qbit/go
1
0
Fork 0
mirror of https://github.com/golang/go synced 2024-11-12 05:50:21 -07:00
Code Releases Activity

cmd/compile: enable disjoint memmove inlining on amd64

Browse Source 
Memmove can use AVX/prefetches/other optional instructions, so
only do it for small sizes, when call overhead dominates.

Change-Id: Ice5e93deb11462217f7fb5fc350b703109bb4090
Reviewed-on: https://go-review.googlesource.com/112517
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Michael Munday <mike.munday@ibm.com>
This commit is contained in:
Ilya Tocar 2018-05-09 15:49:22 -05:00
parent 3000795c83
commit c292b32f33
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/cmd/compile/internal/ssa/rewrite.go
View File

@ -905,7 +905,7 @@ func isInlinableMemmove(dst, src *Value, sz int64, c *Config) bool {
// have fast Move ops.
switch c.arch {
case "amd64", "amd64p32":
return sz <= 16
return sz <= 16 || (sz < 1024 && disjoint(dst, sz, src, sz))
case "386", "ppc64", "ppc64le", "arm64":
return sz <= 8
case "s390x":

5
test/codegen/copy.go
View File

@ -40,19 +40,22 @@ var x [256]byte
func moveDisjointStack() {
var s [256]byte
// s390x:-".*memmove"
// amd64:-".*memmove"
copy(s[:], x[:])
runtime.KeepAlive(&s)
}
func moveDisjointArg(b *[256]byte) {
func moveDisjointArg(b *[256]byte) {
var s [256]byte
// s390x:-".*memmove"
// amd64:-".*memmove"
copy(s[:], b[:])
runtime.KeepAlive(&s)
}
func moveDisjointNoOverlap(a *[256]byte) {
// s390x:-".*memmove"
// amd64:-".*memmove"
copy(a[:], a[128:])
}