[x86] Fix another miscompile found through fuzz testing the new vector

shuffle lowering.

This is closely related to the previous one. Here we failed to use the
source offset when swapping in the other case -- where we end up
swapping the *final* shuffle. The cause of this bug is a bit different:
I simply wasn't thinking about the fact that this mask is actually
a slice of a wide mask and thus has numbers that need SourceOffset
applied. Simple fix. Would be even more simple with an algorithm-y thing
to use here, but correctness first. =]

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215095 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index d85ac5e55e43389aa694247e9bce8a229873163a..c62c2fd5f3584a0c0437208f1ba8200b16c8d226 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -7546,10 +7546,10 @@ static SDValue lowerV8I16SingleInputVectorShuffle(
           // We also have to update the final source mask in this case because
           // it may need to undo the above swap.
           for (int &M : FinalSourceHalfMask)
-            if (M == (InputsFixed[0] ^ 1))
-              M = InputsFixed[1];
-            else if (M == InputsFixed[1])
-              M = InputsFixed[0] ^ 1;
+            if (M == (InputsFixed[0] ^ 1) + SourceOffset)
+              M = InputsFixed[1] + SourceOffset;
+            else if (M == InputsFixed[1] + SourceOffset)
+              M = InputsFixed[0] ^ 1 + SourceOffset;
 
           InputsFixed[1] = InputsFixed[0] ^ 1;
         }

diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index 5c6a4dbaa4b96582526c2ea303dc91bc97176f2d..5d0509f45cadee3437160a1de175285e51243202 100644 (file)
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -238,6 +238,23 @@ define <8 x i16> @shuffle_v8i16_66751643(<8 x i16> %a, <8 x i16> %b) {
   ret <8 x i16> %shuffle
 }
 
+define <8 x i16> @shuffle_v8i16_60514754(<8 x i16> %a, <8 x i16> %b) {
+; SSE2-LABEL: @shuffle_v8i16_60514754
+; SSE2:       # BB#0:
+; SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,6,5,4,7]
+; SSE2-NEXT:    pshufd {{.*}} # xmm0 = xmm0[0,2,2,3]
+; SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[2,0,3,1,4,5,6,7]
+; SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,6,7,5,6]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: @shuffle_v8i16_60514754
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    pshufb {{.*}} # xmm0 = xmm0[12,13,0,1,10,11,2,3,8,9,14,15,10,11,8,9]
+; SSSE3-NEXT:    retq
+  %shuffle = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> <i32 6, i32 0, i32 5, i32 1, i32 4, i32 7, i32 5, i32 4>
+  ret <8 x i16> %shuffle
+}
+
 define <8 x i16> @shuffle_v8i16_00444444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE2-LABEL: @shuffle_v8i16_00444444
 ; SSE2:       # BB#0: