This improves the situation discussed in D19228 where we were forcing VPERMPD/VPERMQ where VPERM2F128/VPERM2I128 would have been better.
llvm-svn: 275411
case X86ISD::MOVSS:
case X86ISD::MOVSD:
case X86ISD::VPPERM:
+ case X86ISD::VPERMI:
case X86ISD::VPERMV:
case X86ISD::VPERMV3:
case X86ISD::VPERMIL2:
;
; AVX2-LABEL: shuffle_v8f32_01230123:
; AVX2: ## BB#0: ## %entry
-; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
;
; AVX2-LABEL: shuffle_v8f32_01230123_mem:
; AVX2: ## BB#0: ## %entry
-; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = mem[0,1,0,1]
+; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX2-NEXT: retq
entry:
%a = load <8 x float>, <8 x float>* %pa
;
; X64-LABEL: test_mm256_broadcastsi128_si256:
; X64: # BB#0:
-; X64-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; X64-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; X64-NEXT: retq
%res = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x i64> %res
; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <16 x i16> %shuffle
; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
ret <32 x i8> %shuffle
; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
ret <32 x i8> %shuffle
; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <32 x i8> %shuffle
; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <32 x i8> %shuffle
; AVX2-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <32 x i8> %shuffle
; AVX2-NEXT: movl $15, %eax
; AVX2-NEXT: vmovd %eax, %xmm1
; AVX2-NEXT: vpshufb %xmm1, %xmm0, %xmm0
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
ret <32 x i8> %shuffle
; AVX2-LABEL: shuffle_v8f32_32103210:
; AVX2: # BB#0:
; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
-; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-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
; AVX2-LABEL: shuffle_v8i32_32103210:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
-; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; 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