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

[DAGCombine] Generalize distributeTruncateThroughAnd to work with any non-opaque constant or constant vector 

llvm-svn: 284574
This commit is contained in:
Simon Pilgrim 2016-10-19 08:57:37 +00:00
parent 99eeab7ff3
commit b2ca2505cc
4 changed files with 15 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -4445,19 +4445,15 @@ SDValue DAGCombiner::distributeTruncateThroughAnd(SDNode *N) {
// (truncate:TruncVT (and N00, N01C)) -> (and (truncate:TruncVT N00), TruncC)
if (N->hasOneUse() && N->getOperand(0).hasOneUse()) {
SDValue N01 = N->getOperand(0).getOperand(1);
if (ConstantSDNode *N01C = isConstOrConstSplat(N01)) {
if (!N01C->isOpaque()) {
if (isConstantOrConstantVector(N01, /* NoOpaques */ true)) {
SDLoc DL(N);
EVT TruncVT = N->getValueType(0);
SDValue N00 = N->getOperand(0).getOperand(0);
APInt TruncC = N01C->getAPIntValue();
TruncC = TruncC.trunc(TruncVT.getScalarSizeInBits());
SDLoc DL(N);
return DAG.getNode(ISD::AND, DL, TruncVT,
DAG.getNode(ISD::TRUNCATE, DL, TruncVT, N00),
DAG.getConstant(TruncC, DL, TruncVT));
}
SDValue Trunc00 = DAG.getNode(ISD::TRUNCATE, DL, TruncVT, N00);
SDValue Trunc01 = DAG.getNode(ISD::TRUNCATE, DL, TruncVT, N01);
AddToWorklist(Trunc00.getNode());
AddToWorklist(Trunc01.getNode());
return DAG.getNode(ISD::AND, DL, TruncVT, Trunc00, Trunc01);
}
}

5
llvm/test/CodeGen/X86/combine-shl.ll
View File

@ -98,11 +98,10 @@ define <4 x i32> @combine_vec_shl_known_zero1(<4 x i32> %x) {
define <4 x i32> @combine_vec_shl_trunc_and(<4 x i32> %x, <4 x i64> %y) {
; SSE-LABEL: combine_vec_shl_trunc_and:
; SSE: # BB#0:
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: pslld $23, %xmm1
; SSE-NEXT: paddd {{.*}}(%rip), %xmm1
; SSE-NEXT: cvttps2dq %xmm1, %xmm1
@ -111,9 +110,9 @@ define <4 x i32> @combine_vec_shl_trunc_and(<4 x i32> %x, <4 x i64> %y) {
;
; AVX-LABEL: combine_vec_shl_trunc_and:
; AVX: # BB#0:
; AVX-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
; AVX-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsllvd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq

5
llvm/test/CodeGen/X86/combine-sra.ll
View File

@ -161,11 +161,10 @@ define <4 x i32> @combine_vec_ashr_ashr2(<4 x i32> %x) {
define <4 x i32> @combine_vec_ashr_trunc_and(<4 x i32> %x, <4 x i64> %y) {
; SSE-LABEL: combine_vec_ashr_trunc_and:
; SSE: # BB#0:
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm2
; SSE-NEXT: psrldq {{.*#+}} xmm2 = xmm2[12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE-NEXT: movdqa %xmm0, %xmm3
@ -187,9 +186,9 @@ define <4 x i32> @combine_vec_ashr_trunc_and(<4 x i32> %x, <4 x i64> %y) {
;
; AVX-LABEL: combine_vec_ashr_trunc_and:
; AVX: # BB#0:
; AVX-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
; AVX-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsravd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq

5
llvm/test/CodeGen/X86/combine-srl.ll
View File

@ -507,11 +507,10 @@ declare <4 x i32> @llvm.ctlz.v4i32(<4 x i32>, i1)
define <4 x i32> @combine_vec_lshr_trunc_and(<4 x i32> %x, <4 x i64> %y) {
; SSE-LABEL: combine_vec_lshr_trunc_and:
; SSE: # BB#0:
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm2
; SSE-NEXT: psrldq {{.*#+}} xmm2 = xmm2[12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE-NEXT: movdqa %xmm0, %xmm3
@ -533,9 +532,9 @@ define <4 x i32> @combine_vec_lshr_trunc_and(<4 x i32> %x, <4 x i64> %y) {
;
; AVX-LABEL: combine_vec_lshr_trunc_and:
; AVX: # BB#0:
; AVX-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
; AVX-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq