From 0651861b7b84f84865a652c4963db1a2c9671d9d Mon Sep 17 00:00:00 2001
From: Chandler Carruth <chandlerc@gmail.com>
Date: Thu, 7 Aug 2014 10:14:27 +0000
Subject: [PATCH] [x86] Fix another miscompile in the new vector shuffle
 lowering found via the fuzz tester.

Here I missed an offset when round-tripping a value through a shuffle
mask. I got it right 2 lines below. See a problem? I do. ;] I'll
probably be adding a little "swap" algorithm which accepts a range and
two values and swaps those values where they occur in the range. Don't
really have a name for it, let me know if you do.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215094 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/X86/X86ISelLowering.cpp        |  2 +-
 test/CodeGen/X86/vector-shuffle-128-v8.ll | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 2ef1a6925b6..d85ac5e55e4 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -7449,7 +7449,7 @@ static SDValue lowerV8I16SingleInputVectorShuffle(
                 Input - SourceOffset;
             // We have to swap the uses in our half mask in one sweep.
             for (int &M : HalfMask)
-              if (M == SourceHalfMask[Input - SourceOffset])
+              if (M == SourceHalfMask[Input - SourceOffset] + SourceOffset)
                 M = Input;
               else if (M == Input)
                 M = SourceHalfMask[Input - SourceOffset] + SourceOffset;
diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index 6ca4857e42e..5c6a4dbaa4b 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -220,6 +220,24 @@ define <8 x i16> @shuffle_v8i16_26401375(<8 x i16> %a, <8 x i16> %b) {
   ret <8 x i16> %shuffle
 }
 
+define <8 x i16> @shuffle_v8i16_66751643(<8 x i16> %a, <8 x i16> %b) {
+; SSE2-LABEL: @shuffle_v8i16_66751643
+; SSE2:       # BB#0:
+; SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[3,1,2,3,4,5,6,7]
+; SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,6,5,7]
+; SSE2-NEXT:    pshufd {{.*}} # xmm0 = xmm0[2,3,2,0]
+; SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[1,1,3,2,4,5,6,7]
+; SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,5,4,6]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: @shuffle_v8i16_66751643
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    pshufb {{.*}} # xmm0 = xmm0[12,13,12,13,14,15,10,11,2,3,12,13,8,9,6,7]
+; SSSE3-NEXT:    retq
+  %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 6, i32 6, i32 7, i32 5, i32 1, i32 6, i32 4, i32 3>
+  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:
-- 
2.34.1