Stowage/go
2
0
Fork 0
mirror of https://github.com/golang/go.git synced 2025-12-08 06:10:04 +00:00
Code Issues Projects Releases Packages Wiki Activity

[dev.simd] simd, cmd/compile: add widening unsigned converts 8->16->32

Browse source 
Change-Id: If0bde7154bd622573375eba5539fd642b8ef9d2f
Reviewed-on: https://go-review.googlesource.com/c/go/+/696555
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Junyang Shao <shaojunyang@google.com>
This commit is contained in:
David Chase 2025-08-15 17:05:05 -04:00
parent 0f660d675f
commit 4fce49b86c
10 changed files with 404 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/cmd/compile/internal/amd64/simdssa.go
View file

@ -44,9 +44,15 @@ func ssaGenSIMDValue(s *ssagen.State, v *ssa.Value) bool {
ssa.OpAMD64VCVTTPS2DQ128,
ssa.OpAMD64VCVTTPS2DQ256,
ssa.OpAMD64VCVTTPS2DQ512,
ssa.OpAMD64VPMOVZXBW256,
ssa.OpAMD64VPMOVZXBW512,
ssa.OpAMD64VPMOVZXBW128,
ssa.OpAMD64VCVTPS2UDQ128,
ssa.OpAMD64VCVTPS2UDQ256,
ssa.OpAMD64VCVTPS2UDQ512,
ssa.OpAMD64VPMOVZXWD256,
ssa.OpAMD64VPMOVZXWD512,
ssa.OpAMD64VPMOVZXWD128,
ssa.OpAMD64VPOPCNTB128,
ssa.OpAMD64VPOPCNTB256,
ssa.OpAMD64VPOPCNTB512,
@ -679,9 +685,15 @@ func ssaGenSIMDValue(s *ssagen.State, v *ssa.Value) bool {
ssa.OpAMD64VCVTTPS2DQMasked128,
ssa.OpAMD64VCVTTPS2DQMasked256,
ssa.OpAMD64VCVTTPS2DQMasked512,
ssa.OpAMD64VPMOVZXBWMasked256,
ssa.OpAMD64VPMOVZXBWMasked512,
ssa.OpAMD64VPMOVZXBWMasked128,
ssa.OpAMD64VCVTPS2UDQMasked128,
ssa.OpAMD64VCVTPS2UDQMasked256,
ssa.OpAMD64VCVTPS2UDQMasked512,
ssa.OpAMD64VPMOVZXWDMasked256,
ssa.OpAMD64VPMOVZXWDMasked512,
ssa.OpAMD64VPMOVZXWDMasked128,
ssa.OpAMD64VEXPANDPSMasked128,
ssa.OpAMD64VEXPANDPSMasked256,
ssa.OpAMD64VEXPANDPSMasked512,
@ -1289,9 +1301,15 @@ func ssaGenSIMDValue(s *ssagen.State, v *ssa.Value) bool {
ssa.OpAMD64VCVTTPS2DQMasked128,
ssa.OpAMD64VCVTTPS2DQMasked256,
ssa.OpAMD64VCVTTPS2DQMasked512,
ssa.OpAMD64VPMOVZXBWMasked256,
ssa.OpAMD64VPMOVZXBWMasked512,
ssa.OpAMD64VPMOVZXBWMasked128,
ssa.OpAMD64VCVTPS2UDQMasked128,
ssa.OpAMD64VCVTPS2UDQMasked256,
ssa.OpAMD64VCVTPS2UDQMasked512,
ssa.OpAMD64VPMOVZXWDMasked256,
ssa.OpAMD64VPMOVZXWDMasked512,
ssa.OpAMD64VPMOVZXWDMasked128,
ssa.OpAMD64VDIVPSMasked128,
ssa.OpAMD64VDIVPSMasked256,
ssa.OpAMD64VDIVPSMasked512,