[x86] PR24562: fix incorrect folding of PSHUFB nodes with a mask where all indices...

This patch fixes a problem in function 'combineX86ShuffleChain' that causes a
chain of shuffles to be wrongly folded away when the combined shuffle mask has
only one element.

We may end up with a combined shuffle mask of one element as a result of
multiple calls to function 'canWidenShuffleElements()'.
Function canWidenShuffleElements attempts to simplify a shuffle mask by widening
the size of the elements being shuffled.
For every pair of shuffle indices, function canWidenShuffleElements checks if
indices refer to adjacent elements. If all pairs refer to "adjacent" elements
then the shuffle mask is safely widened. As a consequence of widening, we end up
with a new shuffle mask which is half the size of the original shuffle mask.

The byte shuffle (pshufb) from test pr24562.ll has a mask of all SM_SentinelZero
indices. Function canWidenShuffleElements would combine each pair of
SM_SentinelZero indices into a single SM_SentinelZero index. So, in a
logarithmic number of steps (4 in this case), the pshufb mask is simplified to
a mask with only one index which is equal to SM_SentinelZero.

Before this patch, function combineX86ShuffleChain wrongly assumed that a mask
of size one is always equivalent to an identity mask. So, the entire shuffle
chain was just folded away as the combined shuffle mask was treated as a no-op
mask.

With this patch we know check if the only element of a combined shuffle mask is
SM_SentinelZero. In case, we propagate a zero vector.

Differential Revision: http://reviews.llvm.org/D13364

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@250027 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 9ffce63501b93c59c04e68e9996379393a627407..82f9fa7a5e845483db20a3123c7fbb748c885416 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -21991,10 +21991,22 @@ static bool combineX86ShuffleChain(SDValue Op, SDValue Root, ArrayRef<int> Mask,
   MVT RootVT = Root.getSimpleValueType();
   SDLoc DL(Root);
 
   MVT RootVT = Root.getSimpleValueType();
   SDLoc DL(Root);
 

-  // Just remove no-op shuffle masks.

   if (Mask.size() == 1) {
   if (Mask.size() == 1) {

-    DCI.CombineTo(Root.getNode(), DAG.getBitcast(RootVT, Input),
-                  /*AddTo*/ true);
+    int Index = Mask[0];
+    assert((Index >= 0 || Index == SM_SentinelUndef ||
+            Index == SM_SentinelZero) &&
+           "Invalid shuffle index found!");
+
+    // We may end up with an accumulated mask of size 1 as a result of
+    // widening of shuffle operands (see function canWidenShuffleElements).
+    // If the only shuffle index is equal to SM_SentinelZero then propagate
+    // a zero vector. Otherwise, the combine shuffle mask is a no-op shuffle
+    // mask, and therefore the entire chain of shuffles can be folded away.
+    if (Index == SM_SentinelZero)
+      DCI.CombineTo(Root.getNode(), getZeroVector(RootVT, Subtarget, DAG, DL));
+    else
+      DCI.CombineTo(Root.getNode(), DAG.getBitcast(RootVT, Input),
+                    /*AddTo*/ true);

     return true;
   }
 
     return true;
   }
 

diff --git a/test/CodeGen/X86/pr24562.ll b/test/CodeGen/X86/pr24562.ll
new file mode 100644 (file)
index 0000000..f2e134b
--- /dev/null
+++ b/test/CodeGen/X86/pr24562.ll
@@ -0,0 +1,19 @@
+; RUN: llc -mattr=+ssse3 -mtriple=x86_64-unknown-unknown < %s | FileCheck %s
+
+; The pshufb from function @pr24562 was wrongly folded into its first operand
+; as a result of a late target shuffle combine on the legalized selection dag.
+; 
+; Check that the pshufb is correctly folded to a zero vector.
+
+define <2 x i64> @pr24562() {
+; CHECK-LABEL: pr24562:
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    xorps %xmm0, %xmm0
+; CHECK-NEXT:    retq
+entry:
+  %0 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>, <16 x i8> <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>) #2
+  %1 = bitcast <16 x i8> %0 to <2 x i64>
+  ret <2 x i64> %1
+}
+
+declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>)