diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll | 129 |
1 files changed, 50 insertions, 79 deletions
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll index 1908a5ae207..dfd03d32453 100644 --- a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll +++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll @@ -195,18 +195,15 @@ define <8 x float> @shuffle_v8f32_81a3c5e7(<8 x float> %a, <8 x float> %b) { define <8 x float> @shuffle_v8f32_08080808(<8 x float> %a, <8 x float> %b) { ; AVX1-LABEL: shuffle_v8f32_08080808: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0] -; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1 -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0] +; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 -; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8f32_08080808: ; AVX2: # BB#0: -; AVX2-NEXT: vbroadcastss %xmm1, %ymm1 +; AVX2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero ; AVX2-NEXT: vbroadcastsd %xmm0, %ymm0 -; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8> ret <8 x float> %shuffle @@ -647,10 +644,10 @@ define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) { ; ; AVX2-LABEL: shuffle_v8f32_c348cda0: ; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,3,4,u,u,u,u,0> -; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0 -; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <4,u,u,0,4,5,2,u> -; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1 +; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,3,0,0,4,7,4,4] +; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,1] +; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,1,2,0,4,5,6,4] +; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[2,1,2,1] ; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 12, i32 3, i32 4, i32 8, i32 12, i32 13, i32 10, i32 0> @@ -660,21 +657,21 @@ define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) { define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) { ; AVX1-LABEL: shuffle_v8f32_f511235a: ; AVX1: # BB#0: +; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1] ; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1] ; AVX1-NEXT: vpermilpd {{.*#+}} ymm2 = ymm2[0,0,3,2] ; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,1,1,1,4,5,5,5] ; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm2[0],ymm0[1],ymm2[2],ymm0[3] -; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1] -; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6] ; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8f32_f511235a: ; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <7,u,u,u,u,u,u,2> -; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1 ; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,5,1,1,2,3,5,u> ; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0 +; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6] +; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1] ; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 5, i32 1, i32 1, i32 2, i32 3, i32 5, i32 10> @@ -682,50 +679,31 @@ define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) { } define <8 x float> @shuffle_v8f32_32103210(<8 x float> %a, <8 x float> %b) { -; AVX1-LABEL: shuffle_v8f32_32103210: -; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 -; AVX1-NEXT: retq -; -; AVX2-LABEL: shuffle_v8f32_32103210: -; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0] -; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0 -; AVX2-NEXT: retq +; ALL-LABEL: shuffle_v8f32_32103210: +; ALL: # BB#0: +; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0] +; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 +; ALL-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0> ret <8 x float> %shuffle } define <8 x float> @shuffle_v8f32_76547654(<8 x float> %a, <8 x float> %b) { -; AVX1-LABEL: shuffle_v8f32_76547654: -; AVX1: # BB#0: -; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 -; AVX1-NEXT: retq -; -; AVX2-LABEL: shuffle_v8f32_76547654: -; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4] -; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0 -; AVX2-NEXT: retq +; ALL-LABEL: shuffle_v8f32_76547654: +; ALL: # BB#0: +; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3] +; ALL-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4> ret <8 x float> %shuffle } define <8 x float> @shuffle_v8f32_76543210(<8 x float> %a, <8 x float> %b) { -; AVX1-LABEL: shuffle_v8f32_76543210: -; AVX1: # BB#0: -; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1] -; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] -; AVX1-NEXT: retq -; -; AVX2-LABEL: shuffle_v8f32_76543210: -; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0] -; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0 -; AVX2-NEXT: retq +; ALL-LABEL: shuffle_v8f32_76543210: +; ALL: # BB#0: +; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1] +; ALL-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0> ret <8 x float> %shuffle } @@ -783,10 +761,10 @@ define <8 x float> @PR21138(<8 x float> %truc, <8 x float> %tchose) { ; ; AVX2-LABEL: PR21138: ; AVX2: # BB#0: -; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,u,u,1,3,5,7> -; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1 -; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <1,3,5,7,u,u,u,u> -; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0 +; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[1,3,1,3,5,7,5,7] +; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,3] +; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[1,3,1,3,5,7,5,7] +; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,3] ; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x float> %truc, <8 x float> %tchose, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> @@ -844,9 +822,8 @@ define <8 x float> @shuffle_v8f32_uuuu1111(<8 x float> %a, <8 x float> %b) { define <8 x float> @shuffle_v8f32_44444444(<8 x float> %a, <8 x float> %b) { ; AVX1-LABEL: shuffle_v8f32_44444444: ; AVX1: # BB#0: -; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8f32_44444444: @@ -1107,18 +1084,15 @@ define <8 x i32> @shuffle_v8i32_81a3c5e7(<8 x i32> %a, <8 x i32> %b) { define <8 x i32> @shuffle_v8i32_08080808(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_08080808: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0] -; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1 -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0] +; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 -; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_08080808: ; AVX2: # BB#0: -; AVX2-NEXT: vpbroadcastd %xmm1, %ymm1 +; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; AVX2-NEXT: vpbroadcastq %xmm0, %ymm0 -; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8> ret <8 x i32> %shuffle @@ -1762,19 +1736,18 @@ define <8 x i32> @shuffle_v8i32_uuu3uu66(<8 x i32> %a, <8 x i32> %b) { define <8 x i32> @shuffle_v8i32_6caa87e5(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_6caa87e5: ; AVX1: # BB#0: +; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3] ; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,0,1] ; AVX1-NEXT: vshufps {{.*#+}} ymm1 = ymm2[0,0],ymm1[2,2],ymm2[4,4],ymm1[6,6] -; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 -; AVX1-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_6caa87e5: ; AVX2: # BB#0: -; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <u,4,2,2,0,u,6,u> -; AVX2-NEXT: vpermd %ymm1, %ymm2, %ymm1 ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,1,3,2] +; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,0,2,2,4,4,6,6] +; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,0,3] ; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 6, i32 12, i32 10, i32 10, i32 8, i32 7, i32 14, i32 5> @@ -1790,8 +1763,8 @@ define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) { ; ; AVX2-LABEL: shuffle_v8i32_32103210: ; AVX2: # BB#0: -; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0] -; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0 +; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,2,1,0] +; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0 ; AVX2-NEXT: retq %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0> ret <8 x i32> %shuffle @@ -1800,15 +1773,14 @@ define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) { define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_76547654: ; AVX1: # BB#0: -; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_76547654: ; AVX2: # BB#0: -; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4] -; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0 +; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,2,3] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4> ret <8 x i32> %shuffle @@ -1817,14 +1789,14 @@ define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) { define <8 x i32> @shuffle_v8i32_76543210(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_76543210: ; AVX1: # BB#0: -; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1] ; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_76543210: ; AVX2: # BB#0: -; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0] -; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0 +; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4] +; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1] ; AVX2-NEXT: retq %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0> ret <8 x i32> %shuffle @@ -2008,9 +1980,8 @@ define <8 x i32> @shuffle_v8i32_2A3Buuuu(<8 x i32> %a, <8 x i32> %b) { define <8 x i32> @shuffle_v8i32_44444444(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_44444444: ; AVX1: # BB#0: -; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0] -; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4] +; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_44444444: |
