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

[X86][AVX] canonicalizeLaneShuffleWithRepeatedOps - handle vperm2x128(movddup(x),movddup(y)) cases 

Fold vperm2x128(movddup(x),movddup(y)) -> movddup(vperm2x128(x,y))
This commit is contained in:
Simon Pilgrim 2021-01-22 16:05:19 +00:00
parent c33d36e066
commit bd122f6d21
3 changed files with 14 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -36922,6 +36922,15 @@ static SDValue canonicalizeLaneShuffleWithRepeatedOps(SDValue V,
return SDValue();
switch (SrcOpc0) {
case X86ISD::MOVDDUP: {
SDValue LHS = DAG.getBitcast(VT, Src0.getOperand(0));
SDValue RHS =
DAG.getBitcast(VT, Src1.isUndef() ? Src1 : Src1.getOperand(0));
SDValue Res =
DAG.getNode(X86ISD::VPERM2X128, DL, VT, LHS, RHS, V.getOperand(2));
Res = DAG.getNode(SrcOpc0, DL, SrcVT0, DAG.getBitcast(SrcVT0, Res));
return DAG.getBitcast(VT, Res);
}
case X86ISD::VSHLI:
case X86ISD::VSRLI:
case X86ISD::VSRAI:

3
llvm/test/CodeGen/X86/extract-concat.ll
View File

@ -68,13 +68,12 @@ define <16 x i64> @catcat(<4 x i64> %x) {
;
; AVX1-LABEL: catcat:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,2,3]
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm4
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: vmovddup {{.*#+}} ymm2 = ymm0[0,0,2,2]
; AVX1-NEXT: vpermilpd {{.*#+}} ymm3 = ymm0[1,1,3,3]
; AVX1-NEXT: vmovaps %ymm4, %ymm0
; AVX1-NEXT: retq

8
llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
View File

@ -109,8 +109,8 @@ define <4 x double> @shuffle_v4f64_1000(<4 x double> %a, <4 x double> %b) {
define <4 x double> @shuffle_v4f64_2200(<4 x double> %a, <4 x double> %b) {
; AVX1-LABEL: shuffle_v4f64_2200:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4f64_2200:
@ -129,8 +129,8 @@ define <4 x double> @shuffle_v4f64_2200(<4 x double> %a, <4 x double> %b) {
define <4 x double> @shuffle_v4f64_2222(<4 x double> %a, <4 x double> %b) {
; AVX1-LABEL: shuffle_v4f64_2222:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4f64_2222:
@ -149,8 +149,8 @@ define <4 x double> @shuffle_v4f64_2222(<4 x double> %a, <4 x double> %b) {
define <4 x double> @shuffle_v4f64_2222_bc(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4f64_2222_bc:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4f64_2222_bc:
@ -856,8 +856,8 @@ define <4 x i64> @shuffle_v4i64_1000(<4 x i64> %a, <4 x i64> %b) {
define <4 x i64> @shuffle_v4i64_2200(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_2200:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4i64_2200: