total uOps: 900 + +Dispatch Width: 4 +uOps Per Cycle: 3.28 +IPC: 2.55 +Block RThroughput: 2.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp rsi, 6 + 1 1 0.33 mov rcx, rdi + 2 2 0.67 cmovb rcx, rax + 1 1 0.33 test dil, 1 + 2 2 0.67 cmove rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.66 2.67 - 2.67 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor eax, eax + - - - 0.01 - 0.99 - - cmp rsi, 6 + - - 0.01 0.67 - 0.32 - - mov rcx, rdi + - - 1.00 0.99 - 0.01 - - cmovb rcx, rax + - - 0.66 0.01 - 0.33 - - test dil, 1 + - - 0.99 0.99 - 0.02 - - cmove rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..55d495e00 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_prefix_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_prefix_with_elems(source, count) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..5b31277bd --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,26 @@ +bench_ref_from_prefix_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + ja .LBB5_1 + xor ecx, ecx + mov eax, 0 + test dil, 3 + je .LBB5_3 + mov rdx, rcx + ret +.LBB5_1: + mov edx, 1 + xor eax, eax + ret +.LBB5_3: + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + xor r8d, r8d + cmp rax, rsi + mov ecx, 1 + cmovbe rcx, rdx + cmova rdi, r8 + mov rax, rdi + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..2f212ec6d --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,85 @@ +Iterations: 100 +Instructions: 2300 +Total Cycles: 807 +Total uOps: 2700 + +Dispatch Width: 4 +uOps Per Cycle: 3.35 +IPC: 2.85 +Block RThroughput: 6.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 3 + 1 1 1.00 je .LBB5_3 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 0 0.25 xor r8d, r8d + 1 1 0.33 cmp rax, rsi + 1 1 0.33 mov ecx, 1 + 3 3 1.00 cmovbe rcx, rdx + 3 3 1.00 cmova rdi, r8 + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 7.99 7.99 - 8.02 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.47 0.52 - 0.01 - - movabs rax, 3074457345618258598 + - - 0.94 0.01 - 0.05 - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - - - - - - - xor ecx, ecx + - - 0.03 0.97 - - - - mov eax, 0 + - - 0.01 0.52 - 0.47 - - test dil, 3 + - - - - - 1.00 - - je .LBB5_3 + - - 0.03 0.51 - 0.46 - - mov rdx, rcx + - - - - - 1.00 - - ret + - - 0.04 0.96 - - - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.01 0.99 - - - - lea rax, [rdx + 2*rdx] + - - 0.52 0.48 - - - - or rax, 3 + - - 0.51 0.49 - - - - add rax, 9 + - - - - - - - - xor r8d, r8d + - - 0.97 0.03 - - - - cmp rax, rsi + - - 0.01 0.99 - - - - mov ecx, 1 + - - 1.04 0.97 - 0.99 - - cmovbe rcx, rdx + - - 1.44 0.54 - 1.02 - - cmova rdi, r8 + - - 0.97 0.01 - 0.02 - - mov rax, rdi + - - 1.00 - - - - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.rs b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.rs new file mode 100644 index 000000000..e9663c721 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_prefix_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_prefix_with_elems(source, count) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..069fd4859 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64 @@ -0,0 +1,22 @@ +bench_ref_from_prefix_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + ja .LBB5_1 + mov rcx, rdx + xor edx, edx + mov eax, 0 + test dil, 1 + jne .LBB5_4 + lea rax, [2*rcx + 4] + xor r8d, r8d + cmp rax, rsi + mov edx, 1 + cmovbe rdx, rcx + cmova rdi, r8 + mov rax, rdi +.LBB5_4: + ret +.LBB5_1: + mov edx, 1 + xor eax, eax + ret diff --git a/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..6f2272640 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_prefix_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 672 +Total uOps: 2300 + +Dispatch Width: 4 +uOps Per Cycle: 3.42 +IPC: 2.83 +Block RThroughput: 5.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.33 mov rcx, rdx + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_4 + 1 1 0.50 lea rax, [2*rcx + 4] + 1 0 0.25 xor r8d, r8d + 1 1 0.33 cmp rax, rsi + 1 1 0.33 mov edx, 1 + 3 3 1.00 cmovbe rdx, rcx + 3 3 1.00 cmova rdi, r8 + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.66 6.66 - 6.68 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - movabs rax, 4611686018427387901 + - - 0.37 0.63 - - - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.63 0.37 - - - - mov rcx, rdx + - - - - - - - - xor edx, edx + - - 0.01 0.98 - 0.01 - - mov eax, 0 + - - 0.98 0.02 - - - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.01 0.99 - - - - lea rax, [2*rcx + 4] + - - - - - - - - xor r8d, r8d + - - 1.00 - - - - - cmp rax, rsi + - - - 0.67 - 0.33 - - mov edx, 1 + - - 0.73 0.98 - 1.29 - - cmovbe rdx, rcx + - - 1.60 0.36 - 1.04 - - cmova rdi, r8 + - - 0.99 0.01 - - - - mov rax, rdi + - - - - - 1.00 - - ret + - - 0.34 0.66 - - - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.rs new file mode 100644 index 000000000..5a6ea3a33 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_suffix_dynamic_padding(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64 new file mode 100644 index 000000000..3e05f6023 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64 @@ -0,0 +1,23 @@ +bench_ref_from_suffix_dynamic_padding: + lea eax, [rsi + rdi] + test al, 3 + jne .LBB5_1 + movabs rax, 9223372036854775804 + and rax, rsi + cmp rax, 9 + jae .LBB5_3 +.LBB5_1: + xor eax, eax + ret +.LBB5_3: + add rax, -9 + movabs rcx, -6148914691236517205 + mul rcx + shr rdx + lea rax, [rdx + 2*rdx] + sub rsi, rax + or rax, -4 + add rsi, rdi + add rax, rsi + add rax, -8 + ret diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..73599d5b6 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_padding.x86-64.mca @@ -0,0 +1,79 @@ +Iterations: 100 +Instructions: 2000 +Total Cycles: 682 +Total uOps: 2100 + +Dispatch Width: 4 +uOps Per Cycle: 3.08 +IPC: 2.93 +Block RThroughput: 5.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea eax, [rsi + rdi] + 1 1 0.33 test al, 3 + 1 1 1.00 jne .LBB5_1 + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rax, rsi + 1 1 0.33 cmp rax, 9 + 1 1 1.00 jae .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rax, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 2 4 1.00 mul rcx + 1 1 0.50 shr rdx + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 sub rsi, rax + 1 1 0.33 or rax, -4 + 1 1 0.33 add rsi, rdi + 1 1 0.33 add rax, rsi + 1 1 0.33 add rax, -8 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.65 6.67 - 6.68 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.90 0.10 - - - - lea eax, [rsi + rdi] + - - 0.93 - - 0.07 - - test al, 3 + - - - - - 1.00 - - jne .LBB5_1 + - - 0.51 0.47 - 0.02 - - movabs rax, 9223372036854775804 + - - - - - 1.00 - - and rax, rsi + - - - 0.09 - 0.91 - - cmp rax, 9 + - - - - - 1.00 - - jae .LBB5_3 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.43 0.47 - 0.10 - - add rax, -9 + - - 0.42 0.39 - 0.19 - - movabs rcx, -6148914691236517205 + - - 1.00 1.00 - - - - mul rcx + - - 0.69 - - 0.31 - - shr rdx + - - 0.54 0.46 - - - - lea rax, [rdx + 2*rdx] + - - 0.07 0.91 - 0.02 - - sub rsi, rax + - - 0.91 0.05 - 0.04 - - or rax, -4 + - - 0.08 0.90 - 0.02 - - add rsi, rdi + - - 0.09 0.91 - - - - add rax, rsi + - - 0.08 0.92 - - - - add rax, -8 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_size.rs b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.rs new file mode 100644 index 000000000..3437b14f4 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_suffix_dynamic_size(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64 new file mode 100644 index 000000000..bd4ace898 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64 @@ -0,0 +1,13 @@ +bench_ref_from_suffix_dynamic_size: + mov rdx, rsi + lea ecx, [rsi + rdi] + mov eax, edx + and eax, 1 + add rax, rdi + xor esi, esi + sub rdx, 4 + cmovb rax, rsi + shr rdx + test cl, 1 + cmovne rax, rsi + ret diff --git a/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..1398bcfe2 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_dynamic_size.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 439 +Total uOps: 1400 + +Dispatch Width: 4 +uOps Per Cycle: 3.19 +IPC: 2.73 +Block RThroughput: 3.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rdx, rsi + 1 1 0.50 lea ecx, [rsi + rdi] + 1 1 0.33 mov eax, edx + 1 1 0.33 and eax, 1 + 1 1 0.33 add rax, rdi + 1 0 0.25 xor esi, esi + 1 1 0.33 sub rdx, 4 + 2 2 0.67 cmovb rax, rsi + 1 1 0.50 shr rdx + 1 1 0.33 test cl, 1 + 2 2 0.67 cmovne rax, rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.33 4.33 - 4.34 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.02 0.32 - 0.66 - - mov rdx, rsi + - - 0.32 0.68 - - - - lea ecx, [rsi + rdi] + - - 0.66 - - 0.34 - - mov eax, edx + - - 0.02 0.33 - 0.65 - - and eax, 1 + - - - 0.99 - 0.01 - - add rax, rdi + - - - - - - - - xor esi, esi + - - 0.65 - - 0.35 - - sub rdx, 4 + - - 1.00 1.00 - - - - cmovb rax, rsi + - - 0.66 - - 0.34 - - shr rdx + - - - 0.01 - 0.99 - - test cl, 1 + - - 1.00 1.00 - - - - cmovne rax, rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_suffix_static_size.rs b/rust/zerocopy/benches/ref_from_suffix_static_size.rs new file mode 100644 index 000000000..c8435d10d --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_static_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_suffix_static_size(source: &[u8]) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64 b/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64 new file mode 100644 index 000000000..9e90b9e25 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64 @@ -0,0 +1,13 @@ +bench_ref_from_suffix_static_size: + lea eax, [rsi + rdi] + cmp rsi, 6 + setb cl + or cl, al + test cl, 1 + je .LBB5_2 + xor eax, eax + ret +.LBB5_2: + lea rax, [rdi + rsi] + add rax, -6 + ret diff --git a/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64.mca b/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64.mca new file mode 100644 index 000000000..ef5892647 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_static_size.x86-64.mca @@ -0,0 +1,61 @@ +Iterations: 100 +Instructions: 1100 +Total Cycles: 338 +Total uOps: 1100 + +Dispatch Width: 4 +uOps Per Cycle: 3.25 +IPC: 3.25 +Block RThroughput: 3.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea eax, [rsi + rdi] + 1 1 0.33 cmp rsi, 6 + 1 1 0.50 setb cl + 1 1 0.33 or cl, al + 1 1 0.33 test cl, 1 + 1 1 1.00 je .LBB5_2 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.50 lea rax, [rdi + rsi] + 1 1 0.33 add rax, -6 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.32 3.33 - 3.35 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.97 0.03 - - - - lea eax, [rsi + rdi] + - - 0.33 0.32 - 0.35 - - cmp rsi, 6 + - - 1.00 - - - - - setb cl + - - - 1.00 - - - - or cl, al + - - - 1.00 - - - - test cl, 1 + - - - - - 1.00 - - je .LBB5_2 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.34 0.66 - - - - lea rax, [rdi + rsi] + - - 0.68 0.32 - - - - add rax, -6 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..73d91cee5 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_suffix_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_suffix_with_elems(source, count) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..c3d10b5fc --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,27 @@ +bench_ref_from_suffix_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + ja .LBB5_1 + lea r8d, [rsi + rdi] + xor ecx, ecx + mov eax, 0 + test r8b, 3 + je .LBB5_3 + mov rdx, rcx + ret +.LBB5_3: + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + sub rsi, rax + jae .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + add rdi, rsi + mov rcx, rdx + mov rax, rdi + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..92e6280bb --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,85 @@ +Iterations: 100 +Instructions: 2300 +Total Cycles: 706 +Total uOps: 2300 + +Dispatch Width: 4 +uOps Per Cycle: 3.26 +IPC: 3.26 +Block RThroughput: 6.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r8d, [rsi + rdi] + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test r8b, 3 + 1 1 1.00 je .LBB5_3 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 1 0.33 sub rsi, rax + 1 1 1.00 jae .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 1 0.33 add rdi, rsi + 1 1 0.33 mov rcx, rdx + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.99 7.00 - 7.01 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - movabs rax, 3074457345618258598 + - - 0.01 0.50 - 0.49 - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - - 1.00 - - - - lea r8d, [rsi + rdi] + - - - - - - - - xor ecx, ecx + - - 0.50 0.49 - 0.01 - - mov eax, 0 + - - 0.49 0.51 - - - - test r8b, 3 + - - - - - 1.00 - - je .LBB5_3 + - - 0.51 0.49 - - - - mov rdx, rcx + - - - - - 1.00 - - ret + - - 0.50 0.50 - - - - lea rax, [rdx + 2*rdx] + - - 1.00 - - - - - or rax, 3 + - - 1.00 - - - - - add rax, 9 + - - 0.99 0.01 - - - - sub rsi, rax + - - - - - 1.00 - - jae .LBB5_4 + - - - - - - - - xor eax, eax + - - - 1.00 - - - - mov edx, 1 + - - - - - 1.00 - - ret + - - 1.00 - - - - - add rdi, rsi + - - - 1.00 - - - - mov rcx, rdx + - - 0.99 0.01 - - - - mov rax, rdi + - - - 0.50 - 0.50 - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.rs b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.rs new file mode 100644 index 000000000..68a28baf5 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_ref_from_suffix_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::LocoPacket> { + match zerocopy::FromBytes::ref_from_suffix_with_elems(source, count) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..bdca57192 --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64 @@ -0,0 +1,23 @@ +bench_ref_from_suffix_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + ja .LBB5_1 + lea r8d, [rsi + rdi] + xor ecx, ecx + mov eax, 0 + test r8b, 1 + jne .LBB5_5 + lea rax, [2*rdx + 4] + sub rsi, rax + jae .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + add rdi, rsi + mov rcx, rdx + mov rax, rdi +.LBB5_5: + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..6d9de0b3e --- /dev/null +++ b/rust/zerocopy/benches/ref_from_suffix_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 571 +Total uOps: 1900 + +Dispatch Width: 4 +uOps Per Cycle: 3.33 +IPC: 3.33 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r8d, [rsi + rdi] + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test r8b, 1 + 1 1 1.00 jne .LBB5_5 + 1 1 0.50 lea rax, [2*rdx + 4] + 1 1 0.33 sub rsi, rax + 1 1 1.00 jae .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 1 0.33 add rdi, rsi + 1 1 0.33 mov rcx, rdx + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.66 5.66 - 5.68 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.66 0.33 - 0.01 - - movabs rax, 4611686018427387901 + - - 0.01 0.99 - - - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.99 0.01 - - - - lea r8d, [rsi + rdi] + - - - - - - - - xor ecx, ecx + - - 0.33 0.33 - 0.34 - - mov eax, 0 + - - 0.33 0.34 - 0.33 - - test r8b, 1 + - - - - - 1.00 - - jne .LBB5_5 + - - 0.34 0.66 - - - - lea rax, [2*rdx + 4] + - - - 1.00 - - - - sub rsi, rax + - - - - - 1.00 - - jae .LBB5_4 + - - - - - - - - xor eax, eax + - - 1.00 - - - - - mov edx, 1 + - - - - - 1.00 - - ret + - - - 1.00 - - - - add rdi, rsi + - - 1.00 - - - - - mov rcx, rdx + - - 0.32 0.68 - - - - mov rax, rdi + - - 0.68 0.32 - - - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_at_dynamic_padding.rs b/rust/zerocopy/benches/split_at_dynamic_padding.rs new file mode 100644 index 000000000..bed90f601 --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_padding.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_at_dynamic_padding( + source: &format::CocoPacket, + len: usize, +) -> Option<Split<&format::CocoPacket>> { + source.split_at(len) +} diff --git a/rust/zerocopy/benches/split_at_dynamic_padding.x86-64 b/rust/zerocopy/benches/split_at_dynamic_padding.x86-64 new file mode 100644 index 000000000..6eaf5a004 --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_padding.x86-64 @@ -0,0 +1,12 @@ +bench_split_at_dynamic_padding: + mov rax, rdi + cmp rcx, rdx + jbe .LBB5_2 + xor esi, esi + mov qword ptr [rax], rsi + ret +.LBB5_2: + mov qword ptr [rax + 8], rdx + mov qword ptr [rax + 16], rcx + mov qword ptr [rax], rsi + ret diff --git a/rust/zerocopy/benches/split_at_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/split_at_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..19ab3414d --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_padding.x86-64.mca @@ -0,0 +1,59 @@ +Iterations: 100 +Instructions: 1000 +Total Cycles: 404 +Total uOps: 1000 + +Dispatch Width: 4 +uOps Per Cycle: 2.48 +IPC: 2.48 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.33 cmp rcx, rdx + 1 1 1.00 jbe .LBB5_2 + 1 0 0.25 xor esi, esi + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 U ret + 1 1 1.00 * mov qword ptr [rax + 8], rdx + 1 1 1.00 * mov qword ptr [rax + 16], rcx + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 4.00 3.01 2.00 2.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.99 - - 0.01 - - mov rax, rdi + - - - 1.00 - - - - cmp rcx, rdx + - - - - - 1.00 - - jbe .LBB5_2 + - - - - - - - - xor esi, esi + - - - - 1.00 - - 1.00 mov qword ptr [rax], rsi + - - - - - 1.00 - - ret + - - - - 1.00 - 1.00 - mov qword ptr [rax + 8], rdx + - - - - 1.00 - - 1.00 mov qword ptr [rax + 16], rcx + - - - - 1.00 - 1.00 - mov qword ptr [rax], rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_at_dynamic_size.rs b/rust/zerocopy/benches/split_at_dynamic_size.rs new file mode 100644 index 000000000..07a22ba2e --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_at_dynamic_size( + source: &format::CocoPacket, + len: usize, +) -> Option<Split<&format::CocoPacket>> { + source.split_at(len) +} diff --git a/rust/zerocopy/benches/split_at_dynamic_size.x86-64 b/rust/zerocopy/benches/split_at_dynamic_size.x86-64 new file mode 100644 index 000000000..8d81b98bd --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_size.x86-64 @@ -0,0 +1,12 @@ +bench_split_at_dynamic_size: + mov rax, rdi + cmp rcx, rdx + jbe .LBB5_2 + xor esi, esi + mov qword ptr [rax], rsi + ret +.LBB5_2: + mov qword ptr [rax + 8], rdx + mov qword ptr [rax + 16], rcx + mov qword ptr [rax], rsi + ret diff --git a/rust/zerocopy/benches/split_at_dynamic_size.x86-64.mca b/rust/zerocopy/benches/split_at_dynamic_size.x86-64.mca new file mode 100644 index 000000000..19ab3414d --- /dev/null +++ b/rust/zerocopy/benches/split_at_dynamic_size.x86-64.mca @@ -0,0 +1,59 @@ +Iterations: 100 +Instructions: 1000 +Total Cycles: 404 +Total uOps: 1000 + +Dispatch Width: 4 +uOps Per Cycle: 2.48 +IPC: 2.48 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.33 cmp rcx, rdx + 1 1 1.00 jbe .LBB5_2 + 1 0 0.25 xor esi, esi + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 U ret + 1 1 1.00 * mov qword ptr [rax + 8], rdx + 1 1 1.00 * mov qword ptr [rax + 16], rcx + 1 1 1.00 * mov qword ptr [rax], rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 4.00 3.01 2.00 2.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.99 - - 0.01 - - mov rax, rdi + - - - 1.00 - - - - cmp rcx, rdx + - - - - - 1.00 - - jbe .LBB5_2 + - - - - - - - - xor esi, esi + - - - - 1.00 - - 1.00 mov qword ptr [rax], rsi + - - - - - 1.00 - - ret + - - - - 1.00 - 1.00 - mov qword ptr [rax + 8], rdx + - - - - 1.00 - - 1.00 mov qword ptr [rax + 16], rcx + - - - - 1.00 - 1.00 - mov qword ptr [rax], rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.rs b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.rs new file mode 100644 index 000000000..3c147d3bd --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +unsafe fn bench_split_at_unchecked_dynamic_padding( + source: &format::CocoPacket, + len: usize, +) -> Split<&format::CocoPacket> { + unsafe { source.split_at_unchecked(len) } +} diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64 b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64 new file mode 100644 index 000000000..74c3b52f6 --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64 @@ -0,0 +1,6 @@ +bench_split_at_unchecked_dynamic_padding: + mov rax, rdi + mov qword ptr [rdi], rsi + mov qword ptr [rdi + 8], rdx + mov qword ptr [rdi + 16], rcx + ret diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..e8c61591c --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_padding.x86-64.mca @@ -0,0 +1,49 @@ +Iterations: 100 +Instructions: 500 +Total Cycles: 303 +Total uOps: 500 + +Dispatch Width: 4 +uOps Per Cycle: 1.65 +IPC: 1.65 +Block RThroughput: 3.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 1.00 * mov qword ptr [rdi], rsi + 1 1 1.00 * mov qword ptr [rdi + 8], rdx + 1 1 1.00 * mov qword ptr [rdi + 16], rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.49 0.50 3.00 1.01 1.50 1.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.49 0.50 - 0.01 - - mov rax, rdi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi], rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi + 8], rdx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi + 16], rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_size.rs b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.rs new file mode 100644 index 000000000..b1aa1dfb3 --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +unsafe fn bench_split_at_unchecked_dynamic_size( + source: &format::CocoPacket, + len: usize, +) -> Split<&format::CocoPacket> { + unsafe { source.split_at_unchecked(len) } +} diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64 b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64 new file mode 100644 index 000000000..56671d1ee --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64 @@ -0,0 +1,6 @@ +bench_split_at_unchecked_dynamic_size: + mov rax, rdi + mov qword ptr [rdi], rsi + mov qword ptr [rdi + 8], rdx + mov qword ptr [rdi + 16], rcx + ret diff --git a/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64.mca b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64.mca new file mode 100644 index 000000000..e8c61591c --- /dev/null +++ b/rust/zerocopy/benches/split_at_unchecked_dynamic_size.x86-64.mca @@ -0,0 +1,49 @@ +Iterations: 100 +Instructions: 500 +Total Cycles: 303 +Total uOps: 500 + +Dispatch Width: 4 +uOps Per Cycle: 1.65 +IPC: 1.65 +Block RThroughput: 3.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 1.00 * mov qword ptr [rdi], rsi + 1 1 1.00 * mov qword ptr [rdi + 8], rdx + 1 1 1.00 * mov qword ptr [rdi + 16], rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.49 0.50 3.00 1.01 1.50 1.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.49 0.50 - 0.01 - - mov rax, rdi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi], rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi + 8], rdx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rdi + 16], rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_padding.rs b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.rs new file mode 100644 index 000000000..b86ad3614 --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_via_immutable_dynamic_padding( + split: Split<&format::CocoPacket>, +) -> (&format::CocoPacket, &[[u8; 3]]) { + split.via_immutable() +} diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64 b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64 new file mode 100644 index 000000000..dac183428 --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64 @@ -0,0 +1,14 @@ +bench_split_via_immutable_dynamic_padding: + mov rax, rdi + mov rcx, qword ptr [rsi] + mov rdx, qword ptr [rsi + 8] + mov rsi, qword ptr [rsi + 16] + lea rdi, [rsi + 2*rsi] + add rdi, rcx + add rdi, 9 + sub rdx, rsi + mov qword ptr [rax], rcx + mov qword ptr [rax + 8], rsi + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rdx + ret diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..6ab4e8387 --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_padding.x86-64.mca @@ -0,0 +1,65 @@ +Iterations: 100 +Instructions: 1300 +Total Cycles: 510 +Total uOps: 1300 + +Dispatch Width: 4 +uOps Per Cycle: 2.55 +IPC: 2.55 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rdx, qword ptr [rsi + 8] + 1 5 0.50 * mov rsi, qword ptr [rsi + 16] + 1 1 0.50 lea rdi, [rsi + 2*rsi] + 1 1 0.33 add rdi, rcx + 1 1 0.33 add rdi, 9 + 1 1 0.33 sub rdx, rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 * mov qword ptr [rax + 8], rsi + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rdx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.00 2.00 4.00 2.00 3.50 3.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.03 0.93 - 0.04 - - mov rax, rdi + - - - - - - 0.49 0.51 mov rcx, qword ptr [rsi] + - - - - - - 1.00 - mov rdx, qword ptr [rsi + 8] + - - - - - - 0.01 0.99 mov rsi, qword ptr [rsi + 16] + - - 0.93 0.07 - - - - lea rdi, [rsi + 2*rsi] + - - 0.05 0.02 - 0.93 - - add rdi, rcx + - - 0.49 0.49 - 0.02 - - add rdi, 9 + - - 0.50 0.49 - 0.01 - - sub rdx, rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax], rcx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax + 8], rsi + - - - - 1.00 - 0.49 0.51 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.51 0.49 mov qword ptr [rax + 24], rdx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_size.rs b/rust/zerocopy/benches/split_via_immutable_dynamic_size.rs new file mode 100644 index 000000000..7d115caa3 --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_size.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_via_immutable_dynamic_size( + split: Split<&format::CocoPacket>, +) -> (&format::CocoPacket, &[[u8; 2]]) { + split.via_immutable() +} diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64 b/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64 new file mode 100644 index 000000000..58f6b09fc --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64 @@ -0,0 +1,13 @@ +bench_split_via_immutable_dynamic_size: + mov rax, rdi + mov rcx, qword ptr [rsi] + mov rdx, qword ptr [rsi + 8] + mov rsi, qword ptr [rsi + 16] + lea rdi, [rcx + 2*rsi] + add rdi, 4 + sub rdx, rsi + mov qword ptr [rax], rcx + mov qword ptr [rax + 8], rsi + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rdx + ret diff --git a/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64.mca b/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64.mca new file mode 100644 index 000000000..4549f20de --- /dev/null +++ b/rust/zerocopy/benches/split_via_immutable_dynamic_size.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 509 +Total uOps: 1200 + +Dispatch Width: 4 +uOps Per Cycle: 2.36 +IPC: 2.36 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rdx, qword ptr [rsi + 8] + 1 5 0.50 * mov rsi, qword ptr [rsi + 16] + 1 1 0.50 lea rdi, [rcx + 2*rsi] + 1 1 0.33 add rdi, 4 + 1 1 0.33 sub rdx, rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 * mov qword ptr [rax + 8], rsi + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rdx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.66 1.66 4.00 1.68 3.50 3.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.34 0.33 - 0.33 - - mov rax, rdi + - - - - - - 0.49 0.51 mov rcx, qword ptr [rsi] + - - - - - - 0.51 0.49 mov rdx, qword ptr [rsi + 8] + - - - - - - 0.01 0.99 mov rsi, qword ptr [rsi + 16] + - - 0.33 0.67 - - - - lea rdi, [rcx + 2*rsi] + - - 0.63 0.34 - 0.03 - - add rdi, 4 + - - 0.36 0.32 - 0.32 - - sub rdx, rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax], rcx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax + 8], rsi + - - - - 1.00 - 0.98 0.02 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.51 0.49 mov qword ptr [rax + 24], rdx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.rs b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.rs new file mode 100644 index 000000000..edba7bf34 --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_via_runtime_check_dynamic_padding( + split: Split<&format::CocoPacket>, +) -> Option<(&format::CocoPacket, &[[u8; 3]])> { + split.via_runtime_check().ok() +} diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64 b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64 new file mode 100644 index 000000000..03684cb09 --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64 @@ -0,0 +1,22 @@ +bench_split_via_runtime_check_dynamic_padding: + mov rax, rdi + mov rdx, qword ptr [rsi + 16] + mov ecx, edx + and ecx, 3 + cmp ecx, 1 + jne .LBB5_1 + mov rcx, qword ptr [rsi] + mov rsi, qword ptr [rsi + 8] + lea rdi, [rdx + 2*rdx] + add rdi, rcx + add rdi, 9 + sub rsi, rdx + mov qword ptr [rax + 8], rdx + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rsi + mov qword ptr [rax], rcx + ret +.LBB5_1: + xor ecx, ecx + mov qword ptr [rax], rcx + ret diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..5034ab058 --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_padding.x86-64.mca @@ -0,0 +1,79 @@ +Iterations: 100 +Instructions: 2000 +Total Cycles: 708 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 2.82 +IPC: 2.82 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rdx, qword ptr [rsi + 16] + 1 1 0.33 mov ecx, edx + 1 1 0.33 and ecx, 3 + 1 1 0.33 cmp ecx, 1 + 1 1 1.00 jne .LBB5_1 + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rsi, qword ptr [rsi + 8] + 1 1 0.50 lea rdi, [rdx + 2*rdx] + 1 1 0.33 add rdi, rcx + 1 1 0.33 add rdi, 9 + 1 1 0.33 sub rsi, rdx + 1 1 1.00 * mov qword ptr [rax + 8], rdx + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 U ret + 1 0 0.25 xor ecx, ecx + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.00 3.02 5.00 4.98 4.00 4.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - mov rax, rdi + - - - - - - - 1.00 mov rdx, qword ptr [rsi + 16] + - - 0.99 0.01 - - - - mov ecx, edx + - - 0.99 0.01 - - - - and ecx, 3 + - - 0.97 0.03 - - - - cmp ecx, 1 + - - - - - 1.00 - - jne .LBB5_1 + - - - - - - 1.00 - mov rcx, qword ptr [rsi] + - - - - - - 0.99 0.01 mov rsi, qword ptr [rsi + 8] + - - 0.01 0.99 - - - - lea rdi, [rdx + 2*rdx] + - - - 0.96 - 0.04 - - add rdi, rcx + - - 0.03 - - 0.97 - - add rdi, 9 + - - 0.01 0.03 - 0.96 - - sub rsi, rdx + - - - - 1.00 - 1.00 - mov qword ptr [rax + 8], rdx + - - - - 1.00 - - 1.00 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.01 0.99 mov qword ptr [rax + 24], rsi + - - - - 1.00 - 0.99 0.01 mov qword ptr [rax], rcx + - - - - - 1.00 - - ret + - - - - - - - - xor ecx, ecx + - - - - 1.00 - 0.01 0.99 mov qword ptr [rax], rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.rs b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.rs new file mode 100644 index 000000000..ce22de909 --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_split_via_runtime_check_dynamic_size( + split: Split<&format::CocoPacket>, +) -> Option<(&format::CocoPacket, &[[u8; 2]])> { + split.via_runtime_check().ok() +} diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64 b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64 new file mode 100644 index 000000000..e54276bd8 --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64 @@ -0,0 +1,13 @@ +bench_split_via_runtime_check_dynamic_size: + mov rax, rdi + mov rcx, qword ptr [rsi] + mov rdx, qword ptr [rsi + 8] + mov rsi, qword ptr [rsi + 16] + lea rdi, [rcx + 2*rsi] + add rdi, 4 + sub rdx, rsi + mov qword ptr [rax], rcx + mov qword ptr [rax + 8], rsi + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rdx + ret diff --git a/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64.mca b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64.mca new file mode 100644 index 000000000..4549f20de --- /dev/null +++ b/rust/zerocopy/benches/split_via_runtime_check_dynamic_size.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 509 +Total uOps: 1200 + +Dispatch Width: 4 +uOps Per Cycle: 2.36 +IPC: 2.36 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rdx, qword ptr [rsi + 8] + 1 5 0.50 * mov rsi, qword ptr [rsi + 16] + 1 1 0.50 lea rdi, [rcx + 2*rsi] + 1 1 0.33 add rdi, 4 + 1 1 0.33 sub rdx, rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 * mov qword ptr [rax + 8], rsi + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rdx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.66 1.66 4.00 1.68 3.50 3.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.34 0.33 - 0.33 - - mov rax, rdi + - - - - - - 0.49 0.51 mov rcx, qword ptr [rsi] + - - - - - - 0.51 0.49 mov rdx, qword ptr [rsi + 8] + - - - - - - 0.01 0.99 mov rsi, qword ptr [rsi + 16] + - - 0.33 0.67 - - - - lea rdi, [rcx + 2*rsi] + - - 0.63 0.34 - 0.03 - - add rdi, 4 + - - 0.36 0.32 - 0.32 - - sub rdx, rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax], rcx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax + 8], rsi + - - - - 1.00 - 0.98 0.02 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.51 0.49 mov qword ptr [rax + 24], rdx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.rs b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.rs new file mode 100644 index 000000000..21d74dba1 --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +unsafe fn bench_split_via_unchecked_dynamic_padding( + split: Split<&format::CocoPacket>, +) -> (&format::CocoPacket, &[[u8; 3]]) { + unsafe { split.via_unchecked() } +} diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64 b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64 new file mode 100644 index 000000000..3c2c4ec9f --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64 @@ -0,0 +1,14 @@ +bench_split_via_unchecked_dynamic_padding: + mov rax, rdi + mov rcx, qword ptr [rsi] + mov rdx, qword ptr [rsi + 8] + mov rsi, qword ptr [rsi + 16] + lea rdi, [rsi + 2*rsi] + add rdi, rcx + add rdi, 9 + sub rdx, rsi + mov qword ptr [rax], rcx + mov qword ptr [rax + 8], rsi + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rdx + ret diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..6ab4e8387 --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_padding.x86-64.mca @@ -0,0 +1,65 @@ +Iterations: 100 +Instructions: 1300 +Total Cycles: 510 +Total uOps: 1300 + +Dispatch Width: 4 +uOps Per Cycle: 2.55 +IPC: 2.55 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rdx, qword ptr [rsi + 8] + 1 5 0.50 * mov rsi, qword ptr [rsi + 16] + 1 1 0.50 lea rdi, [rsi + 2*rsi] + 1 1 0.33 add rdi, rcx + 1 1 0.33 add rdi, 9 + 1 1 0.33 sub rdx, rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 * mov qword ptr [rax + 8], rsi + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rdx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.00 2.00 4.00 2.00 3.50 3.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.03 0.93 - 0.04 - - mov rax, rdi + - - - - - - 0.49 0.51 mov rcx, qword ptr [rsi] + - - - - - - 1.00 - mov rdx, qword ptr [rsi + 8] + - - - - - - 0.01 0.99 mov rsi, qword ptr [rsi + 16] + - - 0.93 0.07 - - - - lea rdi, [rsi + 2*rsi] + - - 0.05 0.02 - 0.93 - - add rdi, rcx + - - 0.49 0.49 - 0.02 - - add rdi, 9 + - - 0.50 0.49 - 0.01 - - sub rdx, rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax], rcx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax + 8], rsi + - - - - 1.00 - 0.49 0.51 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.51 0.49 mov qword ptr [rax + 24], rdx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_size.rs b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.rs new file mode 100644 index 000000000..824e22d67 --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.rs @@ -0,0 +1,11 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +unsafe fn bench_split_via_unchecked_dynamic_size( + split: Split<&format::CocoPacket>, +) -> (&format::CocoPacket, &[[u8; 2]]) { + unsafe { split.via_unchecked() } +} diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64 b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64 new file mode 100644 index 000000000..1e31268ed --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64 @@ -0,0 +1,13 @@ +bench_split_via_unchecked_dynamic_size: + mov rax, rdi + mov rcx, qword ptr [rsi] + mov rdx, qword ptr [rsi + 8] + mov rsi, qword ptr [rsi + 16] + lea rdi, [rcx + 2*rsi] + add rdi, 4 + sub rdx, rsi + mov qword ptr [rax], rcx + mov qword ptr [rax + 8], rsi + mov qword ptr [rax + 16], rdi + mov qword ptr [rax + 24], rdx + ret diff --git a/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64.mca b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64.mca new file mode 100644 index 000000000..4549f20de --- /dev/null +++ b/rust/zerocopy/benches/split_via_unchecked_dynamic_size.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 509 +Total uOps: 1200 + +Dispatch Width: 4 +uOps Per Cycle: 2.36 +IPC: 2.36 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 5 0.50 * mov rcx, qword ptr [rsi] + 1 5 0.50 * mov rdx, qword ptr [rsi + 8] + 1 5 0.50 * mov rsi, qword ptr [rsi + 16] + 1 1 0.50 lea rdi, [rcx + 2*rsi] + 1 1 0.33 add rdi, 4 + 1 1 0.33 sub rdx, rsi + 1 1 1.00 * mov qword ptr [rax], rcx + 1 1 1.00 * mov qword ptr [rax + 8], rsi + 1 1 1.00 * mov qword ptr [rax + 16], rdi + 1 1 1.00 * mov qword ptr [rax + 24], rdx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.66 1.66 4.00 1.68 3.50 3.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.34 0.33 - 0.33 - - mov rax, rdi + - - - - - - 0.49 0.51 mov rcx, qword ptr [rsi] + - - - - - - 0.51 0.49 mov rdx, qword ptr [rsi + 8] + - - - - - - 0.01 0.99 mov rsi, qword ptr [rsi + 16] + - - 0.33 0.67 - - - - lea rdi, [rcx + 2*rsi] + - - 0.63 0.34 - 0.03 - - add rdi, 4 + - - 0.36 0.32 - 0.32 - - sub rdx, rsi + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax], rcx + - - - - 1.00 - 0.50 0.50 mov qword ptr [rax + 8], rsi + - - - - 1.00 - 0.98 0.02 mov qword ptr [rax + 16], rdi + - - - - 1.00 - 0.51 0.49 mov qword ptr [rax + 24], rdx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/transmute.rs b/rust/zerocopy/benches/transmute.rs new file mode 100644 index 000000000..e60bfb252 --- /dev/null +++ b/rust/zerocopy/benches/transmute.rs @@ -0,0 +1,16 @@ +use zerocopy::Unalign; +use zerocopy_derive::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C)] +struct MinimalViableSource { + bytes: [u8; 6], +} + +#[unsafe(no_mangle)] +fn bench_transmute(source: MinimalViableSource) -> Unalign<format::LocoPacket> { + zerocopy::transmute!(source) +} diff --git a/rust/zerocopy/benches/transmute.x86-64 b/rust/zerocopy/benches/transmute.x86-64 new file mode 100644 index 000000000..a4c6299d1 --- /dev/null +++ b/rust/zerocopy/benches/transmute.x86-64 @@ -0,0 +1,3 @@ +bench_transmute: + mov rax, rdi + ret diff --git a/rust/zerocopy/benches/transmute.x86-64.mca b/rust/zerocopy/benches/transmute.x86-64.mca new file mode 100644 index 000000000..f297729c6 --- /dev/null +++ b/rust/zerocopy/benches/transmute.x86-64.mca @@ -0,0 +1,43 @@ +Iterations: 100 +Instructions: 200 +Total Cycles: 104 +Total uOps: 200 + +Dispatch Width: 4 +uOps Per Cycle: 1.92 +IPC: 1.92 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.49 0.50 - 1.01 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.49 0.50 - 0.01 - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/transmute_ref_dynamic_size.rs b/rust/zerocopy/benches/transmute_ref_dynamic_size.rs new file mode 100644 index 000000000..825f0f2be --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_dynamic_size.rs @@ -0,0 +1,16 @@ +use zerocopy_derive::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C, align(2))] +struct MinimalViableSource { + header: [u8; 6], + trailer: [[u8; 2]], +} + +#[unsafe(no_mangle)] +fn bench_transmute_ref_dynamic_size(source: &MinimalViableSource) -> &format::LocoPacket { + zerocopy::transmute_ref!(source) +} diff --git a/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64 b/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64 new file mode 100644 index 000000000..80a0f5906 --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64 @@ -0,0 +1,4 @@ +bench_transmute_ref_dynamic_size: + mov rax, rdi + lea rdx, [rsi + 1] + ret diff --git a/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64.mca b/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64.mca new file mode 100644 index 000000000..ef1bcdca5 --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_dynamic_size.x86-64.mca @@ -0,0 +1,45 @@ +Iterations: 100 +Instructions: 300 +Total Cycles: 104 +Total uOps: 300 + +Dispatch Width: 4 +uOps Per Cycle: 2.88 +IPC: 2.88 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.50 lea rdx, [rsi + 1] + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 - 1.01 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.99 - - 0.01 - - mov rax, rdi + - - - 1.00 - - - - lea rdx, [rsi + 1] + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/transmute_ref_static_size.rs b/rust/zerocopy/benches/transmute_ref_static_size.rs new file mode 100644 index 000000000..a6db611fd --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_static_size.rs @@ -0,0 +1,15 @@ +use zerocopy_derive::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C, align(2))] +struct MinimalViableSource { + bytes: [u8; 6], +} + +#[unsafe(no_mangle)] +fn bench_transmute_ref_static_size(source: &MinimalViableSource) -> &format::LocoPacket { + zerocopy::transmute_ref!(source) +} diff --git a/rust/zerocopy/benches/transmute_ref_static_size.x86-64 b/rust/zerocopy/benches/transmute_ref_static_size.x86-64 new file mode 100644 index 000000000..7a9229c12 --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_static_size.x86-64 @@ -0,0 +1,3 @@ +bench_transmute_ref_static_size: + mov rax, rdi + ret diff --git a/rust/zerocopy/benches/transmute_ref_static_size.x86-64.mca b/rust/zerocopy/benches/transmute_ref_static_size.x86-64.mca new file mode 100644 index 000000000..f297729c6 --- /dev/null +++ b/rust/zerocopy/benches/transmute_ref_static_size.x86-64.mca @@ -0,0 +1,43 @@ +Iterations: 100 +Instructions: 200 +Total Cycles: 104 +Total uOps: 200 + +Dispatch Width: 4 +uOps Per Cycle: 1.92 +IPC: 1.92 +Block RThroughput: 1.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.49 0.50 - 1.01 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.49 0.50 - 0.01 - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_read_from_bytes.rs b/rust/zerocopy/benches/try_read_from_bytes.rs new file mode 100644 index 000000000..f8384b32f --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_bytes.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_read_from_bytes_static_size(source: &[u8]) -> Option<format::CocoPacket> { + zerocopy::TryFromBytes::try_read_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/try_read_from_bytes.x86-64 b/rust/zerocopy/benches/try_read_from_bytes.x86-64 new file mode 100644 index 000000000..08088a08f --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_bytes.x86-64 @@ -0,0 +1,23 @@ +bench_try_read_from_bytes_static_size: + mov ax, -16191 + cmp rsi, 6 + jne .LBB5_1 + mov ecx, dword ptr [rdi] + movzx edx, cx + cmp edx, 49344 + jne .LBB5_4 + movzx eax, word ptr [rdi + 4] + shl rax, 32 + or rcx, rax + shr rcx, 16 + mov ax, -16192 +.LBB5_4: + shl rcx, 16 + movzx eax, ax + or rax, rcx + ret +.LBB5_1: + shl rcx, 16 + movzx eax, ax + or rax, rcx + ret diff --git a/rust/zerocopy/benches/try_read_from_bytes.x86-64.mca b/rust/zerocopy/benches/try_read_from_bytes.x86-64.mca new file mode 100644 index 000000000..385e6a480 --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_bytes.x86-64.mca @@ -0,0 +1,79 @@ +Iterations: 100 +Instructions: 2000 +Total Cycles: 608 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 3.29 +IPC: 3.29 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov ax, -16191 + 1 1 0.33 cmp rsi, 6 + 1 1 1.00 jne .LBB5_1 + 1 5 0.50 * mov ecx, dword ptr [rdi] + 1 1 0.33 movzx edx, cx + 1 1 0.33 cmp edx, 49344 + 1 1 1.00 jne .LBB5_4 + 1 5 0.50 * movzx eax, word ptr [rdi + 4] + 1 1 0.50 shl rax, 32 + 1 1 0.33 or rcx, rax + 1 1 0.50 shr rcx, 16 + 1 1 0.33 mov ax, -16192 + 1 1 0.50 shl rcx, 16 + 1 1 0.33 movzx eax, ax + 1 1 0.33 or rax, rcx + 1 1 1.00 U ret + 1 1 0.50 shl rcx, 16 + 1 1 0.33 movzx eax, ax + 1 1 0.33 or rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.99 5.99 - 6.02 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - mov ax, -16191 + - - - 0.01 - 0.99 - - cmp rsi, 6 + - - - - - 1.00 - - jne .LBB5_1 + - - - - - - - 1.00 mov ecx, dword ptr [rdi] + - - 0.98 - - 0.02 - - movzx edx, cx + - - 0.99 0.01 - - - - cmp edx, 49344 + - - - - - 1.00 - - jne .LBB5_4 + - - - - - - 1.00 - movzx eax, word ptr [rdi + 4] + - - 0.01 - - 0.99 - - shl rax, 32 + - - 0.02 0.98 - - - - or rcx, rax + - - 1.00 - - - - - shr rcx, 16 + - - 0.99 0.01 - - - - mov ax, -16192 + - - 1.00 - - - - - shl rcx, 16 + - - - 1.00 - - - - movzx eax, ax + - - - 1.00 - - - - or rax, rcx + - - - - - 1.00 - - ret + - - 1.00 - - - - - shl rcx, 16 + - - - 1.00 - - - - movzx eax, ax + - - - 0.99 - 0.01 - - or rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_read_from_prefix.rs b/rust/zerocopy/benches/try_read_from_prefix.rs new file mode 100644 index 000000000..fabbac3bd --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_prefix.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_read_from_prefix_static_size(source: &[u8]) -> Option<format::CocoPacket> { + match zerocopy::TryFromBytes::try_read_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_read_from_prefix.x86-64 b/rust/zerocopy/benches/try_read_from_prefix.x86-64 new file mode 100644 index 000000000..d3e1edc3e --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_prefix.x86-64 @@ -0,0 +1,16 @@ +bench_try_read_from_prefix_static_size: + mov eax, 49345 + cmp rsi, 6 + jb .LBB5_2 + mov eax, dword ptr [rdi] + movzx ecx, word ptr [rdi + 4] + shl rcx, 32 + or rcx, rax + movzx eax, cx + and rcx, -65536 + or rcx, 49344 + cmp eax, 49344 + mov eax, 49345 + cmove rax, rcx +.LBB5_2: + ret diff --git a/rust/zerocopy/benches/try_read_from_prefix.x86-64.mca b/rust/zerocopy/benches/try_read_from_prefix.x86-64.mca new file mode 100644 index 000000000..40401d89e --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_prefix.x86-64.mca @@ -0,0 +1,67 @@ +Iterations: 100 +Instructions: 1400 +Total Cycles: 442 +Total uOps: 1500 + +Dispatch Width: 4 +uOps Per Cycle: 3.39 +IPC: 3.17 +Block RThroughput: 3.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov eax, 49345 + 1 1 0.33 cmp rsi, 6 + 1 1 1.00 jb .LBB5_2 + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 5 0.50 * movzx ecx, word ptr [rdi + 4] + 1 1 0.50 shl rcx, 32 + 1 1 0.33 or rcx, rax + 1 1 0.33 movzx eax, cx + 1 1 0.33 and rcx, -65536 + 1 1 0.33 or rcx, 49344 + 1 1 0.33 cmp eax, 49344 + 1 1 0.33 mov eax, 49345 + 2 2 0.67 cmove rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.33 4.33 - 4.34 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.65 0.01 - 0.34 - - mov eax, 49345 + - - 0.01 0.33 - 0.66 - - cmp rsi, 6 + - - - - - 1.00 - - jb .LBB5_2 + - - - - - - - 1.00 mov eax, dword ptr [rdi] + - - - - - - 1.00 - movzx ecx, word ptr [rdi + 4] + - - 0.65 - - 0.35 - - shl rcx, 32 + - - - 0.67 - 0.33 - - or rcx, rax + - - 0.01 0.99 - - - - movzx eax, cx + - - 0.99 0.01 - - - - and rcx, -65536 + - - 0.01 0.99 - - - - or rcx, 49344 + - - 0.99 0.01 - - - - cmp eax, 49344 + - - 0.02 0.33 - 0.65 - - mov eax, 49345 + - - 1.00 0.99 - 0.01 - - cmove rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_read_from_suffix.rs b/rust/zerocopy/benches/try_read_from_suffix.rs new file mode 100644 index 000000000..1e961647b --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_suffix.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_read_from_suffix_static_size(source: &[u8]) -> Option<format::CocoPacket> { + match zerocopy::TryFromBytes::try_read_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_read_from_suffix.x86-64 b/rust/zerocopy/benches/try_read_from_suffix.x86-64 new file mode 100644 index 000000000..095e326f0 --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_suffix.x86-64 @@ -0,0 +1,18 @@ +bench_try_read_from_suffix_static_size: + mov eax, 49345 + cmp rsi, 6 + jb .LBB5_2 + mov eax, dword ptr [rdi + rsi - 6] + movzx ecx, word ptr [rdi + rsi - 2] + shl rcx, 32 + or rcx, rax + movzx edx, cx + xor eax, eax + cmp edx, 49344 + cmovne rcx, rsi + sete al + and rcx, -65536 + xor rax, 49345 + or rax, rcx +.LBB5_2: + ret diff --git a/rust/zerocopy/benches/try_read_from_suffix.x86-64.mca b/rust/zerocopy/benches/try_read_from_suffix.x86-64.mca new file mode 100644 index 000000000..d3eaadbb8 --- /dev/null +++ b/rust/zerocopy/benches/try_read_from_suffix.x86-64.mca @@ -0,0 +1,71 @@ +Iterations: 100 +Instructions: 1600 +Total Cycles: 478 +Total uOps: 1700 + +Dispatch Width: 4 +uOps Per Cycle: 3.56 +IPC: 3.35 +Block RThroughput: 4.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov eax, 49345 + 1 1 0.33 cmp rsi, 6 + 1 1 1.00 jb .LBB5_2 + 1 5 0.50 * mov eax, dword ptr [rdi + rsi - 6] + 1 5 0.50 * movzx ecx, word ptr [rdi + rsi - 2] + 1 1 0.50 shl rcx, 32 + 1 1 0.33 or rcx, rax + 1 1 0.33 movzx edx, cx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp edx, 49344 + 2 2 0.67 cmovne rcx, rsi + 1 1 0.50 sete al + 1 1 0.33 and rcx, -65536 + 1 1 0.33 xor rax, 49345 + 1 1 0.33 or rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.66 4.66 - 4.68 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.32 0.01 - 0.67 - - mov eax, 49345 + - - 0.62 0.02 - 0.36 - - cmp rsi, 6 + - - - - - 1.00 - - jb .LBB5_2 + - - - - - - - 1.00 mov eax, dword ptr [rdi + rsi - 6] + - - - - - - 1.00 - movzx ecx, word ptr [rdi + rsi - 2] + - - 0.37 - - 0.63 - - shl rcx, 32 + - - 0.99 0.01 - - - - or rcx, rax + - - 1.00 - - - - - movzx edx, cx + - - - - - - - - xor eax, eax + - - 0.35 0.64 - 0.01 - - cmp edx, 49344 + - - 1.00 1.00 - - - - cmovne rcx, rsi + - - - - - 1.00 - - sete al + - - 0.01 0.99 - - - - and rcx, -65536 + - - - 1.00 - - - - xor rax, 49345 + - - - 0.99 - 0.01 - - or rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.rs new file mode 100644 index 000000000..126009cd7 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_bytes_dynamic_padding(source: &[u8]) -> Option<&format::CocoPacket> { + zerocopy::TryFromBytes::try_ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64 new file mode 100644 index 000000000..217c5fc61 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64 @@ -0,0 +1,24 @@ +bench_try_ref_from_bytes_dynamic_padding: + test dil, 3 + jne .LBB5_4 + movabs rax, 9223372036854775804 + and rax, rsi + cmp rax, 9 + jb .LBB5_4 + add rax, -9 + movabs rcx, -6148914691236517205 + mul rcx + shr rdx + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + cmp rsi, rax + jne .LBB5_4 + cmp word ptr [rdi], -16192 + je .LBB5_5 +.LBB5_4: + xor edi, edi + mov rdx, rsi +.LBB5_5: + mov rax, rdi + ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..95b993c7e --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_padding.x86-64.mca @@ -0,0 +1,81 @@ +Iterations: 100 +Instructions: 2100 +Total Cycles: 709 +Total uOps: 2300 + +Dispatch Width: 4 +uOps Per Cycle: 3.24 +IPC: 2.96 +Block RThroughput: 5.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 test dil, 3 + 1 1 1.00 jne .LBB5_4 + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rax, rsi + 1 1 0.33 cmp rax, 9 + 1 1 1.00 jb .LBB5_4 + 1 1 0.33 add rax, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 2 4 1.00 mul rcx + 1 1 0.50 shr rdx + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 1 0.33 cmp rsi, rax + 1 1 1.00 jne .LBB5_4 + 2 6 0.50 * cmp word ptr [rdi], -16192 + 1 1 1.00 je .LBB5_5 + 1 0 0.25 xor edi, edi + 1 1 0.33 mov rdx, rsi + 1 1 0.33 mov rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.98 6.99 - 7.03 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.48 0.51 - 0.01 - - test dil, 3 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.51 0.49 - - - - movabs rax, 9223372036854775804 + - - 0.01 0.99 - - - - and rax, rsi + - - 0.51 0.49 - - - - cmp rax, 9 + - - - - - 1.00 - - jb .LBB5_4 + - - 0.98 - - 0.02 - - add rax, -9 + - - 0.98 0.02 - - - - movabs rcx, -6148914691236517205 + - - 1.00 1.00 - - - - mul rcx + - - 0.99 - - 0.01 - - shr rdx + - - - 1.00 - - - - lea rax, [rdx + 2*rdx] + - - - 0.51 - 0.49 - - or rax, 3 + - - 0.01 0.49 - 0.50 - - add rax, 9 + - - - 0.02 - 0.98 - - cmp rsi, rax + - - - - - 1.00 - - jne .LBB5_4 + - - 0.51 0.49 - - 0.50 0.50 cmp word ptr [rdi], -16192 + - - - - - 1.00 - - je .LBB5_5 + - - - - - - - - xor edi, edi + - - 0.50 0.50 - - - - mov rdx, rsi + - - 0.50 0.48 - 0.02 - - mov rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.rs new file mode 100644 index 000000000..fc3cfbae2 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_bytes_dynamic_size(source: &[u8]) -> Option<&format::CocoPacket> { + zerocopy::TryFromBytes::try_ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64 new file mode 100644 index 000000000..cf67afd31 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64 @@ -0,0 +1,22 @@ +bench_try_ref_from_bytes_dynamic_size: + mov rdx, rsi + mov rax, rdi + cmp rsi, 4 + setb cl + or cl, al + test cl, 1 + jne .LBB5_4 + lea rcx, [rdx - 4] + mov rsi, rcx + and rsi, -2 + add rsi, 4 + cmp rdx, rsi + jne .LBB5_4 + cmp word ptr [rax], -16192 + jne .LBB5_4 + shr rcx + mov rdx, rcx + ret +.LBB5_4: + xor eax, eax + ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64.mca new file mode 100644 index 000000000..ecd7a18f6 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_dynamic_size.x86-64.mca @@ -0,0 +1,79 @@ +Iterations: 100 +Instructions: 2000 +Total Cycles: 639 +Total uOps: 2100 + +Dispatch Width: 4 +uOps Per Cycle: 3.29 +IPC: 3.13 +Block RThroughput: 5.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rdx, rsi + 1 1 0.33 mov rax, rdi + 1 1 0.33 cmp rsi, 4 + 1 1 0.50 setb cl + 1 1 0.33 or cl, al + 1 1 0.33 test cl, 1 + 1 1 1.00 jne .LBB5_4 + 1 1 0.50 lea rcx, [rdx - 4] + 1 1 0.33 mov rsi, rcx + 1 1 0.33 and rsi, -2 + 1 1 0.33 add rsi, 4 + 1 1 0.33 cmp rdx, rsi + 1 1 1.00 jne .LBB5_4 + 2 6 0.50 * cmp word ptr [rax], -16192 + 1 1 1.00 jne .LBB5_4 + 1 1 0.50 shr rcx + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.32 6.32 - 6.36 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.33 0.66 - 0.01 - - mov rdx, rsi + - - 0.66 0.34 - - - - mov rax, rdi + - - 0.34 0.66 - - - - cmp rsi, 4 + - - 0.99 - - 0.01 - - setb cl + - - 0.01 0.99 - - - - or cl, al + - - - 1.00 - - - - test cl, 1 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.66 0.34 - - - - lea rcx, [rdx - 4] + - - 0.33 0.66 - 0.01 - - mov rsi, rcx + - - 1.00 - - - - - and rsi, -2 + - - 0.66 0.34 - - - - add rsi, 4 + - - - 1.00 - - - - cmp rdx, rsi + - - - - - 1.00 - - jne .LBB5_4 + - - - - - 1.00 0.50 0.50 cmp word ptr [rax], -16192 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.67 - - 0.33 - - shr rcx + - - 0.67 0.33 - - - - mov rdx, rcx + - - - - - 1.00 - - ret + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_static_size.rs b/rust/zerocopy/benches/try_ref_from_bytes_static_size.rs new file mode 100644 index 000000000..521557146 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_static_size.rs @@ -0,0 +1,7 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_bytes_static_size(source: &[u8]) -> Option<&format::CocoPacket> { + zerocopy::TryFromBytes::try_ref_from_bytes(source).ok() +} diff --git a/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64 b/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64 new file mode 100644 index 000000000..a11f27189 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64 @@ -0,0 +1,13 @@ +bench_try_ref_from_bytes_static_size: + mov rax, rdi + cmp rsi, 6 + setne cl + or cl, al + test cl, 1 + jne .LBB5_2 + cmp word ptr [rax], -16192 + je .LBB5_3 +.LBB5_2: + xor eax, eax +.LBB5_3: + ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64.mca new file mode 100644 index 000000000..e6bd20533 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_static_size.x86-64.mca @@ -0,0 +1,59 @@ +Iterations: 100 +Instructions: 1000 +Total Cycles: 308 +Total uOps: 1100 + +Dispatch Width: 4 +uOps Per Cycle: 3.57 +IPC: 3.25 +Block RThroughput: 3.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 mov rax, rdi + 1 1 0.33 cmp rsi, 6 + 1 1 0.50 setne cl + 1 1 0.33 or cl, al + 1 1 0.33 test cl, 1 + 1 1 1.00 jne .LBB5_2 + 2 6 0.50 * cmp word ptr [rax], -16192 + 1 1 1.00 je .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.98 2.98 - 3.04 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.02 0.97 - 0.01 - - mov rax, rdi + - - 0.02 0.98 - - - - cmp rsi, 6 + - - 1.00 - - - - - setne cl + - - 0.97 0.02 - 0.01 - - or cl, al + - - 0.96 0.03 - 0.01 - - test cl, 1 + - - - - - 1.00 - - jne .LBB5_2 + - - 0.01 0.98 - 0.01 0.50 0.50 cmp word ptr [rax], -16192 + - - - - - 1.00 - - je .LBB5_3 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..8b9e7355e --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_bytes_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + zerocopy::TryFromBytes::try_ref_from_bytes_with_elems(source, count).ok() +} diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..3ef8d1448 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,21 @@ +bench_try_ref_from_bytes_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + seta cl + mov rax, rdi + test al, 3 + setne dil + or dil, cl + jne .LBB5_3 + lea rcx, [rdx + 2*rdx] + or rcx, 3 + add rcx, 9 + cmp rsi, rcx + jne .LBB5_3 + cmp word ptr [rax], -16192 + je .LBB5_4 +.LBB5_3: + xor eax, eax + mov rdx, rsi +.LBB5_4: + ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..8131f3bd5 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,75 @@ +Iterations: 100 +Instructions: 1800 +Total Cycles: 607 +Total uOps: 2000 + +Dispatch Width: 4 +uOps Per Cycle: 3.29 +IPC: 2.97 +Block RThroughput: 5.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 2 2 1.00 seta cl + 1 1 0.33 mov rax, rdi + 1 1 0.33 test al, 3 + 1 1 0.50 setne dil + 1 1 0.33 or dil, cl + 1 1 1.00 jne .LBB5_3 + 1 1 0.50 lea rcx, [rdx + 2*rdx] + 1 1 0.33 or rcx, 3 + 1 1 0.33 add rcx, 9 + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 jne .LBB5_3 + 2 6 0.50 * cmp word ptr [rax], -16192 + 1 1 1.00 je .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.99 5.99 - 6.02 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - movabs rax, 3074457345618258598 + - - - 1.00 - - - - cmp rdx, rax + - - - - - 2.00 - - seta cl + - - 1.00 - - - - - mov rax, rdi + - - 0.99 0.01 - - - - test al, 3 + - - 1.00 - - - - - setne dil + - - - 0.99 - 0.01 - - or dil, cl + - - - - - 1.00 - - jne .LBB5_3 + - - 0.01 0.99 - - - - lea rcx, [rdx + 2*rdx] + - - - 1.00 - - - - or rcx, 3 + - - 0.99 0.01 - - - - add rcx, 9 + - - - 1.00 - - - - cmp rsi, rcx + - - - - - 1.00 - - jne .LBB5_3 + - - 1.00 - - - 0.50 0.50 cmp word ptr [rax], -16192 + - - - - - 1.00 - - je .LBB5_4 + - - - - - - - - xor eax, eax + - - 1.00 - - - - - mov rdx, rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.rs new file mode 100644 index 000000000..9ccd6fef5 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_bytes_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + zerocopy::TryFromBytes::try_ref_from_bytes_with_elems(source, count).ok() +} diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..ba34b1855 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64 @@ -0,0 +1,18 @@ +bench_try_ref_from_bytes_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + seta cl + mov rax, rdi + or dil, cl + test dil, 1 + jne .LBB5_3 + lea rcx, [2*rdx + 4] + cmp rsi, rcx + jne .LBB5_3 + cmp word ptr [rax], -16192 + je .LBB5_4 +.LBB5_3: + xor eax, eax + mov rdx, rsi +.LBB5_4: + ret diff --git a/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..ae049c03d --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_bytes_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,69 @@ +Iterations: 100 +Instructions: 1500 +Total Cycles: 507 +Total uOps: 1700 + +Dispatch Width: 4 +uOps Per Cycle: 3.35 +IPC: 2.96 +Block RThroughput: 4.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 2 2 1.00 seta cl + 1 1 0.33 mov rax, rdi + 1 1 0.33 or dil, cl + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_3 + 1 1 0.50 lea rcx, [2*rdx + 4] + 1 1 0.33 cmp rsi, rcx + 1 1 1.00 jne .LBB5_3 + 2 6 0.50 * cmp word ptr [rax], -16192 + 1 1 1.00 je .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov rdx, rsi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.98 4.99 - 5.03 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - 0.99 - 0.01 - - movabs rax, 4611686018427387901 + - - 0.50 0.50 - - - - cmp rdx, rax + - - 1.96 - - 0.04 - - seta cl + - - 0.01 0.99 - - - - mov rax, rdi + - - 1.00 - - - - - or dil, cl + - - 0.99 0.01 - - - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_3 + - - 0.01 0.99 - - - - lea rcx, [2*rdx + 4] + - - 0.02 0.49 - 0.49 - - cmp rsi, rcx + - - - - - 1.00 - - jne .LBB5_3 + - - - 0.51 - 0.49 0.50 0.50 cmp word ptr [rax], -16192 + - - - - - 1.00 - - je .LBB5_4 + - - - - - - - - xor eax, eax + - - 0.49 0.51 - - - - mov rdx, rsi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.rs new file mode 100644 index 000000000..23b346f9c --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_prefix_dynamic_padding(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64 new file mode 100644 index 000000000..d832cb7ec --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64 @@ -0,0 +1,29 @@ +bench_try_ref_from_prefix_dynamic_padding: + xor edx, edx + mov eax, 0 + test dil, 3 + je .LBB5_1 + ret +.LBB5_1: + movabs rax, 9223372036854775804 + and rsi, rax + cmp rsi, 9 + jae .LBB5_3 + mov edx, 1 + xor eax, eax + ret +.LBB5_3: + add rsi, -9 + movabs rcx, -6148914691236517205 + mov rax, rsi + mul rcx + mov rax, rdx + shr rax + movzx ecx, word ptr [rdi] + cmp cx, -16192 + mov edx, 2 + cmove rdx, rax + xor eax, eax + cmp ecx, 49344 + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..482112a39 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_padding.x86-64.mca @@ -0,0 +1,91 @@ +Iterations: 100 +Instructions: 2600 +Total Cycles: 843 +Total uOps: 2900 + +Dispatch Width: 4 +uOps Per Cycle: 3.44 +IPC: 3.08 +Block RThroughput: 7.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 3 + 1 1 1.00 je .LBB5_1 + 1 1 1.00 U ret + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rsi, rax + 1 1 0.33 cmp rsi, 9 + 1 1 1.00 jae .LBB5_3 + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rsi, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 1 1 0.33 mov rax, rsi + 2 4 1.00 mul rcx + 1 1 0.33 mov rax, rdx + 1 1 0.50 shr rax + 1 5 0.50 * movzx ecx, word ptr [rdi] + 1 1 0.33 cmp cx, -16192 + 1 1 0.33 mov edx, 2 + 2 2 0.67 cmove rdx, rax + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp ecx, 49344 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 8.33 8.33 - 8.34 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor edx, edx + - - 0.32 0.34 - 0.34 - - mov eax, 0 + - - 0.34 0.33 - 0.33 - - test dil, 3 + - - - - - 1.00 - - je .LBB5_1 + - - - - - 1.00 - - ret + - - 0.35 0.65 - - - - movabs rax, 9223372036854775804 + - - 0.96 0.03 - 0.01 - - and rsi, rax + - - 0.01 0.97 - 0.02 - - cmp rsi, 9 + - - - - - 1.00 - - jae .LBB5_3 + - - 0.67 0.01 - 0.32 - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.02 0.34 - 0.64 - - add rsi, -9 + - - 0.33 0.66 - 0.01 - - movabs rcx, -6148914691236517205 + - - 0.66 0.34 - - - - mov rax, rsi + - - 1.00 1.00 - - - - mul rcx + - - 0.01 0.99 - - - - mov rax, rdx + - - 0.99 - - 0.01 - - shr rax + - - - - - - 0.50 0.50 movzx ecx, word ptr [rdi] + - - 0.33 0.03 - 0.64 - - cmp cx, -16192 + - - 0.01 0.31 - 0.68 - - mov edx, 2 + - - 1.00 1.00 - - - - cmove rdx, rax + - - - - - - - - xor eax, eax + - - 0.33 0.33 - 0.34 - - cmp ecx, 49344 + - - 1.00 1.00 - - - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.rs new file mode 100644 index 000000000..41a466ec8 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_prefix_dynamic_size(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64 new file mode 100644 index 000000000..be7f34b9f --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64 @@ -0,0 +1,22 @@ +bench_try_ref_from_prefix_dynamic_size: + xor edx, edx + mov eax, 0 + test dil, 1 + jne .LBB5_4 + cmp rsi, 4 + jae .LBB5_3 + mov edx, 1 + xor eax, eax + ret +.LBB5_3: + add rsi, -4 + shr rsi + movzx ecx, word ptr [rdi] + cmp ecx, 49344 + mov edx, 2 + cmove rdx, rsi + xor eax, eax + cmp cx, -16192 + cmove rax, rdi +.LBB5_4: + ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..11706defe --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 573 +Total uOps: 2100 + +Dispatch Width: 4 +uOps Per Cycle: 3.66 +IPC: 3.32 +Block RThroughput: 5.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_4 + 1 1 0.33 cmp rsi, 4 + 1 1 1.00 jae .LBB5_3 + 1 1 0.33 mov edx, 1 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rsi, -4 + 1 1 0.50 shr rsi + 1 5 0.50 * movzx ecx, word ptr [rdi] + 1 1 0.33 cmp ecx, 49344 + 1 1 0.33 mov edx, 2 + 2 2 0.67 cmove rdx, rsi + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp cx, -16192 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.66 5.67 - 5.67 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor edx, edx + - - 0.30 0.37 - 0.33 - - mov eax, 0 + - - 0.35 0.32 - 0.33 - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_4 + - - 0.32 0.33 - 0.35 - - cmp rsi, 4 + - - - - - 1.00 - - jae .LBB5_3 + - - 0.33 0.35 - 0.32 - - mov edx, 1 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.34 0.64 - 0.02 - - add rsi, -4 + - - 1.00 - - - - - shr rsi + - - - - - - 0.50 0.50 movzx ecx, word ptr [rdi] + - - 0.60 0.40 - - - - cmp ecx, 49344 + - - 0.05 0.95 - - - - mov edx, 2 + - - 1.00 1.00 - - - - cmove rdx, rsi + - - - - - - - - xor eax, eax + - - 0.37 0.31 - 0.32 - - cmp cx, -16192 + - - 1.00 1.00 - - - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_static_size.rs b/rust/zerocopy/benches/try_ref_from_prefix_static_size.rs new file mode 100644 index 000000000..5f13d482b --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_static_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_prefix_static_size(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_prefix(source) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64 b/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64 new file mode 100644 index 000000000..83212f776 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64 @@ -0,0 +1,15 @@ +bench_try_ref_from_prefix_static_size: + cmp rsi, 6 + setb al + or al, dil + test al, 1 + jne .LBB5_2 + movzx eax, word ptr [rdi] + cmp eax, 49344 + mov eax, 2 + cmove rax, rdi + je .LBB5_3 +.LBB5_2: + xor eax, eax +.LBB5_3: + ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64.mca new file mode 100644 index 000000000..5d02b863a --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_static_size.x86-64.mca @@ -0,0 +1,63 @@ +Iterations: 100 +Instructions: 1200 +Total Cycles: 374 +Total uOps: 1300 + +Dispatch Width: 4 +uOps Per Cycle: 3.48 +IPC: 3.21 +Block RThroughput: 3.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 cmp rsi, 6 + 1 1 0.50 setb al + 1 1 0.33 or al, dil + 1 1 0.33 test al, 1 + 1 1 1.00 jne .LBB5_2 + 1 5 0.50 * movzx eax, word ptr [rdi] + 1 1 0.33 cmp eax, 49344 + 1 1 0.33 mov eax, 2 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 je .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 3.66 3.65 - 3.69 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.35 0.64 - 0.01 - - cmp rsi, 6 + - - 1.00 - - - - - setb al + - - 0.02 0.66 - 0.32 - - or al, dil + - - 0.03 0.65 - 0.32 - - test al, 1 + - - - - - 1.00 - - jne .LBB5_2 + - - - - - - 0.50 0.50 movzx eax, word ptr [rdi] + - - 0.92 0.07 - 0.01 - - cmp eax, 49344 + - - 0.37 0.63 - - - - mov eax, 2 + - - 0.97 1.00 - 0.03 - - cmove rax, rdi + - - - - - 1.00 - - je .LBB5_3 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..1744a4075 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_prefix_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_prefix_with_elems(source, count) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..80e66ba16 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,30 @@ +bench_try_ref_from_prefix_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + ja .LBB5_1 + xor ecx, ecx + mov eax, 0 + test dil, 3 + je .LBB5_3 + mov rdx, rcx + ret +.LBB5_3: + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + cmp rax, rsi + jbe .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + movzx esi, word ptr [rdi] + cmp si, -16192 + mov ecx, 2 + cmove rcx, rdx + xor eax, eax + cmp esi, 49344 + cmove rax, rdi + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..512e8ce64 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,91 @@ +Iterations: 100 +Instructions: 2600 +Total Cycles: 806 +Total uOps: 2800 + +Dispatch Width: 4 +uOps Per Cycle: 3.47 +IPC: 3.23 +Block RThroughput: 7.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 3 + 1 1 1.00 je .LBB5_3 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 1 0.33 cmp rax, rsi + 1 1 1.00 jbe .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 5 0.50 * movzx esi, word ptr [rdi] + 1 1 0.33 cmp si, -16192 + 1 1 0.33 mov ecx, 2 + 2 2 0.67 cmove rcx, rdx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp esi, 49344 + 2 2 0.67 cmove rax, rdi + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 7.98 7.99 - 8.03 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.98 - - 0.02 - - movabs rax, 3074457345618258598 + - - - 1.00 - - - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - - - - - - - xor ecx, ecx + - - 0.99 0.01 - - - - mov eax, 0 + - - 0.01 0.96 - 0.03 - - test dil, 3 + - - - - - 1.00 - - je .LBB5_3 + - - 0.97 0.01 - 0.02 - - mov rdx, rcx + - - - - - 1.00 - - ret + - - 0.03 0.97 - - - - lea rax, [rdx + 2*rdx] + - - 0.03 0.97 - - - - or rax, 3 + - - 0.01 0.99 - - - - add rax, 9 + - - - 1.00 - - - - cmp rax, rsi + - - - - - 1.00 - - jbe .LBB5_4 + - - - - - - - - xor eax, eax + - - 0.98 0.01 - 0.01 - - mov edx, 1 + - - - - - 1.00 - - ret + - - - - - - 0.50 0.50 movzx esi, word ptr [rdi] + - - 0.97 0.03 - - - - cmp si, -16192 + - - 0.98 0.01 - 0.01 - - mov ecx, 2 + - - 1.00 0.03 - 0.97 - - cmove rcx, rdx + - - - - - - - - xor eax, eax + - - 0.03 0.97 - - - - cmp esi, 49344 + - - 1.00 1.00 - - - - cmove rax, rdi + - - - 0.03 - 0.97 - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.rs new file mode 100644 index 000000000..ed0f50941 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_prefix_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_prefix_with_elems(source, count) { + Ok((packet, _rest)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..c12e87c13 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64 @@ -0,0 +1,26 @@ +bench_try_ref_from_prefix_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + ja .LBB5_1 + mov rcx, rdx + xor edx, edx + mov eax, 0 + test dil, 1 + jne .LBB5_5 + lea rax, [2*rcx + 4] + cmp rax, rsi + jbe .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + movzx esi, word ptr [rdi] + cmp si, -16192 + mov edx, 2 + cmove rdx, rcx + xor eax, eax + cmp esi, 49344 + cmove rax, rdi +.LBB5_5: + ret diff --git a/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..6c3f1a1ec --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_prefix_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,83 @@ +Iterations: 100 +Instructions: 2200 +Total Cycles: 674 +Total uOps: 2400 + +Dispatch Width: 4 +uOps Per Cycle: 3.56 +IPC: 3.26 +Block RThroughput: 6.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.33 mov rcx, rdx + 1 0 0.25 xor edx, edx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test dil, 1 + 1 1 1.00 jne .LBB5_5 + 1 1 0.50 lea rax, [2*rcx + 4] + 1 1 0.33 cmp rax, rsi + 1 1 1.00 jbe .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 5 0.50 * movzx esi, word ptr [rdi] + 1 1 0.33 cmp si, -16192 + 1 1 0.33 mov edx, 2 + 2 2 0.67 cmove rdx, rcx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp esi, 49344 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.65 6.66 - 6.69 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.66 0.33 - 0.01 - - movabs rax, 4611686018427387901 + - - 0.02 0.66 - 0.32 - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.66 0.33 - 0.01 - - mov rcx, rdx + - - - - - - - - xor edx, edx + - - 0.33 0.01 - 0.66 - - mov eax, 0 + - - 0.34 0.65 - 0.01 - - test dil, 1 + - - - - - 1.00 - - jne .LBB5_5 + - - 0.65 0.35 - - - - lea rax, [2*rcx + 4] + - - - 1.00 - - - - cmp rax, rsi + - - - - - 1.00 - - jbe .LBB5_4 + - - - - - - - - xor eax, eax + - - 0.34 0.01 - 0.65 - - mov edx, 1 + - - - - - 1.00 - - ret + - - - - - - 0.50 0.50 movzx esi, word ptr [rdi] + - - 0.65 0.34 - 0.01 - - cmp si, -16192 + - - 0.66 0.34 - - - - mov edx, 2 + - - 1.00 0.99 - 0.01 - - cmove rdx, rcx + - - - - - - - - xor eax, eax + - - 0.34 0.66 - - - - cmp esi, 49344 + - - 1.00 0.99 - 0.01 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.rs new file mode 100644 index 000000000..981feca3c --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_suffix_dynamic_padding(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64 new file mode 100644 index 000000000..b3e924442 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64 @@ -0,0 +1,26 @@ +bench_try_ref_from_suffix_dynamic_padding: + lea eax, [rsi + rdi] + test al, 3 + jne .LBB5_1 + movabs rax, 9223372036854775804 + and rax, rsi + cmp rax, 9 + jae .LBB5_3 +.LBB5_1: + xor eax, eax + ret +.LBB5_3: + add rax, -9 + movabs rcx, -6148914691236517205 + mul rcx + shr rdx + lea rcx, [rdx + 2*rdx] + sub rsi, rcx + or rcx, -4 + add rsi, rdi + lea rdi, [rcx + rsi] + add rdi, -8 + xor eax, eax + cmp word ptr [rcx + rsi - 8], -16192 + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..d56ae56d8 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_padding.x86-64.mca @@ -0,0 +1,85 @@ +Iterations: 100 +Instructions: 2300 +Total Cycles: 791 +Total uOps: 2600 + +Dispatch Width: 4 +uOps Per Cycle: 3.29 +IPC: 2.91 +Block RThroughput: 6.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea eax, [rsi + rdi] + 1 1 0.33 test al, 3 + 1 1 1.00 jne .LBB5_1 + 1 1 0.33 movabs rax, 9223372036854775804 + 1 1 0.33 and rax, rsi + 1 1 0.33 cmp rax, 9 + 1 1 1.00 jae .LBB5_3 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.33 add rax, -9 + 1 1 0.33 movabs rcx, -6148914691236517205 + 2 4 1.00 mul rcx + 1 1 0.50 shr rdx + 1 1 0.50 lea rcx, [rdx + 2*rdx] + 1 1 0.33 sub rsi, rcx + 1 1 0.33 or rcx, -4 + 1 1 0.33 add rsi, rdi + 1 1 0.50 lea rdi, [rcx + rsi] + 1 1 0.33 add rdi, -8 + 1 0 0.25 xor eax, eax + 2 6 0.50 * cmp word ptr [rcx + rsi - 8], -16192 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 7.70 7.58 - 7.72 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.26 0.74 - - - - lea eax, [rsi + rdi] + - - 0.19 0.28 - 0.53 - - test al, 3 + - - - - - 1.00 - - jne .LBB5_1 + - - 0.93 0.06 - 0.01 - - movabs rax, 9223372036854775804 + - - 0.81 0.14 - 0.05 - - and rax, rsi + - - 0.55 0.43 - 0.02 - - cmp rax, 9 + - - - - - 1.00 - - jae .LBB5_3 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.42 0.56 - 0.02 - - add rax, -9 + - - 0.67 0.30 - 0.03 - - movabs rcx, -6148914691236517205 + - - 1.00 1.00 - - - - mul rcx + - - 0.71 - - 0.29 - - shr rdx + - - 0.32 0.68 - - - - lea rcx, [rdx + 2*rdx] + - - 0.57 0.04 - 0.39 - - sub rsi, rcx + - - 0.28 0.67 - 0.05 - - or rcx, -4 + - - 0.29 0.29 - 0.42 - - add rsi, rdi + - - 0.02 0.98 - - - - lea rdi, [rcx + rsi] + - - 0.02 0.41 - 0.57 - - add rdi, -8 + - - - - - - - - xor eax, eax + - - 0.57 0.01 - 0.42 0.50 0.50 cmp word ptr [rcx + rsi - 8], -16192 + - - 0.09 0.99 - 0.92 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.rs new file mode 100644 index 000000000..c3d75ac9b --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_suffix_dynamic_size(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64 new file mode 100644 index 000000000..d51f7817e --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64 @@ -0,0 +1,18 @@ +bench_try_ref_from_suffix_dynamic_size: + lea eax, [rsi + rdi] + cmp rsi, 4 + setb cl + or cl, al + test cl, 1 + je .LBB5_2 + xor eax, eax + ret +.LBB5_2: + lea rdx, [rsi - 4] + shr rdx + and esi, 1 + lea rcx, [rdi + rsi] + xor eax, eax + cmp word ptr [rdi + rsi], -16192 + cmove rax, rcx + ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..6cf7f8e49 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_dynamic_size.x86-64.mca @@ -0,0 +1,71 @@ +Iterations: 100 +Instructions: 1600 +Total Cycles: 510 +Total uOps: 1800 + +Dispatch Width: 4 +uOps Per Cycle: 3.53 +IPC: 3.14 +Block RThroughput: 4.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea eax, [rsi + rdi] + 1 1 0.33 cmp rsi, 4 + 1 1 0.50 setb cl + 1 1 0.33 or cl, al + 1 1 0.33 test cl, 1 + 1 1 1.00 je .LBB5_2 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.50 lea rdx, [rsi - 4] + 1 1 0.50 shr rdx + 1 1 0.33 and esi, 1 + 1 1 0.50 lea rcx, [rdi + rsi] + 1 0 0.25 xor eax, eax + 2 6 0.50 * cmp word ptr [rdi + rsi], -16192 + 2 2 0.67 cmove rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.99 5.00 - 5.01 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.98 0.02 - - - - lea eax, [rsi + rdi] + - - - 0.98 - 0.02 - - cmp rsi, 4 + - - 1.00 - - - - - setb cl + - - 0.01 0.99 - - - - or cl, al + - - 0.01 0.07 - 0.92 - - test cl, 1 + - - - - - 1.00 - - je .LBB5_2 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.93 0.07 - - - - lea rdx, [rsi - 4] + - - 0.93 - - 0.07 - - shr rdx + - - 0.06 0.93 - 0.01 - - and esi, 1 + - - 0.07 0.93 - - - - lea rcx, [rdi + rsi] + - - - - - - - - xor eax, eax + - - - 0.01 - 0.99 0.50 0.50 cmp word ptr [rdi + rsi], -16192 + - - 1.00 1.00 - - - - cmove rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_static_size.rs b/rust/zerocopy/benches/try_ref_from_suffix_static_size.rs new file mode 100644 index 000000000..d4b92f639 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_static_size.rs @@ -0,0 +1,10 @@ +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_suffix_static_size(source: &[u8]) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_suffix(source) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64 b/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64 new file mode 100644 index 000000000..cd39f7093 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64 @@ -0,0 +1,16 @@ +bench_try_ref_from_suffix_static_size: + lea eax, [rsi + rdi] + cmp rsi, 6 + setb cl + or cl, al + test cl, 1 + je .LBB5_2 + xor eax, eax + ret +.LBB5_2: + lea rcx, [rdi + rsi] + add rcx, -6 + xor eax, eax + cmp word ptr [rdi + rsi - 6], -16192 + cmove rax, rcx + ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64.mca new file mode 100644 index 000000000..087d1e7ed --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_static_size.x86-64.mca @@ -0,0 +1,67 @@ +Iterations: 100 +Instructions: 1400 +Total Cycles: 443 +Total uOps: 1600 + +Dispatch Width: 4 +uOps Per Cycle: 3.61 +IPC: 3.16 +Block RThroughput: 4.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea eax, [rsi + rdi] + 1 1 0.33 cmp rsi, 6 + 1 1 0.50 setb cl + 1 1 0.33 or cl, al + 1 1 0.33 test cl, 1 + 1 1 1.00 je .LBB5_2 + 1 0 0.25 xor eax, eax + 1 1 1.00 U ret + 1 1 0.50 lea rcx, [rdi + rsi] + 1 1 0.33 add rcx, -6 + 1 0 0.25 xor eax, eax + 2 6 0.50 * cmp word ptr [rdi + rsi - 6], -16192 + 2 2 0.67 cmove rax, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.33 4.33 - 4.34 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.32 0.68 - - - - lea eax, [rsi + rdi] + - - 0.05 0.94 - 0.01 - - cmp rsi, 6 + - - 1.00 - - - - - setb cl + - - 0.95 0.05 - - - - or cl, al + - - 0.95 0.02 - 0.03 - - test cl, 1 + - - - - - 1.00 - - je .LBB5_2 + - - - - - - - - xor eax, eax + - - - - - 1.00 - - ret + - - 0.04 0.96 - - - - lea rcx, [rdi + rsi] + - - 0.02 0.97 - 0.01 - - add rcx, -6 + - - - - - - - - xor eax, eax + - - 0.03 0.66 - 0.31 0.50 0.50 cmp word ptr [rdi + rsi - 6], -16192 + - - 0.97 0.05 - 0.98 - - cmove rax, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.rs b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.rs new file mode 100644 index 000000000..1da455c9a --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_suffix_with_elems_dynamic_padding( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_suffix_with_elems(source, count) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64 b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64 new file mode 100644 index 000000000..c7530d8b6 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64 @@ -0,0 +1,32 @@ +bench_try_ref_from_suffix_with_elems_dynamic_padding: + movabs rax, 3074457345618258598 + cmp rdx, rax + ja .LBB5_1 + lea r8d, [rsi + rdi] + xor ecx, ecx + mov eax, 0 + test r8b, 3 + je .LBB5_3 + mov rdx, rcx + ret +.LBB5_3: + lea rax, [rdx + 2*rdx] + or rax, 3 + add rax, 9 + sub rsi, rax + jae .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + lea r8, [rdi + rsi] + movzx esi, word ptr [rdi + rsi] + cmp si, -16192 + mov ecx, 2 + cmove rcx, rdx + xor eax, eax + cmp esi, 49344 + cmove rax, r8 + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..be736c00c --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_padding.x86-64.mca @@ -0,0 +1,95 @@ +Iterations: 100 +Instructions: 2800 +Total Cycles: 878 +Total uOps: 3000 + +Dispatch Width: 4 +uOps Per Cycle: 3.42 +IPC: 3.19 +Block RThroughput: 7.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 3074457345618258598 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r8d, [rsi + rdi] + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test r8b, 3 + 1 1 1.00 je .LBB5_3 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + 1 1 0.50 lea rax, [rdx + 2*rdx] + 1 1 0.33 or rax, 3 + 1 1 0.33 add rax, 9 + 1 1 0.33 sub rsi, rax + 1 1 1.00 jae .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 1 0.50 lea r8, [rdi + rsi] + 1 5 0.50 * movzx esi, word ptr [rdi + rsi] + 1 1 0.33 cmp si, -16192 + 1 1 0.33 mov ecx, 2 + 2 2 0.67 cmove rcx, rdx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp esi, 49344 + 2 2 0.67 cmove rax, r8 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 8.65 8.65 - 8.70 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.67 0.30 - 0.03 - - movabs rax, 3074457345618258598 + - - 0.01 0.99 - - - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.99 0.01 - - - - lea r8d, [rsi + rdi] + - - - - - - - - xor ecx, ecx + - - 0.35 0.62 - 0.03 - - mov eax, 0 + - - 0.99 0.01 - - - - test r8b, 3 + - - - - - 1.00 - - je .LBB5_3 + - - 0.68 0.30 - 0.02 - - mov rdx, rcx + - - - - - 1.00 - - ret + - - 0.07 0.93 - - - - lea rax, [rdx + 2*rdx] + - - 0.06 0.35 - 0.59 - - or rax, 3 + - - 0.02 0.07 - 0.91 - - add rax, 9 + - - 0.01 0.04 - 0.95 - - sub rsi, rax + - - - - - 1.00 - - jae .LBB5_4 + - - - - - - - - xor eax, eax + - - 0.92 0.01 - 0.07 - - mov edx, 1 + - - - - - 1.00 - - ret + - - - 1.00 - - - - lea r8, [rdi + rsi] + - - - - - - 0.50 0.50 movzx esi, word ptr [rdi + rsi] + - - 0.01 0.99 - - - - cmp si, -16192 + - - 0.88 0.04 - 0.08 - - mov ecx, 2 + - - 1.00 0.99 - 0.01 - - cmove rcx, rdx + - - - - - - - - xor eax, eax + - - 0.99 0.01 - - - - cmp esi, 49344 + - - 1.00 1.00 - - - - cmove rax, r8 + - - - 0.99 - 0.01 - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.rs b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.rs new file mode 100644 index 000000000..8c2b80f87 --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.rs @@ -0,0 +1,13 @@ +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_try_ref_from_suffix_with_elems_dynamic_size( + source: &[u8], + count: usize, +) -> Option<&format::CocoPacket> { + match zerocopy::TryFromBytes::try_ref_from_suffix_with_elems(source, count) { + Ok((_rest, packet)) => Some(packet), + _ => None, + } +} diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64 b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64 new file mode 100644 index 000000000..952eb12de --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64 @@ -0,0 +1,28 @@ +bench_try_ref_from_suffix_with_elems_dynamic_size: + movabs rax, 4611686018427387901 + cmp rdx, rax + ja .LBB5_1 + lea r8d, [rsi + rdi] + xor ecx, ecx + mov eax, 0 + test r8b, 1 + jne .LBB5_5 + lea rax, [2*rdx + 4] + sub rsi, rax + jae .LBB5_4 +.LBB5_1: + xor eax, eax + mov edx, 1 + ret +.LBB5_4: + lea r8, [rdi + rsi] + movzx esi, word ptr [rdi + rsi] + cmp si, -16192 + mov ecx, 2 + cmove rcx, rdx + xor eax, eax + cmp esi, 49344 + cmove rax, r8 +.LBB5_5: + mov rdx, rcx + ret diff --git a/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64.mca new file mode 100644 index 000000000..d4f78f67a --- /dev/null +++ b/rust/zerocopy/benches/try_ref_from_suffix_with_elems_dynamic_size.x86-64.mca @@ -0,0 +1,87 @@ +Iterations: 100 +Instructions: 2400 +Total Cycles: 1107 +Total uOps: 2600 + +Dispatch Width: 4 +uOps Per Cycle: 2.35 +IPC: 2.17 +Block RThroughput: 6.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movabs rax, 4611686018427387901 + 1 1 0.33 cmp rdx, rax + 1 1 1.00 ja .LBB5_1 + 1 1 0.50 lea r8d, [rsi + rdi] + 1 0 0.25 xor ecx, ecx + 1 1 0.33 mov eax, 0 + 1 1 0.33 test r8b, 1 + 1 1 1.00 jne .LBB5_5 + 1 1 0.50 lea rax, [2*rdx + 4] + 1 1 0.33 sub rsi, rax + 1 1 1.00 jae .LBB5_4 + 1 0 0.25 xor eax, eax + 1 1 0.33 mov edx, 1 + 1 1 1.00 U ret + 1 1 0.50 lea r8, [rdi + rsi] + 1 5 0.50 * movzx esi, word ptr [rdi + rsi] + 1 1 0.33 cmp si, -16192 + 1 1 0.33 mov ecx, 2 + 2 2 0.67 cmove rcx, rdx + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp esi, 49344 + 2 2 0.67 cmove rax, r8 + 1 1 0.33 mov rdx, rcx + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 6.99 7.00 - 8.01 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.02 0.95 - 0.03 - - movabs rax, 4611686018427387901 + - - 0.93 0.04 - 0.03 - - cmp rdx, rax + - - - - - 1.00 - - ja .LBB5_1 + - - 0.96 0.04 - - - - lea r8d, [rsi + rdi] + - - - - - - - - xor ecx, ecx + - - 0.95 0.02 - 0.03 - - mov eax, 0 + - - 0.95 0.05 - - - - test r8b, 1 + - - - - - 1.00 - - jne .LBB5_5 + - - 0.06 0.94 - - - - lea rax, [2*rdx + 4] + - - 0.93 0.07 - - - - sub rsi, rax + - - - - - 1.00 - - jae .LBB5_4 + - - - - - - - - xor eax, eax + - - 0.03 0.95 - 0.02 - - mov edx, 1 + - - - - - 1.00 - - ret + - - 0.97 0.03 - - - - lea r8, [rdi + rsi] + - - - - - - 0.50 0.50 movzx esi, word ptr [rdi + rsi] + - - 0.03 0.97 - - - - cmp si, -16192 + - - 0.05 0.94 - 0.01 - - mov ecx, 2 + - - 0.06 0.98 - 0.96 - - cmove rcx, rdx + - - - - - - - - xor eax, eax + - - 0.97 0.03 - - - - cmp esi, 49344 + - - 0.06 0.96 - 0.98 - - cmove rax, r8 + - - 0.02 0.03 - 0.95 - - mov rdx, rcx + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_transmute.rs b/rust/zerocopy/benches/try_transmute.rs new file mode 100644 index 000000000..c0de07a8d --- /dev/null +++ b/rust/zerocopy/benches/try_transmute.rs @@ -0,0 +1,16 @@ +use zerocopy::Unalign; +use zerocopy_derive::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C)] +struct MinimalViableSource { + bytes: [u8; 6], +} + +#[unsafe(no_mangle)] +fn bench_try_transmute(source: MinimalViableSource) -> Option<Unalign<format::CocoPacket>> { + zerocopy::try_transmute!(source).ok() +} diff --git a/rust/zerocopy/benches/try_transmute.x86-64 b/rust/zerocopy/benches/try_transmute.x86-64 new file mode 100644 index 000000000..9e16a6632 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute.x86-64 @@ -0,0 +1,9 @@ +bench_try_transmute: + movzx ecx, di + xor eax, eax + cmp ecx, 49344 + sete al + and rdi, -65536 + xor rax, 49345 + or rax, rdi + ret diff --git a/rust/zerocopy/benches/try_transmute.x86-64.mca b/rust/zerocopy/benches/try_transmute.x86-64.mca new file mode 100644 index 000000000..33abc3bf3 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute.x86-64.mca @@ -0,0 +1,55 @@ +Iterations: 100 +Instructions: 800 +Total Cycles: 238 +Total uOps: 800 + +Dispatch Width: 4 +uOps Per Cycle: 3.36 +IPC: 3.36 +Block RThroughput: 2.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 movzx ecx, di + 1 0 0.25 xor eax, eax + 1 1 0.33 cmp ecx, 49344 + 1 1 0.50 sete al + 1 1 0.33 and rdi, -65536 + 1 1 0.33 xor rax, 49345 + 1 1 0.33 or rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 2.33 2.33 - 2.34 - - + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.32 0.67 - 0.01 - - movzx ecx, di + - - - - - - - - xor eax, eax + - - 0.33 0.67 - - - - cmp ecx, 49344 + - - 1.00 - - - - - sete al + - - 0.67 0.33 - - - - and rdi, -65536 + - - - 0.66 - 0.34 - - xor rax, 49345 + - - 0.01 - - 0.99 - - or rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_transmute_ref_dynamic_size.rs b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.rs new file mode 100644 index 000000000..c9236e13d --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.rs @@ -0,0 +1,18 @@ +use zerocopy_derive::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C, align(2))] +struct MinimalViableSource { + header: [u8; 6], + trailer: [[u8; 2]], +} + +#[unsafe(no_mangle)] +fn bench_try_transmute_ref_dynamic_size( + source: &MinimalViableSource, +) -> Option<&format::CocoPacket> { + zerocopy::try_transmute_ref!(source).ok() +} diff --git a/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64 b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64 new file mode 100644 index 000000000..d34d2b3eb --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64 @@ -0,0 +1,6 @@ +bench_try_transmute_ref_dynamic_size: + lea rdx, [rsi + 1] + xor eax, eax + cmp word ptr [rdi], -16192 + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64.mca b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64.mca new file mode 100644 index 000000000..bc771b504 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_dynamic_size.x86-64.mca @@ -0,0 +1,49 @@ +Iterations: 100 +Instructions: 500 +Total Cycles: 209 +Total uOps: 700 + +Dispatch Width: 4 +uOps Per Cycle: 3.35 +IPC: 2.39 +Block RThroughput: 1.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea rdx, [rsi + 1] + 1 0 0.25 xor eax, eax + 2 6 0.50 * cmp word ptr [rdi], -16192 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.50 1.51 - 1.99 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.51 0.49 - - - - lea rdx, [rsi + 1] + - - - - - - - - xor eax, eax + - - - 0.02 - 0.98 0.50 0.50 cmp word ptr [rdi], -16192 + - - 0.99 1.00 - 0.01 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/try_transmute_ref_static_size.rs b/rust/zerocopy/benches/try_transmute_ref_static_size.rs new file mode 100644 index 000000000..631cce2b0 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_static_size.rs @@ -0,0 +1,17 @@ +use zerocopy_derive::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[derive(IntoBytes, KnownLayout, Immutable)] +#[repr(C, align(2))] +struct MinimalViableSource { + bytes: [u8; 6], +} + +#[unsafe(no_mangle)] +fn bench_try_transmute_ref_static_size( + source: &MinimalViableSource, +) -> Option<&format::CocoPacket> { + zerocopy::try_transmute_ref!(source).ok() +} diff --git a/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64 b/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64 new file mode 100644 index 000000000..8c16face9 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64 @@ -0,0 +1,5 @@ +bench_try_transmute_ref_static_size: + xor eax, eax + cmp word ptr [rdi], -16192 + cmove rax, rdi + ret diff --git a/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64.mca b/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64.mca new file mode 100644 index 000000000..cf7384989 --- /dev/null +++ b/rust/zerocopy/benches/try_transmute_ref_static_size.x86-64.mca @@ -0,0 +1,47 @@ +Iterations: 100 +Instructions: 400 +Total Cycles: 160 +Total uOps: 600 + +Dispatch Width: 4 +uOps Per Cycle: 3.75 +IPC: 2.50 +Block RThroughput: 1.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 0 0.25 xor eax, eax + 2 6 0.50 * cmp word ptr [rdi], -16192 + 2 2 0.67 cmove rax, rdi + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.02 1.48 - 1.50 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - - - - - xor eax, eax + - - 0.02 0.49 - 0.49 0.50 0.50 cmp word ptr [rdi], -16192 + - - 1.00 0.99 - 0.01 - - cmove rax, rdi + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_dynamic_size.rs b/rust/zerocopy/benches/write_to_dynamic_size.rs new file mode 100644 index 000000000..c126a1468 --- /dev/null +++ b/rust/zerocopy/benches/write_to_dynamic_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_dynamic_size(source: &format::CocoPacket, destination: &mut [u8]) -> Option<()> { + source.write_to(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_dynamic_size.x86-64 b/rust/zerocopy/benches/write_to_dynamic_size.x86-64 new file mode 100644 index 000000000..c5abb17f7 --- /dev/null +++ b/rust/zerocopy/benches/write_to_dynamic_size.x86-64 @@ -0,0 +1,21 @@ +bench_write_to_dynamic_size: + push r14 + push rbx + push rax + mov rbx, rcx + lea r14, [2*rsi + 5] + and r14, -2 + cmp rcx, r14 + jne .LBB5_2 + mov rax, rdi + mov rdi, rdx + mov rsi, rax + mov rdx, rbx + call qword ptr [rip + memcpy@GOTPCREL] +.LBB5_2: + cmp rbx, r14 + sete al + add rsp, 8 + pop rbx + pop r14 + ret diff --git a/rust/zerocopy/benches/write_to_dynamic_size.x86-64.mca b/rust/zerocopy/benches/write_to_dynamic_size.x86-64.mca new file mode 100644 index 000000000..5b2c08a31 --- /dev/null +++ b/rust/zerocopy/benches/write_to_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 2890 +Total uOps: 2500 + +Dispatch Width: 4 +uOps Per Cycle: 0.87 +IPC: 0.66 +Block RThroughput: 6.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 2 5 1.00 * push rax + 1 1 0.33 mov rbx, rcx + 1 1 0.50 lea r14, [2*rsi + 5] + 1 1 0.33 and r14, -2 + 1 1 0.33 cmp rcx, r14 + 1 1 1.00 jne .LBB5_2 + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov rdi, rdx + 1 1 0.33 mov rsi, rax + 1 1 0.33 mov rdx, rbx + 4 7 1.00 * call qword ptr [rip + memcpy@GOTPCREL] + 1 1 0.33 cmp rbx, r14 + 1 1 0.50 sete al + 1 1 0.33 add rsp, 8 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.66 4.64 4.00 4.70 4.00 3.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - - 1.00 push r14 + - - - - 1.00 - 1.00 - push rbx + - - - - 1.00 - - 1.00 push rax + - - 0.02 0.97 - 0.01 - - mov rbx, rcx + - - 0.97 0.03 - - - - lea r14, [2*rsi + 5] + - - 0.63 0.35 - 0.02 - - and r14, -2 + - - 0.31 0.34 - 0.35 - - cmp rcx, r14 + - - - - - 1.00 - - jne .LBB5_2 + - - 0.33 0.33 - 0.34 - - mov rax, rdi + - - 0.36 0.31 - 0.33 - - mov rdi, rdx + - - 0.33 0.35 - 0.32 - - mov rsi, rax + - - 0.35 0.63 - 0.02 - - mov rdx, rbx + - - - - 1.00 1.00 2.00 - call qword ptr [rip + memcpy@GOTPCREL] + - - 0.65 0.35 - - - - cmp rbx, r14 + - - 0.69 - - 0.31 - - sete al + - - 0.02 0.98 - - - - add rsp, 8 + - - - - - - - 1.00 pop rbx + - - - - - - 1.00 - pop r14 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_prefix_dynamic_size.rs b/rust/zerocopy/benches/write_to_prefix_dynamic_size.rs new file mode 100644 index 000000000..a54d32773 --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_dynamic_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_prefix_dynamic_size( + source: &format::CocoPacket, + destination: &mut [u8], +) -> Option<()> { + source.write_to_prefix(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64 b/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64 new file mode 100644 index 000000000..d7779c6c9 --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64 @@ -0,0 +1,21 @@ +bench_write_to_prefix_dynamic_size: + push r14 + push rbx + push rax + mov rbx, rcx + lea r14, [2*rsi + 5] + and r14, -2 + cmp r14, rcx + ja .LBB5_2 + mov rax, rdi + mov rdi, rdx + mov rsi, rax + mov rdx, r14 + call qword ptr [rip + memcpy@GOTPCREL] +.LBB5_2: + cmp r14, rbx + setbe al + add rsp, 8 + pop rbx + pop r14 + ret diff --git a/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..4cebe24d4 --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_dynamic_size.x86-64.mca @@ -0,0 +1,77 @@ +Iterations: 100 +Instructions: 1900 +Total Cycles: 2890 +Total uOps: 2600 + +Dispatch Width: 4 +uOps Per Cycle: 0.90 +IPC: 0.66 +Block RThroughput: 6.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 2 5 1.00 * push rax + 1 1 0.33 mov rbx, rcx + 1 1 0.50 lea r14, [2*rsi + 5] + 1 1 0.33 and r14, -2 + 1 1 0.33 cmp r14, rcx + 1 1 1.00 ja .LBB5_2 + 1 1 0.33 mov rax, rdi + 1 1 0.33 mov rdi, rdx + 1 1 0.33 mov rsi, rax + 1 1 0.33 mov rdx, r14 + 4 7 1.00 * call qword ptr [rip + memcpy@GOTPCREL] + 1 1 0.33 cmp r14, rbx + 2 2 1.00 setbe al + 1 1 0.33 add rsp, 8 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 5.47 4.49 4.00 5.04 4.00 3.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - - 1.00 push r14 + - - - - 1.00 - 1.00 - push rbx + - - - - 1.00 - - 1.00 push rax + - - 0.48 0.51 - 0.01 - - mov rbx, rcx + - - 0.51 0.49 - - - - lea r14, [2*rsi + 5] + - - 0.48 0.05 - 0.47 - - and r14, -2 + - - 0.48 0.49 - 0.03 - - cmp r14, rcx + - - - - - 1.00 - - ja .LBB5_2 + - - 0.04 0.47 - 0.49 - - mov rax, rdi + - - 0.49 0.03 - 0.48 - - mov rdi, rdx + - - 0.03 0.48 - 0.49 - - mov rsi, rax + - - 0.48 0.51 - 0.01 - - mov rdx, r14 + - - - - 1.00 1.00 2.00 - call qword ptr [rip + memcpy@GOTPCREL] + - - 0.51 0.49 - - - - cmp r14, rbx + - - 1.94 - - 0.06 - - setbe al + - - 0.03 0.97 - - - - add rsp, 8 + - - - - - - - 1.00 pop rbx + - - - - - - 1.00 - pop r14 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_prefix_static_size.rs b/rust/zerocopy/benches/write_to_prefix_static_size.rs new file mode 100644 index 000000000..826222c12 --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_static_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_prefix_static_size( + source: &format::CocoPacket, + destination: &mut [u8], +) -> Option<()> { + source.write_to_prefix(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_prefix_static_size.x86-64 b/rust/zerocopy/benches/write_to_prefix_static_size.x86-64 new file mode 100644 index 000000000..9cf066295 --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_static_size.x86-64 @@ -0,0 +1,11 @@ +bench_write_to_prefix_static_size: + cmp rdx, 6 + jb .LBB5_2 + movzx eax, word ptr [rdi + 4] + mov word ptr [rsi + 4], ax + mov eax, dword ptr [rdi] + mov dword ptr [rsi], eax +.LBB5_2: + cmp rdx, 6 + setae al + ret diff --git a/rust/zerocopy/benches/write_to_prefix_static_size.x86-64.mca b/rust/zerocopy/benches/write_to_prefix_static_size.x86-64.mca new file mode 100644 index 000000000..5d17200ab --- /dev/null +++ b/rust/zerocopy/benches/write_to_prefix_static_size.x86-64.mca @@ -0,0 +1,57 @@ +Iterations: 100 +Instructions: 900 +Total Cycles: 233 +Total uOps: 900 + +Dispatch Width: 4 +uOps Per Cycle: 3.86 +IPC: 3.86 +Block RThroughput: 2.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 cmp rdx, 6 + 1 1 1.00 jb .LBB5_2 + 1 5 0.50 * movzx eax, word ptr [rdi + 4] + 1 1 1.00 * mov word ptr [rsi + 4], ax + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 1 1.00 * mov dword ptr [rsi], eax + 1 1 0.33 cmp rdx, 6 + 1 1 0.50 setae al + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.50 1.49 2.00 2.01 2.00 2.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.25 0.74 - 0.01 - - cmp rdx, 6 + - - - - - 1.00 - - jb .LBB5_2 + - - - - - - 0.50 0.50 movzx eax, word ptr [rdi + 4] + - - - - 1.00 - 0.48 0.52 mov word ptr [rsi + 4], ax + - - - - - - 0.52 0.48 mov eax, dword ptr [rdi] + - - - - 1.00 - 0.50 0.50 mov dword ptr [rsi], eax + - - 0.25 0.75 - - - - cmp rdx, 6 + - - 1.00 - - - - - setae al + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_static_size.rs b/rust/zerocopy/benches/write_to_static_size.rs new file mode 100644 index 000000000..3bb9435c5 --- /dev/null +++ b/rust/zerocopy/benches/write_to_static_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_static_size(source: &format::CocoPacket, destination: &mut [u8]) -> Option<()> { + source.write_to(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_static_size.x86-64 b/rust/zerocopy/benches/write_to_static_size.x86-64 new file mode 100644 index 000000000..d6413e0fd --- /dev/null +++ b/rust/zerocopy/benches/write_to_static_size.x86-64 @@ -0,0 +1,11 @@ +bench_write_to_static_size: + cmp rdx, 6 + jne .LBB5_2 + movzx eax, word ptr [rdi + 4] + mov word ptr [rsi + 4], ax + mov eax, dword ptr [rdi] + mov dword ptr [rsi], eax +.LBB5_2: + cmp rdx, 6 + sete al + ret diff --git a/rust/zerocopy/benches/write_to_static_size.x86-64.mca b/rust/zerocopy/benches/write_to_static_size.x86-64.mca new file mode 100644 index 000000000..cc5bb1d26 --- /dev/null +++ b/rust/zerocopy/benches/write_to_static_size.x86-64.mca @@ -0,0 +1,57 @@ +Iterations: 100 +Instructions: 900 +Total Cycles: 233 +Total uOps: 900 + +Dispatch Width: 4 +uOps Per Cycle: 3.86 +IPC: 3.86 +Block RThroughput: 2.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 cmp rdx, 6 + 1 1 1.00 jne .LBB5_2 + 1 5 0.50 * movzx eax, word ptr [rdi + 4] + 1 1 1.00 * mov word ptr [rsi + 4], ax + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 1 1.00 * mov dword ptr [rsi], eax + 1 1 0.33 cmp rdx, 6 + 1 1 0.50 sete al + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.50 1.49 2.00 2.01 2.00 2.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.25 0.74 - 0.01 - - cmp rdx, 6 + - - - - - 1.00 - - jne .LBB5_2 + - - - - - - 0.50 0.50 movzx eax, word ptr [rdi + 4] + - - - - 1.00 - 0.48 0.52 mov word ptr [rsi + 4], ax + - - - - - - 0.52 0.48 mov eax, dword ptr [rdi] + - - - - 1.00 - 0.50 0.50 mov dword ptr [rsi], eax + - - 0.25 0.75 - - - - cmp rdx, 6 + - - 1.00 - - - - - sete al + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_suffix_dynamic_size.rs b/rust/zerocopy/benches/write_to_suffix_dynamic_size.rs new file mode 100644 index 000000000..9fa6b91cd --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_dynamic_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_suffix_dynamic_size( + source: &format::CocoPacket, + destination: &mut [u8], +) -> Option<()> { + source.write_to_suffix(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64 b/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64 new file mode 100644 index 000000000..75f349562 --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64 @@ -0,0 +1,22 @@ +bench_write_to_suffix_dynamic_size: + push r14 + push rbx + push rax + mov rbx, rcx + lea r14, [2*rsi + 5] + and r14, -2 + sub rcx, r14 + jb .LBB5_2 + mov rax, rdi + add rdx, rcx + mov rdi, rdx + mov rsi, rax + mov rdx, r14 + call qword ptr [rip + memcpy@GOTPCREL] +.LBB5_2: + cmp rbx, r14 + setae al + add rsp, 8 + pop rbx + pop r14 + ret diff --git a/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64.mca b/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64.mca new file mode 100644 index 000000000..95cb9dfe2 --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_dynamic_size.x86-64.mca @@ -0,0 +1,79 @@ +Iterations: 100 +Instructions: 2000 +Total Cycles: 2890 +Total uOps: 2600 + +Dispatch Width: 4 +uOps Per Cycle: 0.90 +IPC: 0.69 +Block RThroughput: 6.5 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 2 5 1.00 * push r14 + 2 5 1.00 * push rbx + 2 5 1.00 * push rax + 1 1 0.33 mov rbx, rcx + 1 1 0.50 lea r14, [2*rsi + 5] + 1 1 0.33 and r14, -2 + 1 1 0.33 sub rcx, r14 + 1 1 1.00 jb .LBB5_2 + 1 1 0.33 mov rax, rdi + 1 1 0.33 add rdx, rcx + 1 1 0.33 mov rdi, rdx + 1 1 0.33 mov rsi, rax + 1 1 0.33 mov rdx, r14 + 4 7 1.00 * call qword ptr [rip + memcpy@GOTPCREL] + 1 1 0.33 cmp rbx, r14 + 1 1 0.50 setae al + 1 1 0.33 add rsp, 8 + 1 6 0.50 * pop rbx + 1 6 0.50 * pop r14 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 4.98 4.98 4.00 5.04 4.00 3.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - - 1.00 push r14 + - - - - 1.00 - 1.00 - push rbx + - - - - 1.00 - - 1.00 push rax + - - 0.94 0.05 - 0.01 - - mov rbx, rcx + - - 0.06 0.94 - - - - lea r14, [2*rsi + 5] + - - 0.93 0.02 - 0.05 - - and r14, -2 + - - 0.05 0.94 - 0.01 - - sub rcx, r14 + - - - - - 1.00 - - jb .LBB5_2 + - - 0.02 0.04 - 0.94 - - mov rax, rdi + - - 0.03 0.97 - - - - add rdx, rcx + - - 0.95 0.05 - - - - mov rdi, rdx + - - 0.94 0.03 - 0.03 - - mov rsi, rax + - - 0.01 0.03 - 0.96 - - mov rdx, r14 + - - - - 1.00 1.00 2.00 - call qword ptr [rip + memcpy@GOTPCREL] + - - 0.05 0.94 - 0.01 - - cmp rbx, r14 + - - 0.97 - - 0.03 - - setae al + - - 0.03 0.97 - - - - add rsp, 8 + - - - - - - - 1.00 pop rbx + - - - - - - 1.00 - pop r14 + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/write_to_suffix_static_size.rs b/rust/zerocopy/benches/write_to_suffix_static_size.rs new file mode 100644 index 000000000..1c95aba4b --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_static_size.rs @@ -0,0 +1,12 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_write_to_suffix_static_size( + source: &format::CocoPacket, + destination: &mut [u8], +) -> Option<()> { + source.write_to_suffix(destination).ok() +} diff --git a/rust/zerocopy/benches/write_to_suffix_static_size.x86-64 b/rust/zerocopy/benches/write_to_suffix_static_size.x86-64 new file mode 100644 index 000000000..934aa370d --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_static_size.x86-64 @@ -0,0 +1,11 @@ +bench_write_to_suffix_static_size: + cmp rdx, 6 + jb .LBB5_2 + movzx eax, word ptr [rdi + 4] + mov word ptr [rsi + rdx - 2], ax + mov eax, dword ptr [rdi] + mov dword ptr [rsi + rdx - 6], eax +.LBB5_2: + cmp rdx, 6 + setae al + ret diff --git a/rust/zerocopy/benches/write_to_suffix_static_size.x86-64.mca b/rust/zerocopy/benches/write_to_suffix_static_size.x86-64.mca new file mode 100644 index 000000000..6b18e4a44 --- /dev/null +++ b/rust/zerocopy/benches/write_to_suffix_static_size.x86-64.mca @@ -0,0 +1,57 @@ +Iterations: 100 +Instructions: 900 +Total Cycles: 233 +Total uOps: 900 + +Dispatch Width: 4 +uOps Per Cycle: 3.86 +IPC: 3.86 +Block RThroughput: 2.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.33 cmp rdx, 6 + 1 1 1.00 jb .LBB5_2 + 1 5 0.50 * movzx eax, word ptr [rdi + 4] + 1 1 1.00 * mov word ptr [rsi + rdx - 2], ax + 1 5 0.50 * mov eax, dword ptr [rdi] + 1 1 1.00 * mov dword ptr [rsi + rdx - 6], eax + 1 1 0.33 cmp rdx, 6 + 1 1 0.50 setae al + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.50 1.49 2.00 2.01 2.00 2.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.25 0.74 - 0.01 - - cmp rdx, 6 + - - - - - 1.00 - - jb .LBB5_2 + - - - - - - 0.50 0.50 movzx eax, word ptr [rdi + 4] + - - - - 1.00 - 0.48 0.52 mov word ptr [rsi + rdx - 2], ax + - - - - - - 0.52 0.48 mov eax, dword ptr [rdi] + - - - - 1.00 - 0.50 0.50 mov dword ptr [rsi + rdx - 6], eax + - - 0.25 0.75 - - - - cmp rdx, 6 + - - 1.00 - - - - - setae al + - - - - - 1.00 - - ret diff --git a/rust/zerocopy/benches/zero_dynamic_padding.rs b/rust/zerocopy/benches/zero_dynamic_padding.rs new file mode 100644 index 000000000..8eda0953d --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_padding.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_padding.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_zero_dynamic_padding(source: &mut format::LocoPacket) { + source.zero() +} diff --git a/rust/zerocopy/benches/zero_dynamic_padding.x86-64 b/rust/zerocopy/benches/zero_dynamic_padding.x86-64 new file mode 100644 index 000000000..7dccf1745 --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_padding.x86-64 @@ -0,0 +1,7 @@ +bench_zero_dynamic_padding: + lea rax, [rsi + 2*rsi] + movabs rdx, 9223372036854775804 + and rdx, rax + add rdx, 12 + xor esi, esi + jmp qword ptr [rip + memset@GOTPCREL] diff --git a/rust/zerocopy/benches/zero_dynamic_padding.x86-64.mca b/rust/zerocopy/benches/zero_dynamic_padding.x86-64.mca new file mode 100644 index 000000000..098fc1078 --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_padding.x86-64.mca @@ -0,0 +1,51 @@ +Iterations: 100 +Instructions: 600 +Total Cycles: 209 +Total uOps: 700 + +Dispatch Width: 4 +uOps Per Cycle: 3.35 +IPC: 2.87 +Block RThroughput: 1.8 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea rax, [rsi + 2*rsi] + 1 1 0.33 movabs rdx, 9223372036854775804 + 1 1 0.33 and rdx, rax + 1 1 0.33 add rdx, 12 + 1 0 0.25 xor esi, esi + 2 6 1.00 * jmp qword ptr [rip + memset@GOTPCREL] + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 1.66 1.66 - 1.68 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.33 0.67 - - - - lea rax, [rsi + 2*rsi] + - - 0.98 - - 0.02 - - movabs rdx, 9223372036854775804 + - - 0.01 0.66 - 0.33 - - and rdx, rax + - - 0.34 0.33 - 0.33 - - add rdx, 12 + - - - - - - - - xor esi, esi + - - - - - 1.00 0.50 0.50 jmp qword ptr [rip + memset@GOTPCREL] diff --git a/rust/zerocopy/benches/zero_dynamic_size.rs b/rust/zerocopy/benches/zero_dynamic_size.rs new file mode 100644 index 000000000..536d800eb --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_dynamic_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_zero_dynamic_size(source: &mut format::LocoPacket) { + source.zero() +} diff --git a/rust/zerocopy/benches/zero_dynamic_size.x86-64 b/rust/zerocopy/benches/zero_dynamic_size.x86-64 new file mode 100644 index 000000000..2b31ed644 --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_size.x86-64 @@ -0,0 +1,5 @@ +bench_zero_dynamic_size: + lea rdx, [2*rsi + 5] + and rdx, -2 + xor esi, esi + jmp qword ptr [rip + memset@GOTPCREL] diff --git a/rust/zerocopy/benches/zero_dynamic_size.x86-64.mca b/rust/zerocopy/benches/zero_dynamic_size.x86-64.mca new file mode 100644 index 000000000..0b086a29b --- /dev/null +++ b/rust/zerocopy/benches/zero_dynamic_size.x86-64.mca @@ -0,0 +1,47 @@ +Iterations: 100 +Instructions: 400 +Total Cycles: 142 +Total uOps: 500 + +Dispatch Width: 4 +uOps Per Cycle: 3.52 +IPC: 2.82 +Block RThroughput: 1.3 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 0.50 lea rdx, [2*rsi + 5] + 1 1 0.33 and rdx, -2 + 1 0 0.25 xor esi, esi + 2 6 1.00 * jmp qword ptr [rip + memset@GOTPCREL] + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - 0.99 1.00 - 1.01 0.50 0.50 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - 0.99 0.01 - - - - lea rdx, [2*rsi + 5] + - - - 0.99 - 0.01 - - and rdx, -2 + - - - - - - - - xor esi, esi + - - - - - 1.00 0.50 0.50 jmp qword ptr [rip + memset@GOTPCREL] diff --git a/rust/zerocopy/benches/zero_static_size.rs b/rust/zerocopy/benches/zero_static_size.rs new file mode 100644 index 000000000..fa7fa0839 --- /dev/null +++ b/rust/zerocopy/benches/zero_static_size.rs @@ -0,0 +1,9 @@ +use zerocopy::*; + +#[path = "formats/coco_static_size.rs"] +mod format; + +#[unsafe(no_mangle)] +fn bench_zero_static_size(source: &mut format::LocoPacket) { + source.zero() +} diff --git a/rust/zerocopy/benches/zero_static_size.x86-64 b/rust/zerocopy/benches/zero_static_size.x86-64 new file mode 100644 index 000000000..ced8e1894 --- /dev/null +++ b/rust/zerocopy/benches/zero_static_size.x86-64 @@ -0,0 +1,4 @@ +bench_zero_static_size: + mov word ptr [rdi + 4], 0 + mov dword ptr [rdi], 0 + ret diff --git a/rust/zerocopy/benches/zero_static_size.x86-64.mca b/rust/zerocopy/benches/zero_static_size.x86-64.mca new file mode 100644 index 000000000..042897ef2 --- /dev/null +++ b/rust/zerocopy/benches/zero_static_size.x86-64.mca @@ -0,0 +1,45 @@ +Iterations: 100 +Instructions: 300 +Total Cycles: 203 +Total uOps: 300 + +Dispatch Width: 4 +uOps Per Cycle: 1.48 +IPC: 1.48 +Block RThroughput: 2.0 + + +Instruction Info: +[1]: #uOps +[2]: Latency +[3]: RThroughput +[4]: MayLoad +[5]: MayStore +[6]: HasSideEffects (U) + +[1] [2] [3] [4] [5] [6] Instructions: + 1 1 1.00 * mov word ptr [rdi + 4], 0 + 1 1 1.00 * mov dword ptr [rdi], 0 + 1 1 1.00 U ret + + +Resources: +[0] - SBDivider +[1] - SBFPDivider +[2] - SBPort0 +[3] - SBPort1 +[4] - SBPort4 +[5] - SBPort5 +[6.0] - SBPort23 +[6.1] - SBPort23 + + +Resource pressure per iteration: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] + - - - - 2.00 1.00 1.00 1.00 + +Resource pressure by instruction: +[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions: + - - - - 1.00 - - 1.00 mov word ptr [rdi + 4], 0 + - - - - 1.00 - 1.00 - mov dword ptr [rdi], 0 + - - - - - 1.00 - - ret |