[X86] Bailout of lowerVectorShuffleAsPermuteAndUnpack for shuffle-with-zero (PR40306)
If we're shuffling with a zero vector, then we are better off not doing VECTOR_SHUFFLE(UNPCK()) as we lose track of those zero elements.
We were already doing this for SSSE3 targets as we have PSHUFB, but its worth doing for all targets.
llvm-svn: 351203
diff --git a/llvm/test/CodeGen/X86/buildvec-extract.ll b/llvm/test/CodeGen/X86/buildvec-extract.ll
index 267eec4..b304580 100644
--- a/llvm/test/CodeGen/X86/buildvec-extract.ll
+++ b/llvm/test/CodeGen/X86/buildvec-extract.ll
@@ -404,11 +404,10 @@
define <2 x i64> @extract1_i16_zext_insert0_i64_undef(<8 x i16> %x) {
; SSE2-LABEL: extract1_i16_zext_insert0_i64_undef:
; SSE2: # %bb.0:
+; SSE2-NEXT: psrld $16, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm1
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm1[0,1,2,3,4,6,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,1,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,2,0,1,4,5,6,7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: retq
;
; SSE41-LABEL: extract1_i16_zext_insert0_i64_undef:
@@ -449,12 +448,10 @@
define <2 x i64> @extract2_i16_zext_insert0_i64_undef(<8 x i16> %x) {
; SSE2-LABEL: extract2_i16_zext_insert0_i64_undef:
; SSE2: # %bb.0:
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE2-NEXT: pxor %xmm1, %xmm1
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[3,1,2,0]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,0,4,5,6,7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: retq
;
; SSE41-LABEL: extract2_i16_zext_insert0_i64_undef: