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-popcnt-512.ll

290 lines
17 KiB
LLVM
Raw Normal View History

Make utils/update_llc_test_checks.py note that the assertions are autogenerated. Also update existing test cases which appear to be generated by it and weren't modified (other than addition of the header) by rerunning it. llvm-svn: 253917
2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; 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=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vpopcntdq | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VPOPCNTDQ --check-prefix=AVX512VPOPCNTDQ-NOBW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vpopcntdq,+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VPOPCNTDQ --check-prefix=AVX512VPOPCNTDQ-BW
[x86][icelake]BITALG vpopcnt{b,w} Differential Revision: https://reviews.llvm.org/D40213 llvm-svn: 318748
2017-11-21 18:32:42 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bitalg | FileCheck %s --check-prefix=AVX512 --check-prefix=BITALG
[X86] Updated vector popcnt tests. Added vec512 tests. llvm-svn: 246921
2015-09-05 17:59:59 +08:00
define <8 x i64> @testv8i64(<8 x i64> %in) nounwind {
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-LABEL: testv8i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512F: # %bb.0:
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm3
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX512F-NEXT: vpshufb %ymm1, %ymm4, %ymm1
; AVX512F-NEXT: vpaddb %ymm3, %ymm1, %ymm1
[X86] SET0 to use XMM registers where possible PR26018 PR32862 Differential Revision: https://reviews.llvm.org/D35839 llvm-svn: 309298
2017-07-28 01:47:01 +08:00
; AVX512F-NEXT: vpxor %xmm3, %xmm3, %xmm3
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-NEXT: vpsadbw %ymm3, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm5
; AVX512F-NEXT: vpshufb %ymm5, %ymm4, %ymm5
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vpshufb %ymm0, %ymm4, %ymm0
; AVX512F-NEXT: vpaddb %ymm5, %ymm0, %ymm0
; AVX512F-NEXT: vpsadbw %ymm3, %ymm0, %ymm0
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: testv8i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512BW: # %bb.0:
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
[X86] SET0 to use XMM registers where possible PR26018 PR32862 Differential Revision: https://reviews.llvm.org/D35965 llvm-svn: 309926
2017-08-03 16:50:18 +08:00
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vpsadbw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: retq
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
;
; AVX512VPOPCNTDQ-LABEL: testv8i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ: # %bb.0:
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
; AVX512VPOPCNTDQ-NEXT: vpopcntq %zmm0, %zmm0
; AVX512VPOPCNTDQ-NEXT: retq
[X86] Regenerate the vector-popcnt and vector-tzcnt tests to get BITALG CHECK linse on all functions not just the vXi16/vXi8. llvm-svn: 318885
2017-11-23 07:35:12 +08:00
;
; BITALG-LABEL: testv8i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; BITALG: # %bb.0:
[X86] Regenerate the vector-popcnt and vector-tzcnt tests to get BITALG CHECK linse on all functions not just the vXi16/vXi8. llvm-svn: 318885
2017-11-23 07:35:12 +08:00
; BITALG-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; BITALG-NEXT: vpandq %zmm1, %zmm0, %zmm2
; BITALG-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; BITALG-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; BITALG-NEXT: vpsrlw $4, %zmm0, %zmm0
; BITALG-NEXT: vpandq %zmm1, %zmm0, %zmm0
; BITALG-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; BITALG-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; BITALG-NEXT: vpxor %xmm1, %xmm1, %xmm1
; BITALG-NEXT: vpsadbw %zmm1, %zmm0, %zmm0
; BITALG-NEXT: retq
[X86] Updated vector popcnt tests. Added vec512 tests. llvm-svn: 246921
2015-09-05 17:59:59 +08:00
%out = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %in)
ret <8 x i64> %out
}
define <16 x i32> @testv16i32(<16 x i32> %in) nounwind {
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-LABEL: testv16i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512F: # %bb.0:
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm3
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX512F-NEXT: vpshufb %ymm1, %ymm4, %ymm1
; AVX512F-NEXT: vpaddb %ymm3, %ymm1, %ymm1
[X86] SET0 to use XMM registers where possible PR26018 PR32862 Differential Revision: https://reviews.llvm.org/D35839 llvm-svn: 309298
2017-07-28 01:47:01 +08:00
; AVX512F-NEXT: vpxor %xmm3, %xmm3, %xmm3
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512F-NEXT: vpunpckhdq {{.*#+}} ymm5 = ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[6],ymm3[6],ymm1[7],ymm3[7]
; AVX512F-NEXT: vpsadbw %ymm3, %ymm5, %ymm5
; AVX512F-NEXT: vpunpckldq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[4],ymm3[4],ymm1[5],ymm3[5]
; AVX512F-NEXT: vpsadbw %ymm3, %ymm1, %ymm1
; AVX512F-NEXT: vpackuswb %ymm5, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm5
; AVX512F-NEXT: vpshufb %ymm5, %ymm4, %ymm5
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vpshufb %ymm0, %ymm4, %ymm0
; AVX512F-NEXT: vpaddb %ymm5, %ymm0, %ymm0
; AVX512F-NEXT: vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[6],ymm3[6],ymm0[7],ymm3[7]
; AVX512F-NEXT: vpsadbw %ymm3, %ymm2, %ymm2
; AVX512F-NEXT: vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[4],ymm3[4],ymm0[5],ymm3[5]
; AVX512F-NEXT: vpsadbw %ymm3, %ymm0, %ymm0
; AVX512F-NEXT: vpackuswb %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: testv16i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512BW: # %bb.0:
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
[X86] SET0 to use XMM registers where possible PR26018 PR32862 Differential Revision: https://reviews.llvm.org/D35965 llvm-svn: 309926
2017-08-03 16:50:18 +08:00
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
[AVX512] Add support for popcount of v8i64 and v16i32 with and without BWI instructions. Without BWI we have to split the vectors into 256-bit vectors so we can use AVX2 pshufb and then concatenate the results. llvm-svn: 266950
2016-04-21 11:57:24 +08:00
; AVX512BW-NEXT: vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
; AVX512BW-NEXT: vpsadbw %zmm1, %zmm2, %zmm2
; AVX512BW-NEXT: vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
; AVX512BW-NEXT: vpsadbw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpackuswb %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT: retq
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
;
; AVX512VPOPCNTDQ-LABEL: testv16i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ: # %bb.0:
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
; AVX512VPOPCNTDQ-NEXT: vpopcntd %zmm0, %zmm0
; AVX512VPOPCNTDQ-NEXT: retq
[X86] Regenerate the vector-popcnt and vector-tzcnt tests to get BITALG CHECK linse on all functions not just the vXi16/vXi8. llvm-svn: 318885
2017-11-23 07:35:12 +08:00
;
; BITALG-LABEL: testv16i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; BITALG: # %bb.0:
[X86] Regenerate the vector-popcnt and vector-tzcnt tests to get BITALG CHECK linse on all functions not just the vXi16/vXi8. llvm-svn: 318885
2017-11-23 07:35:12 +08:00
; BITALG-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; BITALG-NEXT: vpandq %zmm1, %zmm0, %zmm2
; BITALG-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; BITALG-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; BITALG-NEXT: vpsrlw $4, %zmm0, %zmm0
; BITALG-NEXT: vpandq %zmm1, %zmm0, %zmm0
; BITALG-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; BITALG-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; BITALG-NEXT: vpxor %xmm1, %xmm1, %xmm1
; BITALG-NEXT: vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
; BITALG-NEXT: vpsadbw %zmm1, %zmm2, %zmm2
; BITALG-NEXT: vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
; BITALG-NEXT: vpsadbw %zmm1, %zmm0, %zmm0
; BITALG-NEXT: vpackuswb %zmm2, %zmm0, %zmm0
; BITALG-NEXT: retq
[X86] Updated vector popcnt tests. Added vec512 tests. llvm-svn: 246921
2015-09-05 17:59:59 +08:00
%out = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %in)
ret <16 x i32> %out
}
define <32 x i16> @testv32i16(<32 x i16> %in) nounwind {
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512F-LABEL: testv32i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512F: # %bb.0:
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm3
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vpshufb %ymm0, %ymm4, %ymm0
; AVX512F-NEXT: vpaddb %ymm3, %ymm0, %ymm0
; AVX512F-NEXT: vpsllw $8, %ymm0, %ymm3
; AVX512F-NEXT: vpaddb %ymm0, %ymm3, %ymm0
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm3
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX512F-NEXT: vpshufb %ymm1, %ymm4, %ymm1
; AVX512F-NEXT: vpaddb %ymm3, %ymm1, %ymm1
; AVX512F-NEXT: vpsllw $8, %ymm1, %ymm2
; AVX512F-NEXT: vpaddb %ymm1, %ymm2, %ymm1
; AVX512F-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: testv32i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512BW: # %bb.0:
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT: vpsllw $8, %zmm0, %zmm1
; AVX512BW-NEXT: vpaddb %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: vpsrlw $8, %zmm0, %zmm0
; AVX512BW-NEXT: retq
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
;
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-NOBW-LABEL: testv32i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ-NOBW: # %bb.0:
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-NOBW-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VPOPCNTDQ-NOBW-NEXT: vpopcntd %zmm0, %zmm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
; AVX512VPOPCNTDQ-NOBW-NEXT: vpopcntd %zmm1, %zmm1
; AVX512VPOPCNTDQ-NOBW-NEXT: vpmovdw %zmm1, %ymm1
; AVX512VPOPCNTDQ-NOBW-NEXT: retq
;
; AVX512VPOPCNTDQ-BW-LABEL: testv32i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ-BW: # %bb.0:
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512VPOPCNTDQ-BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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
; AVX512VPOPCNTDQ-BW-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512VPOPCNTDQ-BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpsllw $8, %zmm0, %zmm1
; AVX512VPOPCNTDQ-BW-NEXT: vpaddb %zmm0, %zmm1, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpsrlw $8, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: retq
[x86][icelake]BITALG vpopcnt{b,w} Differential Revision: https://reviews.llvm.org/D40213 llvm-svn: 318748
2017-11-21 18:32:42 +08:00
;
; BITALG-LABEL: testv32i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; BITALG: # %bb.0:
[x86][icelake]BITALG vpopcnt{b,w} Differential Revision: https://reviews.llvm.org/D40213 llvm-svn: 318748
2017-11-21 18:32:42 +08:00
; BITALG-NEXT: vpopcntw %zmm0, %zmm0
; BITALG-NEXT: retq
[X86] Updated vector popcnt tests. Added vec512 tests. llvm-svn: 246921
2015-09-05 17:59:59 +08:00
%out = call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %in)
ret <32 x i16> %out
}
define <64 x i8> @testv64i8(<64 x i8> %in) nounwind {
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512F-LABEL: testv64i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512F: # %bb.0:
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm3
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vpshufb %ymm0, %ymm4, %ymm0
; AVX512F-NEXT: vpaddb %ymm3, %ymm0, %ymm0
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm3
; AVX512F-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512F-NEXT: vpsrlw $4, %ymm1, %ymm1
; AVX512F-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX512F-NEXT: vpshufb %ymm1, %ymm4, %ymm1
; AVX512F-NEXT: vpaddb %ymm3, %ymm1, %ymm1
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: testv64i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512BW: # %bb.0:
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[AVX512] Add popcount support for v32i16 and v64i8. llvm-svn: 266858
2016-04-20 13:18:55 +08:00
; AVX512BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT: retq
[X86] Adding vpopcntd and vpopcntq instructions AVX512_VPOPCNTDQ is a new feature set that was published by Intel. The patch represents the LLVM side of the addition of two new intrinsic based instructions (vpopcntd and vpopcntq). Differential Revision: https://reviews.llvm.org/D33169 llvm-svn: 303858
2017-05-25 21:45:23 +08:00
;
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-NOBW-LABEL: testv64i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ-NOBW: # %bb.0:
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-NOBW-NEXT: vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512VPOPCNTDQ-NOBW-NEXT: vpand %ymm2, %ymm0, %ymm3
; AVX512VPOPCNTDQ-NOBW-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX512VPOPCNTDQ-NOBW-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512VPOPCNTDQ-NOBW-NEXT: vpsrlw $4, %ymm0, %ymm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpshufb %ymm0, %ymm4, %ymm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpaddb %ymm3, %ymm0, %ymm0
; AVX512VPOPCNTDQ-NOBW-NEXT: vpand %ymm2, %ymm1, %ymm3
; AVX512VPOPCNTDQ-NOBW-NEXT: vpshufb %ymm3, %ymm4, %ymm3
; AVX512VPOPCNTDQ-NOBW-NEXT: vpsrlw $4, %ymm1, %ymm1
; AVX512VPOPCNTDQ-NOBW-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX512VPOPCNTDQ-NOBW-NEXT: vpshufb %ymm1, %ymm4, %ymm1
; AVX512VPOPCNTDQ-NOBW-NEXT: vpaddb %ymm3, %ymm1, %ymm1
; AVX512VPOPCNTDQ-NOBW-NEXT: retq
;
; AVX512VPOPCNTDQ-BW-LABEL: testv64i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX512VPOPCNTDQ-BW: # %bb.0:
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX512VPOPCNTDQ-BW-NEXT: vpandq %zmm1, %zmm0, %zmm2
[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
; AVX512VPOPCNTDQ-BW-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
[X86][AVX512] Test AVX512VPOPCNTDQ CTPOP with/without AVX512BW llvm-svn: 306991
2017-07-03 03:52:20 +08:00
; AVX512VPOPCNTDQ-BW-NEXT: vpshufb %zmm2, %zmm3, %zmm2
; AVX512VPOPCNTDQ-BW-NEXT: vpsrlw $4, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpshufb %zmm0, %zmm3, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: vpaddb %zmm2, %zmm0, %zmm0
; AVX512VPOPCNTDQ-BW-NEXT: retq
[x86][icelake]BITALG vpopcnt{b,w} Differential Revision: https://reviews.llvm.org/D40213 llvm-svn: 318748
2017-11-21 18:32:42 +08:00
;
; BITALG-LABEL: testv64i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; BITALG: # %bb.0:
[x86][icelake]BITALG vpopcnt{b,w} Differential Revision: https://reviews.llvm.org/D40213 llvm-svn: 318748
2017-11-21 18:32:42 +08:00
; BITALG-NEXT: vpopcntb %zmm0, %zmm0
; BITALG-NEXT: retq
[X86] Updated vector popcnt tests. Added vec512 tests. llvm-svn: 246921
2015-09-05 17:59:59 +08:00
%out = call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %in)
ret <64 x i8> %out
}
declare <8 x i64> @llvm.ctpop.v8i64(<8 x i64>)
declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>)
declare <32 x i16> @llvm.ctpop.v32i16(<32 x i16>)
declare <64 x i8> @llvm.ctpop.v64i8(<64 x i8>)