llvm-project/llvm/test/CodeGen/X86/avx-vperm2x128.ll

654 lines
28 KiB
LLVM
Raw Normal View History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX2
define <8 x float> @shuffle_v8f32_45670123(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_45670123:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_45670123_mem(<8 x float>* %pa, <8 x float>* %pb) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_45670123_mem:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3,0,1]
; ALL-NEXT: retq
entry:
%a = load <8 x float>, <8 x float>* %pa
%b = load <8 x float>, <8 x float>* %pb
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_0123cdef(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_0123cdef:
; ALL: ## BB#0: ## %entry
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; ALL-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 12, i32 13, i32 14, i32 15>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_01230123(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v8f32_01230123:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_01230123:
; AVX2: ## BB#0: ## %entry
; 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>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_01230123_mem(<8 x float>* %pa, <8 x float>* %pb) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v8f32_01230123_mem:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vmovaps (%rdi), %ymm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_01230123_mem:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX2-NEXT: retq
entry:
%a = load <8 x float>, <8 x float>* %pa
%b = load <8 x float>, <8 x float>* %pb
%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>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_45674567(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_45674567:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_45674567_mem(<8 x float>* %pa, <8 x float>* %pb) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_45674567_mem:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3,2,3]
; ALL-NEXT: retq
entry:
%a = load <8 x float>, <8 x float>* %pa
%b = load <8 x float>, <8 x float>* %pb
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
ret <8 x float> %shuffle
}
define <32 x i8> @shuffle_v32i8_2323(<32 x i8> %a, <32 x i8> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v32i8_2323:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
ret <32 x i8> %shuffle
}
define <32 x i8> @shuffle_v32i8_2323_domain(<32 x i8> %a, <32 x i8> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v32i8_2323_domain:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_2323_domain:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vpaddb {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX2-NEXT: retq
entry:
; add forces execution domain
%a2 = add <32 x i8> %a, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%shuffle = shufflevector <32 x i8> %a2, <32 x i8> %b, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
ret <32 x i8> %shuffle
}
define <4 x i64> @shuffle_v4i64_6701(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v4i64_6701:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[0,1]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
ret <4 x i64> %shuffle
}
define <4 x i64> @shuffle_v4i64_6701_domain(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v4i64_6701_domain:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[0,1]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4i64_6701_domain:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vpbroadcastq {{.*}}(%rip), %ymm2
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[0,1]
; AVX2-NEXT: retq
entry:
; add forces execution domain
%a2 = add <4 x i64> %a, <i64 1, i64 1, i64 1, i64 1>
%shuffle = shufflevector <4 x i64> %a2, <4 x i64> %b, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
ret <4 x i64> %shuffle
}
define <8 x i32> @shuffle_v8i32_u5u7cdef(<8 x i32> %a, <8 x i32> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v8i32_u5u7cdef:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_u5u7cdef:
; AVX2: ## BB#0: ## %entry
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm2
; AVX2-NEXT: vpaddd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: retq
entry:
; add forces execution domain
%a2 = add <8 x i32> %a, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%shuffle = shufflevector <8 x i32> %a2, <8 x i32> %b, <8 x i32> <i32 undef, i32 5, i32 undef, i32 7, i32 12, i32 13, i32 14, i32 15>
ret <8 x i32> %shuffle
}
define <16 x i16> @shuffle_v16i16_4501(<16 x i16> %a, <16 x i16> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v16i16_4501:
; AVX1: ## BB#0: ## %entry
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; AVX1-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v16i16_4501:
; AVX2: ## BB#0: ## %entry
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; AVX2-NEXT: vpaddw {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
entry:
; add forces execution domain
%a2 = add <16 x i16> %a, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%shuffle = shufflevector <16 x i16> %a2, <16 x i16> %b, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <16 x i16> %shuffle
}
define <16 x i16> @shuffle_v16i16_4501_mem(<16 x i16>* %a, <16 x i16>* %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: shuffle_v16i16_4501_mem:
; AVX1: ## BB#0: ## %entry
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vmovaps (%rsi), %ymm1
; AVX1-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v16i16_4501_mem:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
[x86] Enable the new vector shuffle lowering by default. Update the entire regression test suite for the new shuffles. Remove most of the old testing which was devoted to the old shuffle lowering path and is no longer relevant really. Also remove a few other random tests that only really exercised shuffles and only incidently or without any interesting aspects to them. Benchmarking that I have done shows a few small regressions with this on LNT, zero measurable regressions on real, large applications, and for several benchmarks where the loop vectorizer fires in the hot path it shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy Bridge machines. Running on AMD machines shows even more dramatic improvements. When using newer ISA vector extensions the gains are much more modest, but the code is still better on the whole. There are a few regressions being tracked (PR21137, PR21138, PR21139) but by and large this is expected to be a win for x86 generated code performance. It is also more correct than the code it replaces. I have fuzz tested this extensively with ISA extensions up through AVX2 and found no crashes or miscompiles (yet...). The old lowering had a few miscompiles and crashers after a somewhat smaller amount of fuzz testing. There is one significant area where the new code path lags behind and that is in AVX-512 support. However, there was *extremely little* support for that already and so this isn't a significant step backwards and the new framework will probably make it easier to implement lowering that uses the full power of AVX-512's table-based shuffle+blend (IMO). Many thanks to Quentin, Andrea, Robert, and others for benchmarking assistance. Thanks to Adam and others for help with AVX-512. Thanks to Hal, Eric, and *many* others for answering my incessant questions about how the backend actually works. =] I will leave the old code path in the tree until the 3 PRs above are at least resolved to folks' satisfaction. Then I will rip it (and 1000s of lines of code) out. =] I don't expect this flag to stay around for very long. It may not survive next week. llvm-svn: 219046
2014-10-04 11:52:55 +08:00
; AVX2-NEXT: vmovdqa (%rsi), %ymm1
; AVX2-NEXT: vpaddw {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
entry:
%c = load <16 x i16>, <16 x i16>* %a
%d = load <16 x i16>, <16 x i16>* %b
%c2 = add <16 x i16> %c, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%shuffle = shufflevector <16 x i16> %c2, <16 x i16> %d, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <16 x i16> %shuffle
}
;;;; Cases with undef indicies mixed in the mask
define <8 x float> @shuffle_v8f32_uu67u9ub(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu67u9ub:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 9, i32 undef, i32 11>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uu67uu67(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu67uu67:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uu67uuab(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu67uuab:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 10, i32 11>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uu67uuef(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu67uuef:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 14, i32 15>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uu674567(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu674567:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uu6789ab(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu6789ab:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[0,1]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_4567uu67(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_4567uu67:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_4567uuef(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_4567uuef:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 14, i32 15>
ret <8 x float> %shuffle
}
;;;; Cases we must not select vperm2f128
define <8 x float> @shuffle_v8f32_uu67ucuf(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: shuffle_v8f32_uu67ucuf:
; ALL: ## BB#0: ## %entry
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,3,4,4,6,7]
; ALL-NEXT: retq
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 12, i32 undef, i32 15>
ret <8 x float> %shuffle
}
;; Test zero mask generation.
;; PR22984: https://llvm.org/bugs/show_bug.cgi?id=22984
;; Prefer xor+vblendpd over vperm2f128 because that has better performance.
;; TODO: When building for optsize we should use vperm2f128.
define <4 x double> @shuffle_v4f64_zz01(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_zz01:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = zero,zero,ymm0[0,1]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz01_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_zz01_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = zero,zero,ymm0[0,1]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz23(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_zz23:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz23_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_zz23_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz45(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_zz45:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = zero,zero,ymm0[0,1]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz45_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_zz45_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = zero,zero,ymm0[0,1]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz67(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_zz67:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_zz67_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_zz67_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_01zz(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_01zz:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_01zz_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_01zz_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_23zz(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_23zz:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_23zz_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_23zz_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; ALL-NEXT: retq
%s = shufflevector <4 x double> %a, <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_45zz(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_45zz:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_45zz_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_45zz_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_67zz(<4 x double> %a) {
; ALL-LABEL: shuffle_v4f64_67zz:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
ret <4 x double> %s
}
define <4 x double> @shuffle_v4f64_67zz_optsize(<4 x double> %a) optsize {
; ALL-LABEL: shuffle_v4f64_67zz_optsize:
; ALL: ## BB#0:
; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; ALL-NEXT: retq
%s = shufflevector <4 x double> <double 0.0, double 0.0, double undef, double undef>, <4 x double> %a, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
ret <4 x double> %s
}
;; With AVX2 select the integer version of the instruction. Use an add to force the domain selection.
define <4 x i64> @shuffle_v4i64_67zz(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_67zz:
; AVX1: ## BB#0:
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; AVX1-NEXT: vpaddq %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v4i64_67zz:
; AVX2: ## BB#0:
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],zero,zero
; AVX2-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%s = shufflevector <4 x i64> <i64 0, i64 0, i64 undef, i64 undef>, <4 x i64> %a, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
%c = add <4 x i64> %b, %s
ret <4 x i64> %c
}
;;; Memory folding cases
define <4 x double> @ld0_hi0_lo1_4f64(<4 x double> * %pa, <4 x double> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld0_hi0_lo1_4f64:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX1-NEXT: vaddpd {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld0_hi0_lo1_4f64:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX2-NEXT: vbroadcastsd {{.*}}(%rip), %ymm1
; AVX2-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%a = load <4 x double>, <4 x double> * %pa
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
%res = fadd <4 x double> %shuffle, <double 1.0, double 1.0, double 1.0, double 1.0>
ret <4 x double> %res
}
define <4 x double> @ld1_hi0_hi1_4f64(<4 x double> %a, <4 x double> * %pb) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld1_hi0_hi1_4f64:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX1-NEXT: vaddpd {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld1_hi0_hi1_4f64:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX2-NEXT: vbroadcastsd {{.*}}(%rip), %ymm1
; AVX2-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%b = load <4 x double>, <4 x double> * %pb
%shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 2, i32 3, i32 6, i32 7>
%res = fadd <4 x double> %shuffle, <double 1.0, double 1.0, double 1.0, double 1.0>
ret <4 x double> %res
}
define <8 x float> @ld0_hi0_lo1_8f32(<8 x float> * %pa, <8 x float> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld0_hi0_lo1_8f32:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX1-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld0_hi0_lo1_8f32:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
; AVX2-NEXT: vaddps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%a = load <8 x float>, <8 x float> * %pa
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
%res = fadd <8 x float> %shuffle, <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
ret <8 x float> %res
}
define <8 x float> @ld1_hi0_hi1_8f32(<8 x float> %a, <8 x float> * %pb) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld1_hi0_hi1_8f32:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX1-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld1_hi0_hi1_8f32:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
; AVX2-NEXT: vaddps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%b = load <8 x float>, <8 x float> * %pb
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 12, i32 13, i32 14, i32 15>
%res = fadd <8 x float> %shuffle, <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
ret <8 x float> %res
}
define <4 x i64> @ld0_hi0_lo1_4i64(<4 x i64> * %pa, <4 x i64> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld0_hi0_lo1_4i64:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld0_hi0_lo1_4i64:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX2-NEXT: vpaddq {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%a = load <4 x i64>, <4 x i64> * %pa
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
%res = add <4 x i64> %shuffle, <i64 1, i64 2, i64 3, i64 4>
ret <4 x i64> %res
}
define <4 x i64> @ld1_hi0_hi1_4i64(<4 x i64> %a, <4 x i64> * %pb) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld1_hi0_hi1_4i64:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld1_hi0_hi1_4i64:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX2-NEXT: vpaddq {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%b = load <4 x i64>, <4 x i64> * %pb
%shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 2, i32 3, i32 6, i32 7>
%res = add <4 x i64> %shuffle, <i64 1, i64 2, i64 3, i64 4>
ret <4 x i64> %res
}
define <8 x i32> @ld0_hi0_lo1_8i32(<8 x i32> * %pa, <8 x i32> %b) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld0_hi0_lo1_8i32:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [1,2,3,4]
; AVX1-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld0_hi0_lo1_8i32:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = mem[2,3],ymm0[0,1]
; AVX2-NEXT: vpaddd {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%a = load <8 x i32>, <8 x i32> * %pa
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
%res = add <8 x i32> %shuffle, <i32 1, i32 2, i32 3, i32 4, i32 1, i32 2, i32 3, i32 4>
ret <8 x i32> %res
}
define <8 x i32> @ld1_hi0_hi1_8i32(<8 x i32> %a, <8 x i32> * %pb) nounwind uwtable readnone ssp {
; AVX1-LABEL: ld1_hi0_hi1_8i32:
; AVX1: ## BB#0: ## %entry
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [1,2,3,4]
; AVX1-NEXT: vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: ld1_hi0_hi1_8i32:
; AVX2: ## BB#0: ## %entry
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],mem[2,3]
; AVX2-NEXT: vpaddd {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
entry:
%b = load <8 x i32>, <8 x i32> * %pb
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 12, i32 13, i32 14, i32 15>
%res = add <8 x i32> %shuffle, <i32 1, i32 2, i32 3, i32 4, i32 1, i32 2, i32 3, i32 4>
ret <8 x i32> %res
}