maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[x86] Teach the new vector shuffle lowering of v4f64 to prefer a direct 

VBLENDPD over using VSHUFPD. While the 256-bit variant of VBLENDPD slows
down to the same speed as VSHUFPD on Sandy Bridge CPUs, it has twice the
reciprocal throughput on Ivy Bridge CPUs much like it does everywhere
for 128-bits. There isn't a downside, so just eagerly use this
instruction when it suffices.

llvm-svn: 218208
This commit is contained in:
Chandler Carruth 2014-09-21 11:17:55 +00:00
parent 6aea21df8e
commit e81bfbada9
2 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -7237,6 +7237,7 @@ static SDValue lowerVectorShuffleAsBlend(SDLoc DL, MVT VT, SDValue V1,
switch (VT.SimpleTy) {
case MVT::v2f64:
case MVT::v4f32:
case MVT::v4f64:
return DAG.getNode(X86ISD::BLENDI, DL, VT, V1, V2,
DAG.getConstant(BlendMask, MVT::i8));
@ -9229,6 +9230,10 @@ static SDValue lowerV4F64VectorShuffle(SDValue Op, SDValue V1, SDValue V2,
if (isShuffleEquivalent(Mask, 5, 1, 7, 3))
return DAG.getNode(X86ISD::UNPCKH, DL, MVT::v4f64, V2, V1);
if (SDValue Blend =
lowerVectorShuffleAsBlend(DL, MVT::v4f64, V1, V2, Mask, DAG))
return Blend;
// Check if the blend happens to exactly fit that of SHUFPD.
if (Mask[0] < 4 && (Mask[1] == -1 || Mask[1] >= 4) &&
Mask[2] < 4 && (Mask[3] == -1 || Mask[3] >= 4)) {

4
llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
View File

@ -359,7 +359,7 @@ define <4 x double> @shuffle_v4f64_5163(<4 x double> %a, <4 x double> %b) {
define <4 x double> @shuffle_v4f64_0527(<4 x double> %a, <4 x double> %b) {
; ALL-LABEL: @shuffle_v4f64_0527
; ALL: # BB#0:
; ALL-NEXT: vshufpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; ALL-NEXT: vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
; ALL-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
ret <4 x double> %shuffle
@ -368,7 +368,7 @@ define <4 x double> @shuffle_v4f64_0527(<4 x double> %a, <4 x double> %b) {
define <4 x double> @shuffle_v4f64_4163(<4 x double> %a, <4 x double> %b) {
; ALL-LABEL: @shuffle_v4f64_4163
; ALL: # BB#0:
; ALL-NEXT: vshufpd {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
; ALL-NEXT: vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
; ALL-NEXT: retq
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
ret <4 x double> %shuffle