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/vselect-packss.ll

398 lines
16 KiB
LLVM
Raw Normal View History

[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +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-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE42
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512NOBW --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512NOBW --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW --check-prefix=AVX512BWNOVL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW --check-prefix=AVX512BWVL
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
;
; General cases - packing of vector comparison to legal vector result types
;
define <16 x i8> @vselect_packss_v16i16(<16 x i16> %a0, <16 x i16> %a1, <16 x i8> %a2, <16 x i8> %a3) {
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE2-LABEL: vselect_packss_v16i16:
[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
; SSE2: # %bb.0:
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE2-NEXT: pcmpeqw %xmm3, %xmm1
; SSE2-NEXT: pcmpeqw %xmm2, %xmm0
; SSE2-NEXT: packsswb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm5, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE42-LABEL: vselect_packss_v16i16:
[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
; SSE42: # %bb.0:
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE42-NEXT: pcmpeqw %xmm3, %xmm1
; SSE42-NEXT: pcmpeqw %xmm2, %xmm0
; SSE42-NEXT: packsswb %xmm1, %xmm0
; SSE42-NEXT: pblendvb %xmm0, %xmm4, %xmm5
; SSE42-NEXT: movdqa %xmm5, %xmm0
; SSE42-NEXT: retq
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
;
; AVX1-LABEL: vselect_packss_v16i16:
[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
; AVX1: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT: vpcmpeqw %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm0
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; AVX1-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: vselect_packss_v16i16:
[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
; AVX2: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; AVX2-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-LABEL: vselect_packss_v16i16:
[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
; AVX512NOBW: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX512NOBW-NEXT: vpmovsxwd %ymm0, %zmm0
; AVX512NOBW-NEXT: vpmovdb %zmm0, %xmm0
; AVX512NOBW-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512NOBW-NEXT: vzeroupper
; AVX512NOBW-NEXT: retq
;
; AVX512BWNOVL-LABEL: vselect_packss_v16i16:
[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
; AVX512BWNOVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWNOVL-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX512BWNOVL-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BWNOVL-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512BWNOVL-NEXT: vzeroupper
; AVX512BWNOVL-NEXT: retq
;
; AVX512BWVL-LABEL: vselect_packss_v16i16:
[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
; AVX512BWVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWVL-NEXT: vpcmpeqw %ymm1, %ymm0, %k0
; AVX512BWVL-NEXT: vpmovm2b %k0, %xmm0
; AVX512BWVL-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
%1 = icmp eq <16 x i16> %a0, %a1
%2 = sext <16 x i1> %1 to <16 x i8>
%3 = and <16 x i8> %2, %a2
%4 = xor <16 x i8> %2, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%5 = and <16 x i8> %4, %a3
%6 = or <16 x i8> %3, %5
ret <16 x i8> %6
}
define <16 x i8> @vselect_packss_v16i32(<16 x i32> %a0, <16 x i32> %a1, <16 x i8> %a2, <16 x i8> %a3) {
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-LABEL: vselect_packss_v16i32:
[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
; SSE2: # %bb.0:
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-NEXT: pcmpeqd %xmm7, %xmm3
; SSE2-NEXT: pcmpeqd %xmm6, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: pcmpeqd %xmm5, %xmm1
; SSE2-NEXT: pcmpeqd %xmm4, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: packsswb %xmm2, %xmm0
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pandn {{[0-9]+}}(%rsp), %xmm0
; SSE2-NEXT: por %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE42-LABEL: vselect_packss_v16i32:
[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
; SSE42: # %bb.0:
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
; SSE42-NEXT: pcmpeqd %xmm7, %xmm3
; SSE42-NEXT: pcmpeqd %xmm6, %xmm2
; SSE42-NEXT: packssdw %xmm3, %xmm2
; SSE42-NEXT: pcmpeqd %xmm5, %xmm1
; SSE42-NEXT: pcmpeqd %xmm4, %xmm0
; SSE42-NEXT: packssdw %xmm1, %xmm0
; SSE42-NEXT: packsswb %xmm2, %xmm0
; SSE42-NEXT: pblendvb %xmm0, {{[0-9]+}}(%rsp), %xmm8
; SSE42-NEXT: movdqa %xmm8, %xmm0
; SSE42-NEXT: retq
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
;
; AVX1-LABEL: vselect_packss_v16i32:
[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
; AVX1: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm6
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm7
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm7, %xmm6
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm1, %xmm1
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm6, %xmm1, %xmm1
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm6
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm0, %xmm0
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpblendvb %xmm0, %xmm4, %xmm5, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: vselect_packss_v16i32:
[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
; AVX2: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm1, %ymm1
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm0, %ymm0
[X86][SSE] truncateVectorWithPACK - Use src type instead of dst to select between PACK*SDW/PACK*SWB Try to keep PACK*SDW/PACK*SWB as wide as possible, this helps ComputeNumSignBits as it can only peek through bitcasts to wider types, pre-AVX2 codegen was already doing this as it could peek through bitcasts/subvectors more easily than AVX2 could through shuffles. This shouldn't affect existing results as calls to truncateVectorWithPACK ensure we have enough sign bits to pack to the same value, but it should make it possible to use truncateVectorWithPACK chains to perform saturation in combineTruncateWithSat with a future patch. llvm-svn: 325149
2018-02-15 02:23:58 +08:00
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] truncateVectorWithPACK - Use src type instead of dst to select between PACK*SDW/PACK*SWB Try to keep PACK*SDW/PACK*SWB as wide as possible, this helps ComputeNumSignBits as it can only peek through bitcasts to wider types, pre-AVX2 codegen was already doing this as it could peek through bitcasts/subvectors more easily than AVX2 could through shuffles. This shouldn't affect existing results as calls to truncateVectorWithPACK ensure we have enough sign bits to pack to the same value, but it should make it possible to use truncateVectorWithPACK chains to perform saturation in combineTruncateWithSat with a future patch. llvm-svn: 325149
2018-02-15 02:23:58 +08:00
; AVX2-NEXT: vpblendvb %xmm0, %xmm4, %xmm5, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-LABEL: vselect_packss_v16i32:
[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
; AVX512NOBW: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-NEXT: vpcmpeqd %zmm1, %zmm0, %k1
; AVX512NOBW-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512NOBW-NEXT: vpmovdb %zmm0, %xmm0
; AVX512NOBW-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512NOBW-NEXT: vzeroupper
; AVX512NOBW-NEXT: retq
;
; AVX512BWNOVL-LABEL: vselect_packss_v16i32:
[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
; AVX512BWNOVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWNOVL-NEXT: vpcmpeqd %zmm1, %zmm0, %k0
; AVX512BWNOVL-NEXT: vpmovm2b %k0, %zmm0
; AVX512BWNOVL-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512BWNOVL-NEXT: vzeroupper
; AVX512BWNOVL-NEXT: retq
;
; AVX512BWVL-LABEL: vselect_packss_v16i32:
[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
; AVX512BWVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWVL-NEXT: vpcmpeqd %zmm1, %zmm0, %k0
; AVX512BWVL-NEXT: vpmovm2b %k0, %xmm0
; AVX512BWVL-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
%1 = icmp eq <16 x i32> %a0, %a1
%2 = sext <16 x i1> %1 to <16 x i8>
%3 = and <16 x i8> %2, %a2
%4 = xor <16 x i8> %2, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%5 = and <16 x i8> %4, %a3
%6 = or <16 x i8> %3, %5
ret <16 x i8> %6
}
define <16 x i8> @vselect_packss_v16i64(<16 x i64> %a0, <16 x i64> %a1, <16 x i8> %a2, <16 x i8> %a3) {
; SSE2-LABEL: vselect_packss_v16i64:
[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
; SSE2: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm8 = xmm7[1,0,3,2]
; SSE2-NEXT: pand %xmm7, %xmm8
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm6
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[1,0,3,2]
; SSE2-NEXT: pand %xmm6, %xmm7
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-NEXT: packssdw %xmm8, %xmm7
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[1,0,3,2]
; SSE2-NEXT: pand %xmm5, %xmm6
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm4
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[1,0,3,2]
; SSE2-NEXT: pand %xmm4, %xmm5
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-NEXT: packssdw %xmm6, %xmm5
; SSE2-NEXT: packssdw %xmm7, %xmm5
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,0,3,2]
; SSE2-NEXT: pand %xmm3, %xmm4
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,0,3,2]
; SSE2-NEXT: pand %xmm2, %xmm3
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-NEXT: packssdw %xmm4, %xmm3
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,0,3,2]
; SSE2-NEXT: pand %xmm1, %xmm2
; SSE2-NEXT: pcmpeqd {{[0-9]+}}(%rsp), %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
; SSE2-NEXT: pand %xmm0, %xmm1
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE2-NEXT: packssdw %xmm2, %xmm1
; SSE2-NEXT: packssdw %xmm3, %xmm1
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE2-NEXT: packsswb %xmm5, %xmm1
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0
; SSE2-NEXT: pand %xmm1, %xmm0
; SSE2-NEXT: pandn {{[0-9]+}}(%rsp), %xmm1
; SSE2-NEXT: por %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE42-LABEL: vselect_packss_v16i64:
[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
; SSE42: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm7
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm6
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE42-NEXT: packssdw %xmm7, %xmm6
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm5
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm4
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE42-NEXT: packssdw %xmm5, %xmm4
; SSE42-NEXT: packssdw %xmm6, %xmm4
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm3
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm2
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE42-NEXT: packssdw %xmm3, %xmm2
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm1
; SSE42-NEXT: pcmpeqq {{[0-9]+}}(%rsp), %xmm0
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; SSE42-NEXT: packssdw %xmm1, %xmm0
; SSE42-NEXT: packssdw %xmm2, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; SSE42-NEXT: packsswb %xmm4, %xmm0
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1
; SSE42-NEXT: pand %xmm0, %xmm1
; SSE42-NEXT: pandn {{[0-9]+}}(%rsp), %xmm0
; SSE42-NEXT: por %xmm1, %xmm0
; SSE42-NEXT: retq
;
; AVX1-LABEL: vselect_packss_v16i64:
[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
; AVX1: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm8
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm9
; AVX1-NEXT: vpcmpeqq %xmm8, %xmm9, %xmm8
; AVX1-NEXT: vpcmpeqq %xmm7, %xmm3, %xmm3
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm8, %xmm3, %xmm8
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3
; AVX1-NEXT: vpcmpeqq %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vpcmpeqq %xmm6, %xmm2, %xmm2
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpackssdw %xmm8, %xmm2, %xmm2
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm6
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpcmpeqq %xmm5, %xmm1, %xmm1
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm5, %xmm3
; AVX1-NEXT: vpcmpeqq %xmm4, %xmm0, %xmm0
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand {{[0-9]+}}(%rsp), %xmm0, %xmm1
; AVX1-NEXT: vpandn {{[0-9]+}}(%rsp), %xmm0, %xmm0
; AVX1-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: vselect_packss_v16i64:
[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
; AVX2: # %bb.0:
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpcmpeqq %ymm7, %ymm3, %ymm3
; AVX2-NEXT: vpcmpeqq %ymm6, %ymm2, %ymm2
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3]
; AVX2-NEXT: vpcmpeqq %ymm5, %ymm1, %ymm1
; AVX2-NEXT: vpcmpeqq %ymm4, %ymm0, %ymm0
[X86] truncateVectorCompareWithPACKSS - use PACKSSDW/PACKSSWB instead of just PACKSSWB. By using the widest type possible for PACKSS truncation we have a better chance of being able to peek through bitcasts and improves other combines driven by ComputeNumSignBits. llvm-svn: 316448
2017-10-24 23:38:16 +08:00
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
[X86][SSE] truncateVectorWithPACK - Use src type instead of dst to select between PACK*SDW/PACK*SWB Try to keep PACK*SDW/PACK*SWB as wide as possible, this helps ComputeNumSignBits as it can only peek through bitcasts to wider types, pre-AVX2 codegen was already doing this as it could peek through bitcasts/subvectors more easily than AVX2 could through shuffles. This shouldn't affect existing results as calls to truncateVectorWithPACK ensure we have enough sign bits to pack to the same value, but it should make it possible to use truncateVectorWithPACK chains to perform saturation in combineTruncateWithSat with a future patch. llvm-svn: 325149
2018-02-15 02:23:58 +08:00
; AVX2-NEXT: vpackssdw %ymm2, %ymm0, %ymm0
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand {{[0-9]+}}(%rsp), %xmm0, %xmm1
; AVX2-NEXT: vpandn {{[0-9]+}}(%rsp), %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-LABEL: vselect_packss_v16i64:
[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
; AVX512NOBW: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512NOBW-NEXT: vpcmpeqq %zmm2, %zmm0, %k0
; AVX512NOBW-NEXT: vpcmpeqq %zmm3, %zmm1, %k1
; AVX512NOBW-NEXT: kunpckbw %k0, %k1, %k1
; AVX512NOBW-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512NOBW-NEXT: vpmovdb %zmm0, %xmm0
; AVX512NOBW-NEXT: vpblendvb %xmm0, %xmm4, %xmm5, %xmm0
; AVX512NOBW-NEXT: vzeroupper
; AVX512NOBW-NEXT: retq
;
; AVX512BWNOVL-LABEL: vselect_packss_v16i64:
[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
; AVX512BWNOVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWNOVL-NEXT: vpcmpeqq %zmm2, %zmm0, %k0
; AVX512BWNOVL-NEXT: vpcmpeqq %zmm3, %zmm1, %k1
; AVX512BWNOVL-NEXT: kunpckbw %k0, %k1, %k0
; AVX512BWNOVL-NEXT: vpmovm2b %k0, %zmm0
; AVX512BWNOVL-NEXT: vpblendvb %xmm0, %xmm4, %xmm5, %xmm0
; AVX512BWNOVL-NEXT: vzeroupper
; AVX512BWNOVL-NEXT: retq
;
; AVX512BWVL-LABEL: vselect_packss_v16i64:
[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
; AVX512BWVL: # %bb.0:
[X86] Add avx512bw command lines to vselect-packss.ll This shows several places where we fail to use masked move or blendm. llvm-svn: 319063
2017-11-28 02:00:49 +08:00
; AVX512BWVL-NEXT: vpcmpeqq %zmm2, %zmm0, %k0
; AVX512BWVL-NEXT: vpcmpeqq %zmm3, %zmm1, %k1
; AVX512BWVL-NEXT: kunpckbw %k0, %k1, %k0
; AVX512BWVL-NEXT: vpmovm2b %k0, %xmm0
; AVX512BWVL-NEXT: vpblendvb %xmm0, %xmm4, %xmm5, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
[X86][SSE] Add further test cases showing failure to compute sign bits through PACKSS Suggested in D37680 Note: had to drop AVX512VL tests as there is an infinite loop in the new tests that needs further investigation (not relevant to D37680). llvm-svn: 312910
2017-09-11 20:18:43 +08:00
%1 = icmp eq <16 x i64> %a0, %a1
%2 = sext <16 x i1> %1 to <16 x i8>
%3 = and <16 x i8> %2, %a2
%4 = xor <16 x i8> %2, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%5 = and <16 x i8> %4, %a3
%6 = or <16 x i8> %3, %5
ret <16 x i8> %6
}
;
; PACKSS case
;
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
define <16 x i8> @vselect_packss(<16 x i16> %a0, <16 x i16> %a1, <16 x i8> %a2, <16 x i8> %a3) {
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE2-LABEL: vselect_packss:
[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
; SSE2: # %bb.0:
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE2-NEXT: pcmpeqw %xmm3, %xmm1
; SSE2-NEXT: pcmpeqw %xmm2, %xmm0
; SSE2-NEXT: packsswb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm5, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE42-LABEL: vselect_packss:
[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
; SSE42: # %bb.0:
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; SSE42-NEXT: pcmpeqw %xmm3, %xmm1
; SSE42-NEXT: pcmpeqw %xmm2, %xmm0
; SSE42-NEXT: packsswb %xmm1, %xmm0
; SSE42-NEXT: pblendvb %xmm0, %xmm4, %xmm5
; SSE42-NEXT: movdqa %xmm5, %xmm0
; SSE42-NEXT: retq
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
;
; AVX1-LABEL: vselect_packss:
[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
; AVX1: # %bb.0:
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT: vpcmpeqw %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm0
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; AVX1-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: vselect_packss:
[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
; AVX2: # %bb.0:
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
; AVX2-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode Helps improve combineLogicBlendIntoPBLENDV support by allowing us to peek into through PACKSS truncations of vector comparison results. Differential Revision: https://reviews.llvm.org/D37680 llvm-svn: 312916
2017-09-11 22:03:47 +08:00
; AVX2-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
[X86] Add a DAG combine to combine (sext (setcc)) with VLX Normally target independent DAG combine would do this combine based on getSetCCResultType, but with VLX getSetCCResultType returns a vXi1 type preventing the DAG combining from kicking in. But doing this combine can allow us to remove the explicit sign extend that would otherwise be emitted. This patch adds a target specific DAG combine to combine the sext+setcc when the result type is the same size as the input to the setcc. I've restricted this to FP compares and things that can be represented with PCMPEQ and PCMPGT since we don't have full integer compare support on the older ISAs. Differential Revision: https://reviews.llvm.org/D41850 llvm-svn: 322101
2018-01-10 02:14:22 +08:00
; AVX512-LABEL: vselect_packss:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vpblendvb %xmm0, %xmm2, %xmm3, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
[X86][SSE] Add test showing failure to compute sign bits through PACKSS Prevents combineLogicBlendIntoPBLENDV from merging to PBLENDV llvm-svn: 312906
2017-09-11 18:50:03 +08:00
%1 = icmp eq <16 x i16> %a0, %a1
%2 = sext <16 x i1> %1 to <16 x i16>
%3 = shufflevector <16 x i16> %2, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%4 = shufflevector <16 x i16> %2, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%5 = tail call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %3, <8 x i16> %4)
%6 = and <16 x i8> %5, %a2
%7 = xor <16 x i8> %5, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%8 = and <16 x i8> %7, %a3
%9 = or <16 x i8> %6, %8
ret <16 x i8> %9
}
declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>)