[dev.ssa] cmd/compile: Use movups for xmm->xmm mov
Movups is 1 byte smaller than movapd that we currently use.
Change-Id: I22f771f066529352722a28543535ec43497cb9c5
Reviewed-on: https://go-review.googlesource.com/19938
Reviewed-by: David Chase <drchase@google.com>
diff --git a/src/cmd/compile/internal/gc/ssa.go b/src/cmd/compile/internal/gc/ssa.go
index 8e68c20..b46016f 100644
--- a/src/cmd/compile/internal/gc/ssa.go
+++ b/src/cmd/compile/internal/gc/ssa.go
@@ -4999,7 +4999,9 @@
if t.IsFloat() {
// Moving the whole sse2 register is faster
// than moving just the correct low portion of it.
- return x86.AMOVAPD
+ // There is no xmm->xmm move with 1 byte opcode,
+ // so use movups, which has 2 byte opcode.
+ return x86.AMOVUPS
} else {
switch t.Size() {
case 1:
