RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity

[DAG] scalarizeBinOpOfSplats - extract from the source of splat vector (PR46189)

Browse Source 
D79003/rG9fa58d1bf2f8 exposed an issue with scalarizeBinOpOfSplats that we were extracting from the splatted vector result instead of the source, the splat index is only valid for the source vector not the result, which may contain undefs, including at the splat index.
This commit is contained in:
Simon Pilgrim 2020-06-04 11:49:28 +01:00
parent 6f80acd90a
commit 7f449074ca
2 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -20550,8 +20550,8 @@ static SDValue scalarizeBinOpOfSplats(SDNode *N, SelectionDAG &DAG) {
SDLoc DL(N);
SDValue IndexC = DAG.getVectorIdxConstant(Index0, DL);
SDValue X = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, EltVT, N0, IndexC);
SDValue Y = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, EltVT, N1, IndexC);
SDValue X = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, EltVT, Src0, IndexC);
SDValue Y = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, EltVT, Src1, IndexC);
SDValue ScalarBO = DAG.getNode(Opcode, DL, EltVT, X, Y, N->getFlags());
// If all lanes but 1 are undefined, no need to splat the scalar result.

17
test/CodeGen/X86/pr46189.ll
View File

@ -12,12 +12,13 @@ define { i64, i64 } @PR46189(double %0, double %1, double %2, double %3, double
; SSE-NEXT: unpcklpd {{.*#+}} xmm3 = xmm3[0,0]
; SSE-NEXT: divpd %xmm3, %xmm5
; SSE-NEXT: cvttpd2dq %xmm5, %xmm0
; SSE-NEXT: subsd %xmm2, %xmm1
; SSE-NEXT: addsd %xmm2, %xmm2
; SSE-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; SSE-NEXT: movapd %xmm1, %xmm3
; SSE-NEXT: subsd %xmm2, %xmm3
; SSE-NEXT: addsd %xmm2, %xmm1
; SSE-NEXT: unpcklpd {{.*#+}} xmm3 = xmm3[0],xmm1[0]
; SSE-NEXT: unpcklpd {{.*#+}} xmm4 = xmm4[0,0]
; SSE-NEXT: divpd %xmm4, %xmm1
; SSE-NEXT: cvttpd2dq %xmm1, %xmm1
; SSE-NEXT: divpd %xmm4, %xmm3
; SSE-NEXT: cvttpd2dq %xmm3, %xmm1
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movq %xmm0, %rax
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
@ -32,9 +33,9 @@ define { i64, i64 } @PR46189(double %0, double %1, double %2, double %3, double
; AVX-NEXT: vmovddup {{.*#+}} xmm3 = xmm3[0,0]
; AVX-NEXT: vdivpd %xmm3, %xmm0, %xmm0
; AVX-NEXT: vcvttpd2dq %xmm0, %xmm0
; AVX-NEXT: vsubsd %xmm2, %xmm1, %xmm1
; AVX-NEXT: vaddsd %xmm2, %xmm0, %xmm2
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX-NEXT: vsubsd %xmm2, %xmm1, %xmm3
; AVX-NEXT: vaddsd %xmm2, %xmm1, %xmm1
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm3[0],xmm1[0]
; AVX-NEXT: vmovddup {{.*#+}} xmm2 = xmm4[0,0]
; AVX-NEXT: vdivpd %xmm2, %xmm1, %xmm1
; AVX-NEXT: vcvttpd2dq %xmm1, %xmm1