DAGCombine: Make sure we only eliminate trunc/extend when the scales of truncation and extension match.

This fixes PR33368.

Reviewer: rksimon

Differential Revision:  https://reviews.llvm.org/D34069

llvm-svn: 306345

2 files changed, 44 insertions, 5 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index d02dcb6f443..d1a5a98607c 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -15013,6 +15013,11 @@ static SDValue combineTruncationShuffle(ShuffleVectorSDNode *SVN,
   unsigned NumElts = VT.getVectorNumElements();
   unsigned EltSizeInBits = VT.getScalarSizeInBits();
   unsigned ExtSrcSizeInBits = N00.getScalarValueSizeInBits();
+  unsigned ExtDstSizeInBits = N0.getScalarValueSizeInBits();
+
+  if (ExtDstSizeInBits % ExtSrcSizeInBits != 0)
+    return SDValue();
+  unsigned ExtScale = ExtDstSizeInBits / ExtSrcSizeInBits;
 
   // (v4i32 truncate_vector_inreg(v2i64)) == shuffle<0,2-1,-1>
   // (v8i16 truncate_vector_inreg(v4i32)) == shuffle<0,2,4,6,-1,-1,-1,-1>
@@ -15034,11 +15039,10 @@ static SDValue combineTruncationShuffle(ShuffleVectorSDNode *SVN,
   if (EltSizeInBits != ExtSrcSizeInBits)
     return SDValue();
 
-  // Attempt to match a 'truncate_vector_inreg' shuffle, we just search for
-  // power-of-2 truncations as they are the most likely.
-  for (unsigned Scale = 2; Scale < NumElts; Scale *= 2)
-    if (isTruncate(Scale))
-      return DAG.getBitcast(VT, N00);
+  // We can remove *extend_vector_inreg only if the truncation happens at
+  // the same scale as the extension.
+  if (isTruncate(ExtScale))
+    return DAG.getBitcast(VT, N00);
 
   return SDValue();
 }
diff --git a/llvm/test/CodeGen/X86/vector-truncate-combine.ll b/llvm/test/CodeGen/X86/vector-truncate-combine.ll
new file mode 100644
index 00000000000..1a6dac8fa6e
--- /dev/null
+++ b/llvm/test/CodeGen/X86/vector-truncate-combine.ll
@@ -0,0 +1,35 @@
+; RUN: llc -mtriple=x86_64-- -O2 -start-after=stack-protector -stop-before=loops %s -o - | FileCheck %s
+
+; This test verifies the fix for PR33368.
+;
+; The expected outcome of the operation is to store bytes 0 and 2 of the incoming
+; parameter into c2 (a 2 x i8 vector). DAGCombine converts shuffles into a
+; sequence of extend and subsequent truncate operations. The bug was that an extension
+; by 4 followed by a truncation by 8 was completely eliminated.
+
+; The test checks for the correct sequence of operations that results from the
+; preservation of the extend/truncate operations mentioned above (2 extend and
+; 3 truncate instructions).
+;
+; NOTE: This operation could be collapsed in to a single truncate. Once that is done
+; this test will have to be adjusted.
+
+; CHECK:      PUNPCKLBWrr
+; CHECK:      PUNPCKLWDrr
+; CHECK:      PACKUSWBrr
+; CHECK:      PACKUSWBrr
+; CHECK:      PACKUSWBrr
+
+define void @test(double %vec.coerce) local_unnamed_addr {
+entry:
+  %c2 = alloca <2 x i8>, align 2
+  %0 = bitcast double %vec.coerce to <8 x i8>
+  %1 = shufflevector <8 x i8> %0, <8 x i8> undef, <4 x i32> <i32 2, i32 undef, i32 undef, i32 0>
+  %2 = shufflevector <4 x i8> %1, <4 x i8> undef, <2 x i32> <i32 3, i32 0>
+  store volatile <2 x i8> %2, <2 x i8>* %c2, align 2
+  br label %if.end
+
+if.end:
+  %3 = bitcast <2 x i8> %2 to i16
+  ret void
+}