diff options
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/VectorCombine.cpp | 3 | ||||
| -rw-r--r-- | llvm/test/Transforms/VectorCombine/X86/select-shuffle.ll | 9 |
2 files changed, 8 insertions, 4 deletions
diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp index 9d43fb4..15deaf9 100644 --- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp +++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp @@ -1794,6 +1794,9 @@ bool VectorCombine::foldShuffleToIdentity(Instruction &I) { } } + if (NumVisited <= 1) + return false; + // If we got this far, we know the shuffles are superfluous and can be // removed. Scan through again and generate the new tree of instructions. std::function<Value *(ArrayRef<InstLane>)> Generate = diff --git a/llvm/test/Transforms/VectorCombine/X86/select-shuffle.ll b/llvm/test/Transforms/VectorCombine/X86/select-shuffle.ll index 60a6c4b..685d661 100644 --- a/llvm/test/Transforms/VectorCombine/X86/select-shuffle.ll +++ b/llvm/test/Transforms/VectorCombine/X86/select-shuffle.ll @@ -12,11 +12,12 @@ define <4 x double> @PR60649() { ; CHECK: unreachable: ; CHECK-NEXT: br label [[END]] ; CHECK: end: -; CHECK-NEXT: [[TMP0:%.*]] = phi <4 x double> [ zeroinitializer, [[ENTRY:%.*]] ], [ zeroinitializer, [[UNREACHABLE:%.*]] ] +; CHECK-NEXT: [[T0:%.*]] = phi <4 x double> [ zeroinitializer, [[ENTRY:%.*]] ], [ zeroinitializer, [[UNREACHABLE:%.*]] ] ; CHECK-NEXT: [[T1:%.*]] = phi <4 x double> [ zeroinitializer, [[ENTRY]] ], [ zeroinitializer, [[UNREACHABLE]] ] -; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[TMP0]], <4 x double> [[TMP0]], <4 x i32> <i32 2, i32 3, i32 poison, i32 poison> -; CHECK-NEXT: [[TMP2:%.*]] = fdiv <4 x double> [[TMP0]], <double 0.000000e+00, double 0.000000e+00, double undef, double undef> -; CHECK-NEXT: [[TMP3:%.*]] = fmul <4 x double> [[TMP1]], <double 0.000000e+00, double 0.000000e+00, double undef, double undef> +; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x double> [[T0]], <4 x double> [[T0]], <4 x i32> <i32 2, i32 3, i32 poison, i32 poison> +; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[T0]], <4 x double> [[T0]], <4 x i32> <i32 0, i32 1, i32 poison, i32 poison> +; CHECK-NEXT: [[TMP2:%.*]] = fdiv <4 x double> [[TMP1]], <double 0.000000e+00, double 0.000000e+00, double undef, double undef> +; CHECK-NEXT: [[TMP3:%.*]] = fmul <4 x double> [[TMP0]], <double 0.000000e+00, double 0.000000e+00, double undef, double undef> ; CHECK-NEXT: [[T5:%.*]] = shufflevector <4 x double> [[TMP2]], <4 x double> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 4, i32 5> ; CHECK-NEXT: ret <4 x double> [[T5]] ; |