fix PR8900, a shuffle miscompilation. Patch by Nadav Rotem!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122921 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index ad8086040ada9764567cc7c5428c978a03783de5..9c20e8427115ab84643c452c960728cc8ec9cfca 100644 (file)
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -5597,9 +5597,9 @@ def : Pat<(v4f32 (X86Unpckhps VR128:$src1, VR128:$src2)),
 
 // Shuffle with UNPCKLPD
 def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, (memopv2f64 addr:$src2))),
-          (VUNPCKLPSrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
+          (VUNPCKLPDrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
 def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, (memopv2f64 addr:$src2))),
-          (UNPCKLPSrm VR128:$src1, addr:$src2)>;
+          (UNPCKLPDrm VR128:$src1, addr:$src2)>;
 
 def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, VR128:$src2)),
           (VUNPCKLPDrr VR128:$src1, VR128:$src2)>, Requires<[HasAVX]>;
@@ -5608,9 +5608,9 @@ def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, VR128:$src2)),
 
 // Shuffle with UNPCKHPD
 def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, (memopv2f64 addr:$src2))),
-          (VUNPCKLPSrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
+          (VUNPCKHPDrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
 def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, (memopv2f64 addr:$src2))),
-          (UNPCKLPSrm VR128:$src1, addr:$src2)>;
+          (UNPCKHPDrm VR128:$src1, addr:$src2)>;
 
 def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, VR128:$src2)),
           (VUNPCKHPDrr VR128:$src1, VR128:$src2)>, Requires<[HasAVX]>;

diff --git a/test/CodeGen/X86/sse2.ll b/test/CodeGen/X86/sse2.ll
index 6fc019071f8bf4ac669af4419c6055b78434eead..a9d718d2df018f3de96df64d63984cd7ee757b45 100644 (file)
--- a/test/CodeGen/X86/sse2.ll
+++ b/test/CodeGen/X86/sse2.ll
@@ -192,3 +192,16 @@ entry:
 ; CHECK: test15:
 ; CHECK:       movhlps %xmm1, %xmm0
 }
+
+; PR8900
+; CHECK: test16:
+; CHECK: unpcklpd
+; CHECK: ret
+
+define  <2 x double> @test16(<4 x double> * nocapture %srcA, <2 x double>* nocapture %dst) {
+  %i5 = getelementptr inbounds <4 x double>* %srcA, i32 3
+  %i6 = load <4 x double>* %i5, align 32
+  %i7 = shufflevector <4 x double> %i6, <4 x double> undef, <2 x i32> <i32 0, i32 2>
+  ret <2 x double> %i7
+}
+