mirror of
https://github.com/rust-lang/rust.git
synced 2025-01-13 00:04:12 +00:00
e244e840f2
[Arm64] use isb instruction instead of yield in spin loops On arm64 we have seen on several databases that ISB (instruction synchronization barrier) is better to use than yield in a spin loop. The yield instruction is a nop. The isb instruction puts the processor to sleep for some short time. isb is a good equivalent to the pause instruction on x86. Below is an experiment that shows the effects of yield and isb on Arm64 and the time of a pause instruction on x86 Intel processors. The micro-benchmarks use https://github.com/google/benchmark.git ``` $ cat a.cc static void BM_scalar_increment(benchmark::State& state) { int i = 0; for (auto _ : state) benchmark::DoNotOptimize(i++); } BENCHMARK(BM_scalar_increment); static void BM_yield(benchmark::State& state) { for (auto _ : state) asm volatile("yield"::); } BENCHMARK(BM_yield); static void BM_isb(benchmark::State& state) { for (auto _ : state) asm volatile("isb"::); } BENCHMARK(BM_isb); BENCHMARK_MAIN(); $ g++ -o run a.cc -O2 -lbenchmark -lpthread $ ./run -------------------------------------------------------------- Benchmark Time CPU Iterations -------------------------------------------------------------- AWS Graviton2 (Neoverse-N1) processor: BM_scalar_increment 0.485 ns 0.485 ns 1000000000 BM_yield 0.400 ns 0.400 ns 1000000000 BM_isb 13.2 ns 13.2 ns 52993304 AWS Graviton (A-72) processor: BM_scalar_increment 0.897 ns 0.874 ns 801558633 BM_yield 0.877 ns 0.875 ns 800002377 BM_isb 13.0 ns 12.7 ns 55169412 Apple Arm64 M1 processor: BM_scalar_increment 0.315 ns 0.315 ns 1000000000 BM_yield 0.313 ns 0.313 ns 1000000000 BM_isb 9.06 ns 9.06 ns 77259282 ``` ``` static void BM_pause(benchmark::State& state) { for (auto _ : state) asm volatile("pause"::); } BENCHMARK(BM_pause); Intel Skylake processor: BM_scalar_increment 0.295 ns 0.295 ns 1000000000 BM_pause 41.7 ns 41.7 ns 16780553 ``` Tested on Graviton2 aarch64-linux with `./x.py test`. |
||
|---|---|---|
| .. | ||
| alloc | ||
| array | ||
| char | ||
| convert | ||
| fmt | ||
| future | ||
| hash | ||
| iter | ||
| macros | ||
| mem | ||
| num | ||
| ops | ||
| prelude | ||
| ptr | ||
| slice | ||
| str | ||
| stream | ||
| sync | ||
| task | ||
| unicode | ||
| any.rs | ||
| ascii.rs | ||
| bool.rs | ||
| borrow.rs | ||
| cell.rs | ||
| clone.rs | ||
| cmp.rs | ||
| default.rs | ||
| ffi.rs | ||
| hint.rs | ||
| internal_macros.rs | ||
| intrinsics.rs | ||
| lazy.rs | ||
| lib.rs | ||
| marker.rs | ||
| option.rs | ||
| panic.rs | ||
| panicking.rs | ||
| pin.rs | ||
| primitive.rs | ||
| raw.rs | ||
| result.rs | ||
| time.rs | ||
| tuple.rs | ||
| unit.rs | ||