From ce450f893d551e25123e0bdb27acc9a85d15cb7f Mon Sep 17 00:00:00 2001 From: Ali Saidi Date: Sat, 4 Sep 2021 15:11:26 -0500 Subject: [PATCH] Use the 64b inner:monotonize() implementation not the 128b one for aarch64 aarch64 prior to v8.4 (FEAT_LSE2) doesn't have an instruction that guarantees untorn 128b reads except for completing a 128b load/store exclusive pair (ldxp/stxp) or compare-and-swap (casp) successfully. The requirement to complete a 128b read+write atomic is actually more expensive and more unfair than the previous implementation of monotonize() which used a Mutex on aarch64, especially at large core counts. For aarch64 switch to the 64b atomic implementation which is about 13x faster for a benchmark that involves many calls to Instant::now(). --- library/std/src/time/monotonic.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/library/std/src/time/monotonic.rs b/library/std/src/time/monotonic.rs index fa96b7abff6..5783fa760df 100644 --- a/library/std/src/time/monotonic.rs +++ b/library/std/src/time/monotonic.rs @@ -5,7 +5,7 @@ pub(super) fn monotonize(raw: time::Instant) -> time::Instant { inner::monotonize(raw) } -#[cfg(all(target_has_atomic = "64", not(target_has_atomic = "128")))] +#[cfg(any(all(target_has_atomic = "64", not(target_has_atomic = "128")), target_arch = "aarch64"))] pub mod inner { use crate::sync::atomic::AtomicU64; use crate::sync::atomic::Ordering::*; @@ -70,7 +70,7 @@ pub mod inner { } } -#[cfg(target_has_atomic = "128")] +#[cfg(all(target_has_atomic = "128", not(target_arch = "aarch64")))] pub mod inner { use crate::sync::atomic::AtomicU128; use crate::sync::atomic::Ordering::*;