aboutsummaryrefslogtreecommitdiff
path: root/src/cmd/compile/internal/amd64
diff options
context:
space:
mode:
authorKeith Randall <khr@golang.org>2021-05-07 14:14:39 -0700
committerBen Shi <powerman1st@163.com>2021-05-08 03:27:59 +0000
commitb211fe005860db3ceff5fd56af9951d6d1f44325 (patch)
tree2d4db9f01381ed1cab1ac47f620d08865e6a78ef /src/cmd/compile/internal/amd64
parentf24eac47710b0170fd45611ab1867e87701e0a95 (diff)
downloadgo-b211fe005860db3ceff5fd56af9951d6d1f44325.tar.gz
go-b211fe005860db3ceff5fd56af9951d6d1f44325.zip
cmd/compile: remove bit operations that modify memory directly
These operations (BT{S,R,C}{Q,L}modify) are quite a bit slower than other ways of doing the same thing. Without the BTxmodify operations, there are two fallback ways the compiler performs these operations: AND/OR/XOR operations directly on memory, or load-BTx-write sequences. The compiler kinda chooses one arbitrarily depending on rewrite rule application order. Currently, it uses load-BTx-write for the Const benchmarks and AND/OR/XOR directly to memory for the non-Const benchmarks. TBD, someone might investigate which of the two fallback strategies is really better. For now, they are both better than BTx ops. name old time/op new time/op delta BitSet-8 1.09µs ± 2% 0.64µs ± 5% -41.60% (p=0.000 n=9+10) BitClear-8 1.15µs ± 3% 0.68µs ± 6% -41.00% (p=0.000 n=10+10) BitToggle-8 1.18µs ± 4% 0.73µs ± 2% -38.36% (p=0.000 n=10+8) BitSetConst-8 37.0ns ± 7% 25.8ns ± 2% -30.24% (p=0.000 n=10+10) BitClearConst-8 30.7ns ± 2% 25.0ns ±12% -18.46% (p=0.000 n=10+10) BitToggleConst-8 36.9ns ± 1% 23.8ns ± 3% -35.46% (p=0.000 n=9+10) Fixes #45790 Update #45242 Change-Id: Ie33a72dc139f261af82db15d446cd0855afb4e59 Reviewed-on: https://go-review.googlesource.com/c/go/+/318149 Trust: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Ben Shi <powerman1st@163.com>
Diffstat (limited to 'src/cmd/compile/internal/amd64')
-rw-r--r--src/cmd/compile/internal/amd64/ssa.go4
1 files changed, 1 insertions, 3 deletions
diff --git a/src/cmd/compile/internal/amd64/ssa.go b/src/cmd/compile/internal/amd64/ssa.go
index 6a478de2a0..ca5f36e775 100644
--- a/src/cmd/compile/internal/amd64/ssa.go
+++ b/src/cmd/compile/internal/amd64/ssa.go
@@ -756,7 +756,6 @@ func ssaGenValue(s *ssagen.State, v *ssa.Value) {
p.To.Type = obj.TYPE_REG
p.To.Reg = v.Reg()
case ssa.OpAMD64MOVQstore, ssa.OpAMD64MOVSSstore, ssa.OpAMD64MOVSDstore, ssa.OpAMD64MOVLstore, ssa.OpAMD64MOVWstore, ssa.OpAMD64MOVBstore, ssa.OpAMD64MOVOstore,
- ssa.OpAMD64BTCQmodify, ssa.OpAMD64BTCLmodify, ssa.OpAMD64BTRQmodify, ssa.OpAMD64BTRLmodify, ssa.OpAMD64BTSQmodify, ssa.OpAMD64BTSLmodify,
ssa.OpAMD64ADDQmodify, ssa.OpAMD64SUBQmodify, ssa.OpAMD64ANDQmodify, ssa.OpAMD64ORQmodify, ssa.OpAMD64XORQmodify,
ssa.OpAMD64ADDLmodify, ssa.OpAMD64SUBLmodify, ssa.OpAMD64ANDLmodify, ssa.OpAMD64ORLmodify, ssa.OpAMD64XORLmodify:
p := s.Prog(v.Op.Asm())
@@ -804,8 +803,7 @@ func ssaGenValue(s *ssagen.State, v *ssa.Value) {
}
fallthrough
case ssa.OpAMD64ANDQconstmodify, ssa.OpAMD64ANDLconstmodify, ssa.OpAMD64ORQconstmodify, ssa.OpAMD64ORLconstmodify,
- ssa.OpAMD64BTCQconstmodify, ssa.OpAMD64BTCLconstmodify, ssa.OpAMD64BTSQconstmodify, ssa.OpAMD64BTSLconstmodify,
- ssa.OpAMD64BTRQconstmodify, ssa.OpAMD64BTRLconstmodify, ssa.OpAMD64XORQconstmodify, ssa.OpAMD64XORLconstmodify:
+ ssa.OpAMD64XORQconstmodify, ssa.OpAMD64XORLconstmodify:
sc := v.AuxValAndOff()
off := sc.Off64()
val := sc.Val64()