From 99482f2f9e7710206386ff45869cb76a53e0ac76 Mon Sep 17 00:00:00 2001 From: Rick Hudson Date: Thu, 19 Feb 2015 18:11:24 -0500 Subject: [PATCH] runtime: Add prefetch to allocation code The routine mallocgc retrieves objects from freelists. Prefetch the object that will be returned in the next call to mallocgc. Experiments indicate that this produces a 1% improvement when using prefetchnta and less when using prefetcht0, prefetcht1, or prefetcht2. Benchmark numbers indicate a 1% improvement over no prefetch, much less over prefetcht0, prefetcht1, and prefetcht2. These numbers were for the garbage benchmark with MAXPROCS=4 no prefetch >> 5.96 / 5.77 / 5.89 prefetcht0(uintptr(v.ptr().next)) >> 5.88 / 6.17 / 5.84 prefetcht1(uintptr(v.ptr().next)) >> 5.88 / 5.89 / 5.91 prefetcht2(uintptr(v.ptr().next)) >> 5.87 / 6.47 / 5.92 prefetchnta(uintptr(v.ptr().next)) >> 5.72 / 5.84 / 5.85 Change-Id: I54e07172081cccb097d5b5ce8789d74daa055ed9 Reviewed-on: https://go-review.googlesource.com/5350 Reviewed-by: Dmitry Vyukov Reviewed-by: Austin Clements --- src/runtime/malloc.go | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/src/runtime/malloc.go b/src/runtime/malloc.go index 475f97fd05..fac5ca49ce 100644 --- a/src/runtime/malloc.go +++ b/src/runtime/malloc.go @@ -553,7 +553,8 @@ func mallocgc(size uintptr, typ *_type, flags uint32) unsafe.Pointer { } s.freelist = v.ptr().next s.ref++ - //TODO: prefetch v.next + // prefetchnta offers best performance, see change list message. + prefetchnta(uintptr(v.ptr().next)) x = unsafe.Pointer(v) (*[2]uint64)(x)[0] = 0 (*[2]uint64)(x)[1] = 0 @@ -584,7 +585,8 @@ func mallocgc(size uintptr, typ *_type, flags uint32) unsafe.Pointer { } s.freelist = v.ptr().next s.ref++ - //TODO: prefetch + // prefetchnta offers best performance, see change list message. + prefetchnta(uintptr(v.ptr().next)) x = unsafe.Pointer(v) if flags&flagNoZero == 0 { v.ptr().next = 0