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/vector-pack-128.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

271 lines
11 KiB
LLVM
Raw Normal View History

[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
[NFC] Disallow unused prefixes in CodeGen/X86 tests. Also fixed remaining tests that featured unused prefixes. Differential Revision: https://reviews.llvm.org/D94330
2021-01-09 04:21:29 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+avx512f | FileCheck %s --check-prefixes=AVX,AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+avx512bw | FileCheck %s --check-prefixes=AVX,AVX512
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; trunc(concat(x,y)) -> pack
define <8 x i16> @trunc_concat_packssdw_128(<4 x i32> %a0, <4 x i32> %a1) nounwind {
; SSE-LABEL: trunc_concat_packssdw_128:
; SSE: # %bb.0:
; SSE-NEXT: psrad $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_concat_packssdw_128:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrad $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_concat_packssdw_128:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsrad $17, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [15,15,15,15]
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_concat_packssdw_128:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrad $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX512-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm1, %xmm1
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX512-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX512-NEXT: retq
%1 = ashr <4 x i32> %a0, <i32 17, i32 17, i32 17, i32 17>
%2 = and <4 x i32> %a1, <i32 15, i32 15, i32 15, i32 15>
%3 = shufflevector <4 x i32> %1, <4 x i32> %2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%4 = trunc <8 x i32> %3 to <8 x i16>
ret <8 x i16> %4
}
define <8 x i16> @trunc_concat_packusdw_128(<4 x i32> %a0, <4 x i32> %a1) nounwind {
; SSE2-LABEL: trunc_concat_packusdw_128:
; SSE2: # %bb.0:
; SSE2-NEXT: psrld $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE2-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE4-LABEL: trunc_concat_packusdw_128:
; SSE4: # %bb.0:
; SSE4-NEXT: psrld $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE4-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE4-NEXT: packusdw %xmm1, %xmm0
; SSE4-NEXT: retq
;
; AVX1-LABEL: trunc_concat_packusdw_128:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrld $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_concat_packusdw_128:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsrld $17, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [15,15,15,15]
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_concat_packusdw_128:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrld $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX512-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm1, %xmm1
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX512-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX512-NEXT: retq
%1 = lshr <4 x i32> %a0, <i32 17, i32 17, i32 17, i32 17>
%2 = and <4 x i32> %a1, <i32 15, i32 15, i32 15, i32 15>
%3 = shufflevector <4 x i32> %1, <4 x i32> %2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%4 = trunc <8 x i32> %3 to <8 x i16>
ret <8 x i16> %4
}
define <16 x i8> @trunc_concat_packsswb_128(<8 x i16> %a0, <8 x i16> %a1) nounwind {
; SSE-LABEL: trunc_concat_packsswb_128:
; SSE: # %bb.0:
; SSE-NEXT: psraw $15, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: retq
;
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX-LABEL: trunc_concat_packsswb_128:
; AVX: # %bb.0:
; AVX-NEXT: vpsraw $15, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
%1 = ashr <8 x i16> %a0, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
%2 = and <8 x i16> %a1, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = shufflevector <8 x i16> %1, <8 x i16> %2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%4 = trunc <16 x i16> %3 to <16 x i8>
ret <16 x i8> %4
}
define <16 x i8> @trunc_concat_packuswb_128(<8 x i16> %a0, <8 x i16> %a1) nounwind {
; SSE-LABEL: trunc_concat_packuswb_128:
; SSE: # %bb.0:
; SSE-NEXT: psrlw $15, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX-LABEL: trunc_concat_packuswb_128:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $15, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][AVX] combineVectorSignBitsTruncation - use PACKSS/PACKUS in more AVX cases AVX512 has fast truncation ops, but if the truncation source is a concatenation of subvectors then its likely that we can use PACK more efficiently. This is only guaranteed to work for truncations to 128/256-bit vectors as the PACK works across 128-bit sub-lanes, for now I've just disabled 512-bit truncation cases but we need to get them working eventually for D61129.
2021-01-05 23:01:23 +08:00
; AVX-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
%1 = lshr <8 x i16> %a0, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
%2 = and <8 x i16> %a1, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = shufflevector <8 x i16> %1, <8 x i16> %2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%4 = trunc <16 x i16> %3 to <16 x i8>
ret <16 x i8> %4
}
; concat(trunc(x),trunc(y)) -> pack
define <8 x i16> @concat_trunc_packssdw_128(<4 x i32> %a0, <4 x i32> %a1) nounwind {
; SSE2-LABEL: concat_trunc_packssdw_128:
; SSE2: # %bb.0:
; SSE2-NEXT: psrad $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE2-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE2-NEXT: packssdw %xmm0, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm1
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT: retq
;
; SSE4-LABEL: concat_trunc_packssdw_128:
; SSE4: # %bb.0:
; SSE4-NEXT: psrad $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE4-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE4-NEXT: packssdw %xmm1, %xmm0
; SSE4-NEXT: retq
;
; AVX1-LABEL: concat_trunc_packssdw_128:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrad $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: concat_trunc_packssdw_128:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsrad $17, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [15,15,15,15]
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpackssdw %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpackusdw %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: retq
;
; AVX512-LABEL: concat_trunc_packssdw_128:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrad $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX512-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX512-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
%1 = ashr <4 x i32> %a0, <i32 17, i32 17, i32 17, i32 17>
%2 = and <4 x i32> %a1, <i32 15, i32 15, i32 15, i32 15>
%3 = trunc <4 x i32> %1 to <4 x i16>
%4 = trunc <4 x i32> %2 to <4 x i16>
%5 = shufflevector <4 x i16> %3, <4 x i16> %4, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %5
}
define <8 x i16> @concat_trunc_packusdw_128(<4 x i32> %a0, <4 x i32> %a1) nounwind {
; SSE2-LABEL: concat_trunc_packusdw_128:
; SSE2: # %bb.0:
; SSE2-NEXT: psrld $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE2-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE2-NEXT: packssdw %xmm0, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm1
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT: retq
;
; SSE4-LABEL: concat_trunc_packusdw_128:
; SSE4: # %bb.0:
; SSE4-NEXT: psrld $17, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE4-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE4-NEXT: packusdw %xmm1, %xmm0
; SSE4-NEXT: retq
;
; AVX1-LABEL: concat_trunc_packusdw_128:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrld $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: concat_trunc_packusdw_128:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsrld $17, %xmm0, %xmm0
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [15,15,15,15]
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: concat_trunc_packusdw_128:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrld $17, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX512-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX512-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
%1 = lshr <4 x i32> %a0, <i32 17, i32 17, i32 17, i32 17>
%2 = and <4 x i32> %a1, <i32 15, i32 15, i32 15, i32 15>
%3 = trunc <4 x i32> %1 to <4 x i16>
%4 = trunc <4 x i32> %2 to <4 x i16>
%5 = shufflevector <4 x i16> %3, <4 x i16> %4, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %5
}
define <16 x i8> @concat_trunc_packsswb_128(<8 x i16> %a0, <8 x i16> %a1) nounwind {
; SSE-LABEL: concat_trunc_packsswb_128:
; SSE: # %bb.0:
; SSE-NEXT: psraw $15, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: concat_trunc_packsswb_128:
; AVX: # %bb.0:
; AVX-NEXT: vpsraw $15, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <8 x i16> %a0, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
%2 = and <8 x i16> %a1, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = trunc <8 x i16> %1 to <8 x i8>
%4 = trunc <8 x i16> %2 to <8 x i8>
%5 = shufflevector <8 x i8> %3, <8 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %5
}
define <16 x i8> @concat_trunc_packuswb_128(<8 x i16> %a0, <8 x i16> %a1) nounwind {
; SSE-LABEL: concat_trunc_packuswb_128:
; SSE: # %bb.0:
; SSE-NEXT: psrlw $15, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: concat_trunc_packuswb_128:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $15, %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
[X86][SSE] Add PACKSS/PACKUS style patterns tests Similar to the proposed generic code generated by D61129 - there's still some shuffle combining improvements to go before that patch is ready.
2020-07-05 23:17:56 +08:00
; AVX-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = lshr <8 x i16> %a0, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
%2 = and <8 x i16> %a1, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = trunc <8 x i16> %1 to <8 x i8>
%4 = trunc <8 x i16> %2 to <8 x i8>
%5 = shufflevector <8 x i8> %3, <8 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %5
}