[x86] Teach the target combine step to aggressively fold pshufd insturcions.

Summary:
This allows it to fold pshufd instructions across intervening
half-shuffles and other noise. This pattern actually shows up in the
generic lowering tests, but I've also added direct tests using
intrinsics to make sure that the specific desired functionality is
working even if the lowering stuff changes in the future.

Differential Revision: http://reviews.llvm.org/D4292

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211892 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 61 insertions, 2 deletions

diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index 091822b6cb..5d1922a348 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -157,9 +157,8 @@ define <8 x i16> @shuffle_v8i16_26401375(<8 x i16> %a, <8 x i16> %b) {
 ; CHECK-SSE2:       # BB#0:
 ; CHECK-SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[0,2,1,3,4,5,6,7]
 ; CHECK-SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,5,4,6]
-; CHECK-SSE2-NEXT:    pshufd {{.*}} # xmm0 = xmm0[0,3,2,1]
+; CHECK-SSE2-NEXT:    pshufd {{.*}} # xmm0 = xmm0[0,3,1,2]
 ; CHECK-SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[1,3,2,0,4,5,6,7]
-; CHECK-SSE2-NEXT:    pshufd {{.*}} # xmm0 = xmm0[0,1,3,2]
 ; CHECK-SSE2-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 6, i32 4, i32 0, i32 1, i32 3, i32 7, i32 5>
   ret <8 x i16> %shuffle
diff --git a/test/CodeGen/X86/vector-shuffle-combining.ll b/test/CodeGen/X86/vector-shuffle-combining.ll
index dae1ef5875..1bc2aee6ef 100644
--- a/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -3,9 +3,69 @@
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
 
+declare <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32>, i8)
 declare <8 x i16> @llvm.x86.sse2.pshufl.w(<8 x i16>, i8)
 declare <8 x i16> @llvm.x86.sse2.pshufh.w(<8 x i16>, i8)
 
+define <4 x i32> @combine_pshufd1(<4 x i32> %a) {
+; CHECK-SSE2-LABEL: @combine_pshufd1
+; CHECK-SSE2:       # BB#0:
+; CHECK-SSE2-NEXT:    retq
+  %b = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %a, i8 27) 
+  %c = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %b, i8 27) 
+  ret <4 x i32> %c
+}
+
+define <4 x i32> @combine_pshufd2(<4 x i32> %a) {
+; CHECK-SSE2-LABEL: @combine_pshufd2
+; CHECK-SSE2:       # BB#0:
+; CHECK-SSE2-NEXT:    retq
+  %b = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %a, i8 27) 
+  %b.cast = bitcast <4 x i32> %b to <8 x i16>
+  %c = call <8 x i16> @llvm.x86.sse2.pshufl.w(<8 x i16> %b.cast, i8 -28)
+  %c.cast = bitcast <8 x i16> %c to <4 x i32>
+  %d = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %c.cast, i8 27) 
+  ret <4 x i32> %d
+}
+
+define <4 x i32> @combine_pshufd3(<4 x i32> %a) {
+; CHECK-SSE2-LABEL: @combine_pshufd3
+; CHECK-SSE2:       # BB#0:
+; CHECK-SSE2-NEXT:    retq
+  %b = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %a, i8 27) 
+  %b.cast = bitcast <4 x i32> %b to <8 x i16>
+  %c = call <8 x i16> @llvm.x86.sse2.pshufh.w(<8 x i16> %b.cast, i8 -28)
+  %c.cast = bitcast <8 x i16> %c to <4 x i32>
+  %d = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %c.cast, i8 27) 
+  ret <4 x i32> %d
+}
+
+define <4 x i32> @combine_pshufd4(<4 x i32> %a) {
+; CHECK-SSE2-LABEL: @combine_pshufd4
+; CHECK-SSE2:       # BB#0:
+; CHECK-SSE2-NEXT:    pshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,6,5,4]
+; CHECK-SSE2-NEXT:    retq
+  %b = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %a, i8 -31) 
+  %b.cast = bitcast <4 x i32> %b to <8 x i16>
+  %c = call <8 x i16> @llvm.x86.sse2.pshufh.w(<8 x i16> %b.cast, i8 27)
+  %c.cast = bitcast <8 x i16> %c to <4 x i32>
+  %d = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %c.cast, i8 -31) 
+  ret <4 x i32> %d
+}
+
+define <4 x i32> @combine_pshufd5(<4 x i32> %a) {
+; CHECK-SSE2-LABEL: @combine_pshufd5
+; CHECK-SSE2:       # BB#0:
+; CHECK-SSE2-NEXT:    pshuflw {{.*}} # xmm0 = xmm0[3,2,1,0,4,5,6,7]
+; CHECK-SSE2-NEXT:    retq
+  %b = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %a, i8 -76) 
+  %b.cast = bitcast <4 x i32> %b to <8 x i16>
+  %c = call <8 x i16> @llvm.x86.sse2.pshufl.w(<8 x i16> %b.cast, i8 27)
+  %c.cast = bitcast <8 x i16> %c to <4 x i32>
+  %d = call <4 x i32> @llvm.x86.sse2.pshuf.d(<4 x i32> %c.cast, i8 -76)
+  ret <4 x i32> %d
+}
+
 define <8 x i16> @combine_pshuflw1(<8 x i16> %a) {
 ; CHECK-SSE2-LABEL: @combine_pshuflw1
 ; CHECK-SSE2:       # BB#0: