[X86] When inserting into the upper bits of a vXi1 vector, make sure we shift enough...

We may need to widen the vector to make the shifts legal, but if we do that we need to make sure we shift left/right after accounting for the new size. If not we can't guarantee we are shifting in zeros.

The test cases affected actually show cases where we should move the shifts all together, but that's another problem.

llvm-svn: 320248

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index bcffa72afeac934e0bd337e5343fd3d0a8baaea2..716b5edc4749614e905fd4abffabab7121ac4bf5 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -5099,7 +5099,8 @@ static SDValue insert1BitVector(SDValue Op, SelectionDAG &DAG,
     // Zero upper bits of the Vec
     WideSubVec = DAG.getNode(X86ISD::KSHIFTL, dl, WideOpVT, WideSubVec,
                              DAG.getConstant(IdxVal, dl, MVT::i8));
-    SDValue ShiftBits = DAG.getConstant(SubVecNumElems, dl, MVT::i8);
+    NumElems = WideOpVT.getVectorNumElements();
+    SDValue ShiftBits = DAG.getConstant(NumElems - IdxVal, dl, MVT::i8);
     Vec = DAG.getNode(ISD::INSERT_SUBVECTOR, dl, WideOpVT, Undef, Vec, ZeroIdx);
     Vec = DAG.getNode(X86ISD::KSHIFTL, dl, WideOpVT, Vec, ShiftBits);
     Vec = DAG.getNode(X86ISD::KSHIFTR, dl, WideOpVT, Vec, ShiftBits);

diff --git a/llvm/test/CodeGen/X86/avx512-skx-insert-subvec.ll b/llvm/test/CodeGen/X86/avx512-skx-insert-subvec.ll
index 4c650903e4716a5c3c6dc3667c653d7d5fe5cc7b..4421fc096732638b073272c0ac492ad44ef810b1 100644 (file)
--- a/llvm/test/CodeGen/X86/avx512-skx-insert-subvec.ll
+++ b/llvm/test/CodeGen/X86/avx512-skx-insert-subvec.ll
@@ -79,8 +79,8 @@ define <4 x i1> @test5(<2 x i1> %a, <2 x i1>%b) {
 ; CHECK-NEXT:    vpsllq $63, %xmm1, %xmm0
 ; CHECK-NEXT:    vptestmq %xmm0, %xmm0, %k1
 ; CHECK-NEXT:    kshiftlb $2, %k1, %k1
-; CHECK-NEXT:    kshiftlb $2, %k0, %k0
-; CHECK-NEXT:    kshiftrb $2, %k0, %k0
+; CHECK-NEXT:    kshiftlb $6, %k0, %k0
+; CHECK-NEXT:    kshiftrb $6, %k0, %k0
 ; CHECK-NEXT:    korb %k1, %k0, %k0
 ; CHECK-NEXT:    vpmovm2d %k0, %xmm0
 ; CHECK-NEXT:    retq
@@ -97,8 +97,8 @@ define <16 x i1> @test6(<2 x i1> %a, <2 x i1>%b) {
 ; CHECK-NEXT:    vpsllq $63, %xmm1, %xmm0
 ; CHECK-NEXT:    vptestmq %xmm0, %xmm0, %k1
 ; CHECK-NEXT:    kshiftlb $2, %k1, %k1
-; CHECK-NEXT:    kshiftlb $2, %k0, %k0
-; CHECK-NEXT:    kshiftrb $2, %k0, %k0
+; CHECK-NEXT:    kshiftlb $6, %k0, %k0
+; CHECK-NEXT:    kshiftrb $6, %k0, %k0
 ; CHECK-NEXT:    korb %k1, %k0, %k0
 ; CHECK-NEXT:    vpmovm2b %k0, %xmm0
 ; CHECK-NEXT:    retq