[InstCombine] Only fold extract element to trunc if vector hasOneUse (llvm#115627) (llvm#999)

Author: bcahoon

llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp

@@ -205,9 +205,9 @@ Instruction *InstCombinerImpl::foldBitcastExtElt(ExtractElementInst &Ext) {
     if (IsBigEndian)
       ExtIndexC = NumElts.getKnownMinValue() - 1 - ExtIndexC;
     unsigned ShiftAmountC = ExtIndexC * DestWidth;
-    if (!ShiftAmountC ||
-        (isDesirableIntType(X->getType()->getPrimitiveSizeInBits()) &&
-        Ext.getVectorOperand()->hasOneUse())) {
+    if ((!ShiftAmountC ||
+         isDesirableIntType(X->getType()->getPrimitiveSizeInBits())) &&
+        Ext.getVectorOperand()->hasOneUse()) {
       if (ShiftAmountC)
         X = Builder.CreateLShr(X, ShiftAmountC, "extelt.offset");
       if (DestTy->isFloatingPointTy()) {

llvm/test/Transforms/InstCombine/extractelement.ll

@@ -722,20 +722,14 @@ define i8 @bitcast_scalar_index_variable(i32 %x, i64 %y) {
   ret i8 %r
 }
 
-; extra use is ok if we don't need a shift
+; extra use is not ok, even if we don't need a shift
 
 define i8 @bitcast_scalar_index0_use(i64 %x) {
-; ANYLE-LABEL: @bitcast_scalar_index0_use(
-; ANYLE-NEXT:    [[V:%.*]] = bitcast i64 [[X:%.*]] to <8 x i8>
-; ANYLE-NEXT:    call void @use(<8 x i8> [[V]])
-; ANYLE-NEXT:    [[R:%.*]] = trunc i64 [[X]] to i8
-; ANYLE-NEXT:    ret i8 [[R]]
-;
-; ANYBE-LABEL: @bitcast_scalar_index0_use(
-; ANYBE-NEXT:    [[V:%.*]] = bitcast i64 [[X:%.*]] to <8 x i8>
-; ANYBE-NEXT:    call void @use(<8 x i8> [[V]])
-; ANYBE-NEXT:    [[R:%.*]] = extractelement <8 x i8> [[V]], i64 0
-; ANYBE-NEXT:    ret i8 [[R]]
+; ANY-LABEL: @bitcast_scalar_index0_use(
+; ANY-NEXT:    [[V:%.*]] = bitcast i64 [[X:%.*]] to <8 x i8>
+; ANY-NEXT:    call void @use(<8 x i8> [[V]])
+; ANY-NEXT:    [[R:%.*]] = extractelement <8 x i8> [[V]], i64 0
+; ANY-NEXT:    ret i8 [[R]]
 ;
 
   %v = bitcast i64 %x to <8 x i8>

llvm/test/Transforms/InstCombine/vector_insertelt_shuffle.ll

@@ -90,4 +90,26 @@ define <4 x float> @bazzzzzz(<4 x float> %x, i32 %a) {
   ret <4 x float> %ins1
 }
 
+; test that foldBitcastExtElt doesn't interfere with shuffle folding
+
+define <4 x half> @bitcast_extract_insert_to_shuffle(i32 %a, i32 %b) {
+; CHECK-LABEL: @bitcast_extract_insert_to_shuffle(
+; CHECK-NEXT:    [[AVEC:%.*]] = bitcast i32 [[A:%.*]] to <2 x half>
+; CHECK-NEXT:    [[BVEC:%.*]] = bitcast i32 [[B:%.*]] to <2 x half>
+; CHECK-NEXT:    [[INS3:%.*]] = shufflevector <2 x half> [[AVEC]], <2 x half> [[BVEC]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    ret <4 x half> [[INS3]]
+;
+  %avec = bitcast i32 %a to <2 x half>
+  %a0 = extractelement <2 x half> %avec, i32 0
+  %a1 = extractelement <2 x half> %avec, i32 1
+  %bvec = bitcast i32 %b to <2 x half>
+  %b0 = extractelement <2 x half> %bvec, i32 0
+  %b1 = extractelement <2 x half> %bvec, i32 1
+  %ins0 = insertelement <4 x half> undef, half %a0, i32 0
+  %ins1 = insertelement <4 x half> %ins0, half %a1, i32 1
+  %ins2 = insertelement <4 x half> %ins1, half %b0, i32 2
+  %ins3 = insertelement <4 x half> %ins2, half %b1, i32 3
+  ret <4 x half> %ins3
+}
+