diff options
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-partial-undef.ll | 33 |
1 files changed, 32 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/X86/vector-partial-undef.ll b/llvm/test/CodeGen/X86/vector-partial-undef.ll index 2b4ab11fea5..3c4acf72219 100644 --- a/llvm/test/CodeGen/X86/vector-partial-undef.ll +++ b/llvm/test/CodeGen/X86/vector-partial-undef.ll @@ -109,6 +109,37 @@ define <4 x i64> @or_undef_elts(<2 x i64> %x) { define <8 x i32> @xor_undef_elts(<4 x i32> %x) { ; SSE-LABEL: xor_undef_elts: ; SSE: # %bb.0: +; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3] +; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm0[0,2,2,3] +; SSE-NEXT: pxor {{.*}}(%rip), %xmm2 +; SSE-NEXT: pxor {{.*}}(%rip), %xmm1 +; SSE-NEXT: movdqa %xmm1, %xmm0 +; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],xmm2[2,0] +; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[1,0] +; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[3,0],xmm1[0,0] +; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,2],xmm2[2,0] +; SSE-NEXT: retq +; +; AVX-LABEL: xor_undef_elts: +; AVX: # %bb.0: +; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,3,0,2] +; AVX-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,3] +; AVX-NEXT: vxorps {{.*}}(%rip), %ymm0, %ymm0 +; AVX-NEXT: vmovaps {{.*#+}} ymm1 = [6,1,5,4,3,2,0,7] +; AVX-NEXT: vpermps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq + %extend = shufflevector <4 x i32> %x, <4 x i32> undef, <8 x i32> <i32 undef, i32 undef, i32 1, i32 3, i32 0, i32 2, i32 undef, i32 undef> + %bogus_bo = xor <8 x i32> %extend, <i32 42, i32 43, i32 undef, i32 undef, i32 undef, i32 undef, i32 44, i32 12> + %arbitrary_shuf = shufflevector <8 x i32> %bogus_bo, <8 x i32> undef, <8 x i32> <i32 6, i32 1, i32 5, i32 4, i32 3, i32 2, i32 0, i32 7> + ret <8 x i32> %arbitrary_shuf +} + +; Verify that this isn't limited to high/low halves +; Special case: the undef-ness of the 1st shuffle may be lost if we turn that into vector concat. + +define <8 x i32> @xor_undef_elts_alt(<4 x i32> %x) { +; SSE-LABEL: xor_undef_elts_alt: +; SSE: # %bb.0: ; SSE-NEXT: movaps %xmm0, %xmm1 ; SSE-NEXT: movaps {{.*#+}} xmm2 = <u,u,44,12> ; SSE-NEXT: xorps %xmm0, %xmm2 @@ -120,7 +151,7 @@ define <8 x i32> @xor_undef_elts(<4 x i32> %x) { ; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,2],xmm2[2,0] ; SSE-NEXT: retq ; -; AVX-LABEL: xor_undef_elts: +; AVX-LABEL: xor_undef_elts_alt: ; AVX: # %bb.0: ; AVX-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0 ; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 |
