diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll | 81 |
1 files changed, 81 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll index 6d315df2595..5192eaeec4d 100644 --- a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll +++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll @@ -544,6 +544,34 @@ define <4 x double> @shuffle_v4f64_1z3z(<4 x double> %a, <4 x double> %b) { ret <4 x double> %shuffle } +define <4 x double> @shuffle_v4f64_1z2z(<4 x double> %a, <4 x double> %b) { +; AVX1-LABEL: shuffle_v4f64_1z2z: +; AVX1: # BB#0: +; AVX1-NEXT: vxorpd %ymm1, %ymm1, %ymm1 +; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3] +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX1-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0] +; AVX1-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0] +; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX1-NEXT: retq +; +; AVX2-LABEL: shuffle_v4f64_1z2z: +; AVX2: # BB#0: +; AVX2-NEXT: vxorpd %ymm1, %ymm1, %ymm1 +; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3] +; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,0,2,0] +; AVX2-NEXT: retq +; +; AVX512VL-LABEL: shuffle_v4f64_1z2z: +; AVX512VL: # BB#0: +; AVX512VL-NEXT: vpxor %ymm1, %ymm1, %ymm1 +; AVX512VL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3] +; AVX512VL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,0,2,0] +; AVX512VL-NEXT: retq + %1 = shufflevector <4 x double> %a, <4 x double> <double 0.000000e+00, double undef, double undef, double undef>, <4 x i32> <i32 1, i32 4, i32 2, i32 4> + ret <4 x double> %1 +} + define <4 x i64> @shuffle_v4i64_0000(<4 x i64> %a, <4 x i64> %b) { ; AVX1-LABEL: shuffle_v4i64_0000: ; AVX1: # BB#0: @@ -1536,3 +1564,56 @@ define <4 x i64> @shuffle_v4i64_1230(<4 x i64> %a) { %shuffle = shufflevector <4 x i64> %a, <4 x i64> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 0> ret <4 x i64> %shuffle } + +define <4 x i64> @shuffle_v4i64_z0z3(<4 x i64> %a, <4 x i64> %b) { +; AVX1-LABEL: shuffle_v4i64_z0z3: +; AVX1: # BB#0: +; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,3] +; AVX1-NEXT: vxorpd %ymm1, %ymm1, %ymm1 +; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3] +; AVX1-NEXT: retq +; +; AVX2-LABEL: shuffle_v4i64_z0z3: +; AVX2: # BB#0: +; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,2,3] +; AVX2-NEXT: vpxor %ymm1, %ymm1, %ymm1 +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7] +; AVX2-NEXT: retq +; +; AVX512VL-LABEL: shuffle_v4i64_z0z3: +; AVX512VL: # BB#0: +; AVX512VL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,2,3] +; AVX512VL-NEXT: vpxor %ymm1, %ymm1, %ymm1 +; AVX512VL-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7] +; AVX512VL-NEXT: retq + %1 = shufflevector <4 x i64> %a, <4 x i64> <i64 0, i64 undef, i64 undef, i64 undef>, <4 x i32> <i32 4, i32 0, i32 4, i32 3> + ret <4 x i64> %1 +} + +define <4 x i64> @shuffle_v4i64_1z2z(<4 x i64> %a, <4 x i64> %b) { +; AVX1-LABEL: shuffle_v4i64_1z2z: +; AVX1: # BB#0: +; AVX1-NEXT: vxorpd %ymm1, %ymm1, %ymm1 +; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3] +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX1-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0] +; AVX1-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0] +; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX1-NEXT: retq +; +; AVX2-LABEL: shuffle_v4i64_1z2z: +; AVX2: # BB#0: +; AVX2-NEXT: vpxor %ymm1, %ymm1, %ymm1 +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7] +; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[1,0,2,0] +; AVX2-NEXT: retq +; +; AVX512VL-LABEL: shuffle_v4i64_1z2z: +; AVX512VL: # BB#0: +; AVX512VL-NEXT: vpxor %ymm1, %ymm1, %ymm1 +; AVX512VL-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7] +; AVX512VL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[1,0,2,0] +; AVX512VL-NEXT: retq + %1 = shufflevector <4 x i64> %a, <4 x i64> <i64 0, i64 undef, i64 undef, i64 undef>, <4 x i32> <i32 1, i32 4, i32 2, i32 4> + ret <4 x i64> %1 +} |
