[X86][AVX] Fix wrong lowering of VPERM2X128 nodes

There were cases where the backend computed a wrong permute mask for a VPERM2X128 node.

Example:
\code
define <8 x float> @foo(<8 x float> %a, <8 x float> %b) {
  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
  ret <8 x float> %shuffle
}
\code end

Before this patch, llc (with -mattr=+avx) emitted the following vperm2f128:
  vperm2f128 $0, %ymm0, %ymm0, %ymm0  # ymm0 = ymm0[0,1,0,1]

With this patch, llc emits a vperm2f128 with a correct permute mask:
  vperm2f128 $17, %ymm0, %ymm0, %ymm0  # ymm0 = ymm0[2,3,2,3]

Differential Revision: http://reviews.llvm.org/D8119

llvm-svn: 231601

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -9039,7 +9039,15 @@ static SDValue lowerV2X128VectorShuffle(SDLoc DL, MVT VT, SDValue V1,
 
   // Otherwise form a 128-bit permutation.
   // FIXME: Detect zero-vector inputs and use the VPERM2X128 to zero that half.
-  unsigned PermMask = Mask[0] / 2 | (Mask[2] / 2) << 4;
+  int MaskLO = Mask[0];
+  if (MaskLO == SM_SentinelUndef)
+    MaskLO = Mask[1] == SM_SentinelUndef ? 0 : Mask[1];
+
+  int MaskHI = Mask[2];
+  if (MaskHI == SM_SentinelUndef)
+    MaskHI = Mask[3] == SM_SentinelUndef ? 0 : Mask[3];
+
+  unsigned PermMask = MaskLO / 2 | (MaskHI / 2) << 4;
   return DAG.getNode(X86ISD::VPERM2X128, DL, VT, V1, V2,
                      DAG.getConstant(PermMask, MVT::i8));
 }

llvm/test/CodeGen/X86/avx-vperm2x128.ll

@@ -172,13 +172,83 @@ entry:
 define <8 x float> @F(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
 ; ALL-LABEL: F:
 ; ALL:       ## BB#0: ## %entry
-; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm1[0,1,0,1]
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
 ; ALL-NEXT:    retq
 entry:
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 9, i32 undef, i32 11>
   ret <8 x float> %shuffle
 }
 
+define <8 x float> @F2(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F2:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F3(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F3:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 10, i32 11>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F4(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F4:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 14, i32 15>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F5(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F5:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F6(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F6:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F7(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F7:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @F8(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+; ALL-LABEL: F8:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
+; ALL-NEXT:    retq
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 14, i32 15>
+  ret <8 x float> %shuffle
+}
+
 ;;;; Cases we must not select vperm2f128
 
 define <8 x float> @G(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {

llvm/test/CodeGen/X86/vector-shuffle-512-v8.ll

@@ -686,7 +686,7 @@ define <8 x double> @shuffle_v8f64_c348cda0(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_c348cda0:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[0,1],ymm2[0,1]
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm2[0,1]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vbroadcastsd %xmm1, %ymm4
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm4 = ymm3[0,1,2],ymm4[3]
@@ -1402,15 +1402,14 @@ define <8 x i64> @shuffle_v8i64_6caa87e5(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_6caa87e5:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vperm2i128 {{.*#+}} ymm2 = ymm0[0,1,0,1]
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpblendd {{.*#+}} ymm4 = ymm1[0,1,2,3],ymm3[4,5],ymm1[6,7]
-; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm4[0,1],ymm2[2,3],ymm4[4,5],ymm2[6,7]
 ; ALL-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
-; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm3[0,1,2,3],ymm1[4,5,6,7]
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
+; ALL-NEXT:    vpblendd {{.*#+}} ymm3 = ymm1[0,1,2,3],ymm2[4,5],ymm1[6,7]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm0[2,3],ymm3[4,5],ymm0[6,7]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1,2,3],ymm1[4,5,6,7]
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
-; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
+; ALL-NEXT:    vinserti64x4 $1, %ymm3, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 6, i32 12, i32 10, i32 10, i32 8, i32 7, i32 14, i32 5>
   ret <8 x i64> %shuffle