maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll

676 lines
33 KiB
LLVM
Raw Normal View History

[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BWVL
; PR31551
; Pairs of shufflevector:trunc functions with functional equivalence.
; Ideally, the shuffles should be lowered to code with the same quality as the truncates.
define void @shuffle_v64i8_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
; AVX512F-LABEL: shuffle_v64i8_to_v32i8:
; AVX512F: # BB#0:
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512F-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512F-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512F-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v32i8:
; AVX512VL: # BB#0:
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512VL-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512VL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512VL-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v32i8:
; AVX512BW: # BB#0:
[AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead. These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use. But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases. I also generally dislike patterns rooted in a bitcast which these were. Differential Revision: https://reviews.llvm.org/D35977 llvm-svn: 309589
2017-08-01 01:35:44 +08:00
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512BW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BW-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v32i8:
; AVX512BWVL: # BB#0:
[AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead. These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use. But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases. I also generally dislike patterns rooted in a bitcast which these were. Differential Revision: https://reviews.llvm.org/D35977 llvm-svn: 309589
2017-08-01 01:35:44 +08:00
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512BWVL-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512BWVL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BWVL-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BWVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62>
store <32 x i8> %strided.vec, <32 x i8>* %S
ret void
}
define void @trunc_v32i16_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
; AVX512F-LABEL: trunc_v32i16_to_v32i8:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpmovsxwd (%rdi), %zmm0
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vpmovsxwd 32(%rdi), %zmm1
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_v32i16_to_v32i8:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpmovsxwd (%rdi), %zmm0
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT: vpmovsxwd 32(%rdi), %zmm1
; AVX512VL-NEXT: vpmovdb %zmm1, %xmm1
; AVX512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512VL-NEXT: vmovdqa %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_v32i16_to_v32i8:
; AVX512BW: # BB#0:
[AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead. These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use. But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases. I also generally dislike patterns rooted in a bitcast which these were. Differential Revision: https://reviews.llvm.org/D35977 llvm-svn: 309589
2017-08-01 01:35:44 +08:00
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BW-NEXT: vpmovwb %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_v32i16_to_v32i8:
; AVX512BWVL: # BB#0:
[AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead. These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use. But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases. I also generally dislike patterns rooted in a bitcast which these were. Differential Revision: https://reviews.llvm.org/D35977 llvm-svn: 309589
2017-08-01 01:35:44 +08:00
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BWVL-NEXT: vpmovwb %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512BWVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <32 x i16>
%strided.vec = trunc <32 x i16> %bc to <32 x i8>
store <32 x i8> %strided.vec, <32 x i8>* %S
ret void
}
define void @shuffle_v32i16_to_v16i16(<32 x i16>* %L, <16 x i16>* %S) nounwind {
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512F-LABEL: shuffle_v32i16_to_v16i16:
; AVX512F: # BB#0:
; AVX512F-NEXT: vpshuflw {{.*#+}} ymm0 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512F-NEXT: vpshufhw {{.*#+}} ymm0 = ymm0[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512F-NEXT: vpshuflw {{.*#+}} ymm1 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512F-NEXT: vpshufhw {{.*#+}} ymm1 = ymm1[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512F-NEXT: vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
; AVX512F-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512F-NEXT: vmovaps %ymm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i16_to_v16i16:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpshuflw {{.*#+}} ymm0 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512VL-NEXT: vpshufhw {{.*#+}} ymm0 = ymm0[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512VL-NEXT: vpshuflw {{.*#+}} ymm1 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512VL-NEXT: vpshufhw {{.*#+}} ymm1 = ymm1[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512VL-NEXT: vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
; AVX512VL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512VL-NEXT: vmovaps %ymm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i16_to_v16i16:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vpshuflw {{.*#+}} ymm1 = ymm1[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512BW-NEXT: vpshufhw {{.*#+}} ymm1 = ymm1[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512BW-NEXT: vpshuflw {{.*#+}} ymm0 = ymm0[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512BW-NEXT: vpshufhw {{.*#+}} ymm0 = ymm0[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512BW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512BW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BW-NEXT: vmovaps %ymm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i16_to_v16i16:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,16,18,20,22,8,10,12,14,24,26,28,30]
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vpermq {{.*#+}} ymm0 = ymm2[0,2,1,3]
; AVX512BWVL-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
%vec = load <32 x i16>, <32 x i16>* %L
%strided.vec = shufflevector <32 x i16> %vec, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
store <16 x i16> %strided.vec, <16 x i16>* %S
ret void
}
define void @trunc_v16i32_to_v16i16(<32 x i16>* %L, <16 x i16>* %S) nounwind {
; AVX512-LABEL: trunc_v16i32_to_v16i16:
; AVX512: # BB#0:
; AVX512-NEXT: vmovdqa32 (%rdi), %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%bc = bitcast <32 x i16> %vec to <16 x i32>
%strided.vec = trunc <16 x i32> %bc to <16 x i16>
store <16 x i16> %strided.vec, <16 x i16>* %S
ret void
}
define void @shuffle_v16i32_to_v8i32(<16 x i32>* %L, <8 x i32>* %S) nounwind {
; AVX512-LABEL: shuffle_v16i32_to_v8i32:
; AVX512: # BB#0:
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512-NEXT: vmovaps (%rdi), %zmm0
; AVX512-NEXT: vextractf64x4 $1, %zmm0, %ymm1
; AVX512-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512-NEXT: vmovaps %ymm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <16 x i32>, <16 x i32>* %L
%strided.vec = shufflevector <16 x i32> %vec, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
store <8 x i32> %strided.vec, <8 x i32>* %S
ret void
}
define void @trunc_v8i64_to_v8i32(<16 x i32>* %L, <8 x i32>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i32:
; AVX512: # BB#0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqd %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <16 x i32>, <16 x i32>* %L
%bc = bitcast <16 x i32> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i32>
store <8 x i32> %strided.vec, <8 x i32>* %S
ret void
}
define void @shuffle_v64i8_to_v16i8(<64 x i8>* %L, <16 x i8>* %S) nounwind {
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512F-LABEL: shuffle_v64i8_to_v16i8:
; AVX512F: # BB#0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v16i8:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v16i8:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v16i8:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BWVL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
store <16 x i8> %strided.vec, <16 x i8>* %S
ret void
}
define void @trunc_v16i32_to_v16i8(<64 x i8>* %L, <16 x i8>* %S) nounwind {
; AVX512-LABEL: trunc_v16i32_to_v16i8:
; AVX512: # BB#0:
; AVX512-NEXT: vmovdqa32 (%rdi), %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <16 x i32>
%strided.vec = trunc <16 x i32> %bc to <16 x i8>
store <16 x i8> %strided.vec, <16 x i8>* %S
ret void
}
define void @shuffle_v32i16_to_v8i16(<32 x i16>* %L, <8 x i16>* %S) nounwind {
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512F-LABEL: shuffle_v32i16_to_v8i16:
; AVX512F: # BB#0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i16_to_v8i16:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i16_to_v8i16:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i16_to_v8i16:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vmovdqa %xmm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
%vec = load <32 x i16>, <32 x i16>* %L
%strided.vec = shufflevector <32 x i16> %vec, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
store <8 x i16> %strided.vec, <8 x i16>* %S
ret void
}
define void @trunc_v8i64_to_v8i16(<32 x i16>* %L, <8 x i16>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i16:
; AVX512: # BB#0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqw %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%bc = bitcast <32 x i16> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i16>
store <8 x i16> %strided.vec, <8 x i16>* %S
ret void
}
define void @shuffle_v64i8_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512F-LABEL: shuffle_v64i8_to_v8i8:
; AVX512F: # BB#0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v8i8:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v8i8:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v8i8:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vpmovwb %xmm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <8 x i32> <i32 0, i32 8, i32 16, i32 24, i32 32, i32 40, i32 48, i32 56>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define void @trunc_v8i64_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i8:
; AVX512: # BB#0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqb %zmm0, (%rsi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86] Add test cases that cover pr31551. NFC. llvm-svn: 291127
2017-01-06 00:48:28 +08:00
; AVX512-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i8>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
[X86] Adding a test for vector shuffle extractions. When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present). Committed on behalf of @jbhateja (Jatin Bhateja) Differential Revision: https://reviews.llvm.org/D36271 llvm-svn: 309963
2017-08-04 01:04:59 +08:00
[X86][AVX512] Added additional shuffle+trunc test case. An existing test should have covered this but a typo caused it to fail. I've kept both as the codegen for the typo case needs addressing as well. llvm-svn: 310791
2017-08-13 20:30:36 +08:00
define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61(<64 x i8> %x) {
; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512F: # BB#0:
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512BW: # BB#0:
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
[X86][AVX512] Added additional shuffle+trunc test case. An existing test should have covered this but a typo caused it to fail. I've kept both as the codegen for the typo case needs addressing as well. llvm-svn: 310791
2017-08-13 20:30:36 +08:00
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512BWVL: # BB#0:
Revert r307036 because of PR34919. llvm-svn: 315540
2017-10-12 08:24:52 +08:00
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
[X86][AVX512] Added additional shuffle+trunc test case. An existing test should have covered this but a typo caused it to fail. I've kept both as the codegen for the typo case needs addressing as well. llvm-svn: 310791
2017-08-13 20:30:36 +08:00
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
ret <16 x i8> %res
}
[X86] Adding a test for vector shuffle extractions. When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present). Committed on behalf of @jbhateja (Jatin Bhateja) Differential Revision: https://reviews.llvm.org/D36271 llvm-svn: 309963
2017-08-04 01:04:59 +08:00
define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62(<64 x i8> %x) {
; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512F: # BB#0:
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BW: # BB#0:
[DAGCombiner] Extending pattern detection for vector shuffle. Summary: If all the operands of a BUILD_VECTOR extract elements from same vector then split the vector efficiently based on the maximum vector access index. This will also fix PR 33784 Reviewers: zvi, delena, RKSimon, thakis Reviewed By: RKSimon Subscribers: chandlerc, eladcohen, llvm-commits Differential Revision: https://reviews.llvm.org/D35788 llvm-svn: 311833
2017-08-27 03:02:36 +08:00
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm2
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
[X86] Adding a test for vector shuffle extractions. When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present). Committed on behalf of @jbhateja (Jatin Bhateja) Differential Revision: https://reviews.llvm.org/D36271 llvm-svn: 309963
2017-08-04 01:04:59 +08:00
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BWVL: # BB#0:
[DAGCombiner] Extending pattern detection for vector shuffle. Summary: If all the operands of a BUILD_VECTOR extract elements from same vector then split the vector efficiently based on the maximum vector access index. This will also fix PR 33784 Reviewers: zvi, delena, RKSimon, thakis Reviewed By: RKSimon Subscribers: chandlerc, eladcohen, llvm-commits Differential Revision: https://reviews.llvm.org/D35788 llvm-svn: 311833
2017-08-27 03:02:36 +08:00
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm2
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
[X86] Adding a test for vector shuffle extractions. When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present). Committed on behalf of @jbhateja (Jatin Bhateja) Differential Revision: https://reviews.llvm.org/D36271 llvm-svn: 309963
2017-08-04 01:04:59 +08:00
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
ret <16 x i8> %res
}
[DAGCombiner] Extending pattern detection for vector shuffle. Summary: If all the operands of a BUILD_VECTOR extract elements from same vector then split the vector efficiently based on the maximum vector access index. This will also fix PR 33784 Reviewers: zvi, delena, RKSimon, thakis Reviewed By: RKSimon Subscribers: chandlerc, eladcohen, llvm-commits Differential Revision: https://reviews.llvm.org/D35788 llvm-svn: 311833
2017-08-27 03:02:36 +08:00
define <4 x double> @PR34175(<32 x i16>* %p) {
; AVX512F-LABEL: PR34175:
; AVX512F: # BB#0:
; AVX512F-NEXT: vmovdqu (%rdi), %ymm0
; AVX512F-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512F-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512F-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512F-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR34175:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vmovdqu (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512VL-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512VL-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR34175:
; AVX512BW: # BB#0:
; AVX512BW-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512BW-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
; AVX512BW-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512BW-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR34175:
; AVX512BWVL: # BB#0:
; AVX512BWVL-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,8,16,24,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX512BWVL-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512BWVL-NEXT: retq
%v = load <32 x i16>, <32 x i16>* %p, align 2
%shuf = shufflevector <32 x i16> %v, <32 x i16> undef, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
%tofp = uitofp <4 x i16> %shuf to <4 x double>
ret <4 x double> %tofp
}