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-trunc.ll

2084 lines
79 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][SSE] Drop unnecessary -mcpu argument from trunc tests cpu/triple duplication llvm-svn: 286104
2016-11-07 21:28:20 +08:00
; 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=+ssse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST
[X86][SSE] Drop unnecessary -mcpu argument from trunc tests cpu/triple duplication llvm-svn: 286104
2016-11-07 21:28:20 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BWVL
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i32> @trunc8i64_8i32(<8 x i64> %a) {
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-LABEL: trunc8i64_8i32:
[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
; SSE: # %bb.0: # %entry
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-LABEL: trunc8i64_8i32:
[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: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc8i64_8i32:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-LABEL: trunc8i64_8i32:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
entry:
%0 = trunc <8 x i64> %a to <8 x i32>
ret <8 x i32> %0
}
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
define <8 x i32> @trunc8i64_8i32_ashr(<8 x i64> %a) {
[SelectionDAG] Add initial implementation of TargetLowering::SimplifyDemandedVectorElts This is mainly a move of simplifyShuffleOperands from DAGCombiner::visitVECTOR_SHUFFLE to create a more general purpose TargetLowering::SimplifyDemandedVectorElts implementation. Further features can be moved/added in future patches. Differential Revision: https://reviews.llvm.org/D42896 llvm-svn: 325232
2018-02-15 20:14:15 +08:00
; SSE-LABEL: trunc8i64_8i32_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc8i64_8i32_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
[SelectionDAG] Add initial implementation of TargetLowering::SimplifyDemandedVectorElts This is mainly a move of simplifyShuffleOperands from DAGCombiner::visitVECTOR_SHUFFLE to create a more general purpose TargetLowering::SimplifyDemandedVectorElts implementation. Further features can be moved/added in future patches. Differential Revision: https://reviews.llvm.org/D42896 llvm-svn: 325232
2018-02-15 20:14:15 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,3],xmm3[1,3]
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc8i64_8i32_ashr:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[1,3,2,3,5,7,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[1,3,2,3,5,7,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32_ashr:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [1,3,5,7,5,7,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX512-LABEL: trunc8i64_8i32_ashr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsraq $32, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
entry:
%0 = ashr <8 x i64> %a, <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
%1 = trunc <8 x i64> %0 to <8 x i32>
ret <8 x i32> %1
}
define <8 x i32> @trunc8i64_8i32_lshr(<8 x i64> %a) {
; SSE-LABEL: trunc8i64_8i32_lshr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Allow float domain crossing if we are merging 2 or more shuffles and the root started as a float domain shuffle llvm-svn: 325349
2018-02-16 22:57:25 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i32_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[X86][SSE] Allow float domain crossing if we are merging 2 or more shuffles and the root started as a float domain shuffle llvm-svn: 325349
2018-02-16 22:57:25 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,3],xmm3[1,3]
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc8i64_8i32_lshr:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpsrlq $32, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32_lshr:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vpsrlq $32, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX512-LABEL: trunc8i64_8i32_lshr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsrlq $32, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
entry:
%0 = lshr <8 x i64> %a, <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
%1 = trunc <8 x i64> %0 to <8 x i32>
ret <8 x i32> %1
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i16> @trunc8i64_8i16(<8 x i64> %a) {
; SSE2-LABEL: trunc8i64_8i16:
[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: # %entry
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i64_8i16:
[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
; SSSE3: # %bb.0: # %entry
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSSE3-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i64_8i16:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i16:
[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: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc8i64_8i16:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i16:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-LABEL: trunc8i64_8i16:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
entry:
%0 = trunc <8 x i64> %a to <8 x i16>
ret <8 x i16> %0
}
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
define void @trunc8i64_8i8(<8 x i64> %a) {
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; SSE2-LABEL: trunc8i64_8i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movq %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i64_8i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: pand %xmm4, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: pand %xmm4, %xmm1
; SSSE3-NEXT: pand %xmm4, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: packuswb %xmm0, %xmm0
; SSSE3-NEXT: movq %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i64_8i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE41-NEXT: pand %xmm4, %xmm3
; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pand %xmm4, %xmm1
; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: packuswb %xmm0, %xmm0
; SSE41-NEXT: movq %xmm0, (%rax)
; SSE41-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
; AVX1-LABEL: trunc8i64_8i8:
[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: # %entry
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[X86] Move promotion of vector and/or/xor from legalization to DAG combine Summary: I've noticed that the bitcasts we introduce for these make computeKnownBits and computeNumSignBits not work well in LegalizeVectorOps. LegalizeVectorOps legalizes bottom up while LegalizeDAG legalizes top down. The bottom up strategy for LegalizeVectorOps means operands are legalized before their uses. So we promote and/or/xor before we legalize the operands that use them making computeKnownBits/computeNumSignBits in places like LowerTruncate suboptimal. I looked at changing LegalizeVectorOps to be top down as well, but that was more disruptive and caused some regressions. I also looked at just moving promotion of binops to LegalizeDAG, but that had a few issues one around matching AND,ANDN,OR into VSELECT because I had to create ANDN as vXi64, but the other nodes hadn't legalized yet, I didn't look too hard at fixing that. This patch seems to produce better results overall than my other attempts. We now form broadcasts of constants better in some cases. For at least some of them the AND was being introduced in LegalizeDAG, promoted to vXi64, and the BUILD_VECTOR was also legalized there. I think we got bad ordering of that. Now the promotion is out of the legalizer so we handle this better. In the longer term I think we really should evaluate whether we should be doing this promotion at all. It's really there to reduce isel pattern count, but I'm wondering if we'd be better served just eating the pattern cost or doing C++ based isel for vector and/or/xor in X86ISelDAGToDAG. The masked and/or/xor will definitely be difficult in patterns if a bitcast gets between the vselect and the and/or/xor node. That becomes a lot of permutations to cover. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D53107 llvm-svn: 344487
2018-10-15 09:51:58 +08:00
; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm3 = mem[0,0]
; AVX1-NEXT: vandpd %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandpd %xmm3, %xmm1, %xmm1
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[X86] Move promotion of vector and/or/xor from legalization to DAG combine Summary: I've noticed that the bitcasts we introduce for these make computeKnownBits and computeNumSignBits not work well in LegalizeVectorOps. LegalizeVectorOps legalizes bottom up while LegalizeDAG legalizes top down. The bottom up strategy for LegalizeVectorOps means operands are legalized before their uses. So we promote and/or/xor before we legalize the operands that use them making computeKnownBits/computeNumSignBits in places like LowerTruncate suboptimal. I looked at changing LegalizeVectorOps to be top down as well, but that was more disruptive and caused some regressions. I also looked at just moving promotion of binops to LegalizeDAG, but that had a few issues one around matching AND,ANDN,OR into VSELECT because I had to create ANDN as vXi64, but the other nodes hadn't legalized yet, I didn't look too hard at fixing that. This patch seems to produce better results overall than my other attempts. We now form broadcasts of constants better in some cases. For at least some of them the AND was being introduced in LegalizeDAG, promoted to vXi64, and the BUILD_VECTOR was also legalized there. I think we got bad ordering of that. Now the promotion is out of the legalizer so we handle this better. In the longer term I think we really should evaluate whether we should be doing this promotion at all. It's really there to reduce isel pattern count, but I'm wondering if we'd be better served just eating the pattern cost or doing C++ based isel for vector and/or/xor in X86ISelDAGToDAG. The masked and/or/xor will definitely be difficult in patterns if a bitcast gets between the vselect and the and/or/xor node. That becomes a lot of permutations to cover. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D53107 llvm-svn: 344487
2018-10-15 09:51:58 +08:00
; AVX1-NEXT: vandpd %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandpd %xmm3, %xmm0, %xmm0
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; AVX1-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc8i64_8i8:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-SLOW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-SLOW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-SLOW-NEXT: vmovq %xmm0, (%rax)
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i8:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-FAST-NEXT: vmovq %xmm0, (%rax)
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-LABEL: trunc8i64_8i8:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: vpmovqb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
entry:
%0 = trunc <8 x i64> %a to <8 x i8>
store <8 x i8> %0, <8 x i8>* undef, align 4
ret void
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i16> @trunc8i32_8i16(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i16:
[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: # %entry
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i16:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i16:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16:
[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: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16:
[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: # %entry
[X86] In LowerTRUNCATE, create an ISD::VECTOR_SHUFFLE instead of explicitly creating a PSHUFB. This will be lowered by regular shuffle lowering to a PSHUFB later. Similar was already done for several other shuffles in this function. The test changes are because the old code used explicity zeroing for elements that could have been undef. While I was here I also changed other shuffle vectors in the same function to use the same input twice instead of creating UNDEF nodes. getVectorShuffle can create the UNDEF for us. llvm-svn: 294130
2017-02-06 02:33:14 +08:00
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc8i32_8i16:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
entry:
%0 = trunc <8 x i32> %a to <8 x i16>
ret <8 x i16> %0
}
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
[X86][SSE] Add support for lowering v8i16 binary shuffles to PACKSS/PACKUS Missed in D38472 llvm-svn: 314916
2017-10-05 01:31:28 +08:00
; SSE-LABEL: trunc8i32_8i16_ashr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Add support for lowering v8i16 binary shuffles to PACKSS/PACKUS Missed in D38472 llvm-svn: 314916
2017-10-05 01:31:28 +08:00
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc8i32_8i16_ashr:
[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: # %entry
[X86][SSE] Improve shuffling combining with horizontal operations Recognise cases when we can merge the shuffles with their horizontal (HADD/HSUB/PACK) instruction inputs. Replaces an older implementation which performed some of this during lowering, expanding an existing target shuffle combine stage instead. Differential Revision: https://reviews.llvm.org/D38506 llvm-svn: 315150
2017-10-07 20:42:23 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrad $16, %xmm1, %xmm1
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm0
[X86][SSE] Improve shuffling combining with horizontal operations Recognise cases when we can merge the shuffles with their horizontal (HADD/HSUB/PACK) instruction inputs. Replaces an older implementation which performed some of this during lowering, expanding an existing target shuffle combine stage instead. Differential Revision: https://reviews.llvm.org/D38506 llvm-svn: 315150
2017-10-07 20:42:23 +08:00
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i16_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16_ashr:
[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
; AVX512VL: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BWVL-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = ashr <8 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <8 x i32> %0 to <8 x i16>
ret <8 x i16> %1
}
define <8 x i16> @trunc8i32_8i16_lshr(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE2-NEXT: psrld $16, %xmm0
; SSE2-NEXT: psrld $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i16_lshr:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,10,11,14,15,14,15,255,255]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i16_lshr:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; SSE41-NEXT: psrld $16, %xmm1
[X86][SSE] Add support for lowering v8i16 binary shuffles to PACKSS/PACKUS Missed in D38472 llvm-svn: 314916
2017-10-05 01:31:28 +08:00
; SSE41-NEXT: psrld $16, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
[X86][SSE] Add PACKUS support to LowerTruncate Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317128
2017-11-02 05:52:29 +08:00
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16_lshr:
[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
; AVX512VL: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BWVL-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = lshr <8 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <8 x i32> %0 to <8 x i16>
ret <8 x i16> %1
}
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
define void @trunc8i32_8i8(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i8:
[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: # %entry
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movq %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i8:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: movq %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i8:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: movq %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i8:
[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: # %entry
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i8:
[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: # %entry
[X86] In LowerTRUNCATE, create an ISD::VECTOR_SHUFFLE instead of explicitly creating a PSHUFB. This will be lowered by regular shuffle lowering to a PSHUFB later. Similar was already done for several other shuffles in this function. The test changes are because the old code used explicity zeroing for elements that could have been undef. While I was here I also changed other shuffle vectors in the same function to use the same input twice instead of creating UNDEF nodes. getVectorShuffle can create the UNDEF for us. llvm-svn: 294130
2017-02-06 02:33:14 +08:00
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc8i32_8i8:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vmovq %xmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i8:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovdb %ymm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i8:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vmovq %xmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i8:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovdb %ymm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
entry:
%0 = trunc <8 x i32> %a to <8 x i8>
store <8 x i8> %0, <8 x i8>* undef, align 4
ret void
}
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
define void @trunc16i32_16i16(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i16:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm2
; SSE2-NEXT: psrad $16, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i16:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSSE3-NEXT: pslld $16, %xmm1
; SSSE3-NEXT: psrad $16, %xmm1
; SSSE3-NEXT: pslld $16, %xmm0
; SSSE3-NEXT: psrad $16, %xmm0
; SSSE3-NEXT: packssdw %xmm1, %xmm0
; SSSE3-NEXT: pslld $16, %xmm3
; SSSE3-NEXT: psrad $16, %xmm3
; SSSE3-NEXT: pslld $16, %xmm2
; SSSE3-NEXT: psrad $16, %xmm2
; SSSE3-NEXT: packssdw %xmm3, %xmm2
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i16:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1],xmm1[2],xmm4[3],xmm1[4],xmm4[5],xmm1[6],xmm4[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1],xmm0[2],xmm4[3],xmm0[4],xmm4[5],xmm0[6],xmm4[7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1],xmm3[2],xmm4[3],xmm3[4],xmm4[5],xmm3[6],xmm4[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1],xmm2[2],xmm4[3],xmm2[4],xmm4[5],xmm2[6],xmm4[7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i16:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1],xmm2[2],xmm3[3],xmm2[4],xmm3[5],xmm2[6],xmm3[7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1],xmm1[2],xmm3[3],xmm1[4],xmm3[5],xmm1[6],xmm3[7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1],xmm2[2],xmm3[3],xmm2[4],xmm3[5],xmm2[6],xmm3[7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1],xmm0[2],xmm3[3],xmm0[4],xmm3[5],xmm0[6],xmm3[7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovups %ymm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i16:
[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: # %entry
[X86] In LowerTRUNCATE, create an ISD::VECTOR_SHUFFLE instead of explicitly creating a PSHUFB. This will be lowered by regular shuffle lowering to a PSHUFB later. Similar was already done for several other shuffles in this function. The test changes are because the old code used explicity zeroing for elements that could have been undef. While I was here I also changed other shuffle vectors in the same function to use the same input twice instead of creating UNDEF nodes. getVectorShuffle can create the UNDEF for us. llvm-svn: 294130
2017-02-06 02:33:14 +08:00
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: retq
entry:
%0 = trunc <16 x i32> %a to <16 x i16>
store <16 x i16> %0, <16 x i16>* undef, align 4
ret void
}
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
define void @trunc16i32_16i16_ashr(<16 x i32> %a) {
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; SSE-LABEL: trunc16i32_16i16_ashr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; SSE-NEXT: psrad $16, %xmm3
; SSE-NEXT: psrad $16, %xmm2
; SSE-NEXT: packssdw %xmm3, %xmm2
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm2, (%rax)
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc16i32_16i16_ashr:
[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: # %entry
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm2, %xmm2
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm0
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm2, %xmm2
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsrad $16, %xmm1, %xmm1
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovups %ymm0, (%rax)
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-LABEL: trunc16i32_16i16_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vpsrad $16, %ymm1, %ymm1
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16_ashr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsrld $16, %zmm0, %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = ashr <16 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <16 x i32> %0 to <16 x i16>
store <16 x i16> %1, <16 x i16>* undef, align 4
ret void
}
define void @trunc16i32_16i16_lshr(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE2-NEXT: psrld $16, %xmm2
; SSE2-NEXT: psrld $16, %xmm3
; SSE2-NEXT: psrld $16, %xmm0
; SSE2-NEXT: psrld $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm2
; SSE2-NEXT: psrad $16, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i16_lshr:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSSE3-NEXT: psrld $16, %xmm2
; SSSE3-NEXT: psrld $16, %xmm3
; SSSE3-NEXT: psrld $16, %xmm0
; SSSE3-NEXT: psrld $16, %xmm1
; SSSE3-NEXT: pslld $16, %xmm1
; SSSE3-NEXT: psrad $16, %xmm1
; SSSE3-NEXT: pslld $16, %xmm0
; SSSE3-NEXT: psrad $16, %xmm0
; SSSE3-NEXT: packssdw %xmm1, %xmm0
; SSSE3-NEXT: pslld $16, %xmm3
; SSSE3-NEXT: psrad $16, %xmm3
; SSSE3-NEXT: pslld $16, %xmm2
; SSSE3-NEXT: psrad $16, %xmm2
; SSSE3-NEXT: packssdw %xmm3, %xmm2
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i16_lshr:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE41-NEXT: psrld $16, %xmm3
; SSE41-NEXT: psrld $16, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: psrld $16, %xmm1
; SSE41-NEXT: psrld $16, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i16_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovups %ymm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i16_lshr:
[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: # %entry
[X86][SSE] Add PACKUS support to LowerTruncate Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317128
2017-11-02 05:52:29 +08:00
; AVX2-NEXT: vpsrld $16, %ymm1, %ymm1
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16_lshr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsrld $16, %zmm0, %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = lshr <16 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <16 x i32> %0 to <16 x i16>
store <16 x i16> %1, <16 x i16>* undef, align 4
ret void
}
define void @trunc16i32_16i8(<16 x i32> %a) {
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; SSE2-LABEL: trunc16i32_16i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: pand %xmm4, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: pand %xmm4, %xmm1
; SSSE3-NEXT: pand %xmm4, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE41-NEXT: pand %xmm4, %xmm3
; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pand %xmm4, %xmm1
; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packuswb %xmm2, %xmm0
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc16i32_16i8:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[X86] Move promotion of vector and/or/xor from legalization to DAG combine Summary: I've noticed that the bitcasts we introduce for these make computeKnownBits and computeNumSignBits not work well in LegalizeVectorOps. LegalizeVectorOps legalizes bottom up while LegalizeDAG legalizes top down. The bottom up strategy for LegalizeVectorOps means operands are legalized before their uses. So we promote and/or/xor before we legalize the operands that use them making computeKnownBits/computeNumSignBits in places like LowerTruncate suboptimal. I looked at changing LegalizeVectorOps to be top down as well, but that was more disruptive and caused some regressions. I also looked at just moving promotion of binops to LegalizeDAG, but that had a few issues one around matching AND,ANDN,OR into VSELECT because I had to create ANDN as vXi64, but the other nodes hadn't legalized yet, I didn't look too hard at fixing that. This patch seems to produce better results overall than my other attempts. We now form broadcasts of constants better in some cases. For at least some of them the AND was being introduced in LegalizeDAG, promoted to vXi64, and the BUILD_VECTOR was also legalized there. I think we got bad ordering of that. Now the promotion is out of the legalizer so we handle this better. In the longer term I think we really should evaluate whether we should be doing this promotion at all. It's really there to reduce isel pattern count, but I'm wondering if we'd be better served just eating the pattern cost or doing C++ based isel for vector and/or/xor in X86ISelDAGToDAG. The masked and/or/xor will definitely be difficult in patterns if a bitcast gets between the vselect and the and/or/xor node. That becomes a lot of permutations to cover. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D53107 llvm-svn: 344487
2018-10-15 09:51:58 +08:00
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm1, %xmm1
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[X86] Move promotion of vector and/or/xor from legalization to DAG combine Summary: I've noticed that the bitcasts we introduce for these make computeKnownBits and computeNumSignBits not work well in LegalizeVectorOps. LegalizeVectorOps legalizes bottom up while LegalizeDAG legalizes top down. The bottom up strategy for LegalizeVectorOps means operands are legalized before their uses. So we promote and/or/xor before we legalize the operands that use them making computeKnownBits/computeNumSignBits in places like LowerTruncate suboptimal. I looked at changing LegalizeVectorOps to be top down as well, but that was more disruptive and caused some regressions. I also looked at just moving promotion of binops to LegalizeDAG, but that had a few issues one around matching AND,ANDN,OR into VSELECT because I had to create ANDN as vXi64, but the other nodes hadn't legalized yet, I didn't look too hard at fixing that. This patch seems to produce better results overall than my other attempts. We now form broadcasts of constants better in some cases. For at least some of them the AND was being introduced in LegalizeDAG, promoted to vXi64, and the BUILD_VECTOR was also legalized there. I think we got bad ordering of that. Now the promotion is out of the legalizer so we handle this better. In the longer term I think we really should evaluate whether we should be doing this promotion at all. It's really there to reduce isel pattern count, but I'm wondering if we'd be better served just eating the pattern cost or doing C++ based isel for vector and/or/xor in X86ISelDAGToDAG. The masked and/or/xor will definitely be difficult in patterns if a bitcast gets between the vselect and the and/or/xor node. That becomes a lot of permutations to cover. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D53107 llvm-svn: 344487
2018-10-15 09:51:58 +08:00
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm0, %xmm0
[X86][SSE] Simplify combineVectorTruncationWithPACKUS to reduce code duplication Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code. This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting). I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking. llvm-svn: 334289
2018-06-08 21:59:11 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-LABEL: trunc16i32_16i8:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: retq
[X86][SSE] Added extra vector truncation tests Baseline comparison to D14588 llvm-svn: 253132
2015-11-14 23:23:59 +08:00
entry:
%0 = trunc <16 x i32> %a to <16 x i8>
store <16 x i8> %0, <16 x i8>* undef, align 4
ret void
}
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
define void @trunc16i32_16i8_ashr(<16 x i32> %a) {
; SSE-LABEL: trunc16i32_16i8_ashr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE-NEXT: psrad $24, %xmm1
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; SSE-NEXT: psrad $24, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE-NEXT: psrad $24, %xmm3
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; SSE-NEXT: psrad $24, %xmm2
; SSE-NEXT: packssdw %xmm3, %xmm2
; SSE-NEXT: packsswb %xmm2, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i8_ashr:
[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: # %entry
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm2, %xmm2
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsrad $24, %xmm0, %xmm0
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm2, %xmm2
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsrad $24, %xmm1, %xmm1
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vpsrad $24, %ymm1, %ymm1
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX2-NEXT: vpsrad $24, %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] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +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] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i8_ashr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsrld $24, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = ashr <16 x i32> %a, <i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
%1 = trunc <16 x i32> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i32_16i8_lshr(<16 x i32> %a) {
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSE2-LABEL: trunc16i32_16i8_lshr:
[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: # %entry
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSE2-NEXT: psrld $24, %xmm1
; SSE2-NEXT: psrld $24, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: psrld $24, %xmm3
; SSE2-NEXT: psrld $24, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i8_lshr:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSSE3-NEXT: psrld $24, %xmm1
; SSSE3-NEXT: psrld $24, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: psrld $24, %xmm3
; SSSE3-NEXT: psrld $24, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i8_lshr:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSE41-NEXT: psrld $24, %xmm1
; SSE41-NEXT: psrld $24, %xmm0
[X86][SSE] Consistently prefer lowering to PACKUS over PACKSS We have some combines/lowerings that attempt to use PACKSS-then-PACKUS and others that use PACKUS-then-PACKSS. PACKUS is much easier to combine with if we know the upper bits are zero as ComputeKnownBits can easily see through BITCASTs etc. especially now that rL333995 and rL334007 have landed. It also effectively works at byte level which further simplifies shuffle combines. The only (minor) annoyances are that ComputeKnownBits can sometimes take longer as it doesn't fail as quickly as ComputeNumSignBits (but I'm not seeing any actual regressions in tests) and PACKUSDW only became available after SSE41 so we have more codegen diffs between targets. llvm-svn: 334276
2018-06-08 18:29:00 +08:00
; SSE41-NEXT: packusdw %xmm1, %xmm0
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSE41-NEXT: psrld $24, %xmm3
; SSE41-NEXT: psrld $24, %xmm2
[X86][SSE] Consistently prefer lowering to PACKUS over PACKSS We have some combines/lowerings that attempt to use PACKSS-then-PACKUS and others that use PACKUS-then-PACKSS. PACKUS is much easier to combine with if we know the upper bits are zero as ComputeKnownBits can easily see through BITCASTs etc. especially now that rL333995 and rL334007 have landed. It also effectively works at byte level which further simplifies shuffle combines. The only (minor) annoyances are that ComputeKnownBits can sometimes take longer as it doesn't fail as quickly as ComputeNumSignBits (but I'm not seeing any actual regressions in tests) and PACKUSDW only became available after SSE41 so we have more codegen diffs between targets. llvm-svn: 334276
2018-06-08 18:29:00 +08:00
; SSE41-NEXT: packusdw %xmm3, %xmm2
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; SSE41-NEXT: packuswb %xmm2, %xmm0
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc16i32_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm0, %xmm0
[X86][SSE] Consistently prefer lowering to PACKUS over PACKSS We have some combines/lowerings that attempt to use PACKSS-then-PACKUS and others that use PACKUS-then-PACKSS. PACKUS is much easier to combine with if we know the upper bits are zero as ComputeKnownBits can easily see through BITCASTs etc. especially now that rL333995 and rL334007 have landed. It also effectively works at byte level which further simplifies shuffle combines. The only (minor) annoyances are that ComputeKnownBits can sometimes take longer as it doesn't fail as quickly as ComputeNumSignBits (but I'm not seeing any actual regressions in tests) and PACKUSDW only became available after SSE41 so we have more codegen diffs between targets. llvm-svn: 334276
2018-06-08 18:29:00 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm1, %xmm1
[X86][SSE] Consistently prefer lowering to PACKUS over PACKSS We have some combines/lowerings that attempt to use PACKSS-then-PACKUS and others that use PACKUS-then-PACKSS. PACKUS is much easier to combine with if we know the upper bits are zero as ComputeKnownBits can easily see through BITCASTs etc. especially now that rL333995 and rL334007 have landed. It also effectively works at byte level which further simplifies shuffle combines. The only (minor) annoyances are that ComputeKnownBits can sometimes take longer as it doesn't fail as quickly as ComputeNumSignBits (but I'm not seeing any actual regressions in tests) and PACKUSDW only became available after SSE41 so we have more codegen diffs between targets. llvm-svn: 334276
2018-06-08 18:29:00 +08:00
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8_lshr:
[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: # %entry
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; AVX2-NEXT: vpsrld $24, %ymm1, %ymm1
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; AVX2-NEXT: vpsrld $24, %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: vpackusdw %ymm1, %ymm0, %ymm0
[X86][SSE] Add PACKUS support to combineVectorTruncation Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317315
2017-11-03 19:33:48 +08:00
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i8_lshr:
[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
; AVX512: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512-NEXT: vpsrld $24, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = lshr <16 x i32> %a, <i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
%1 = trunc <16 x i32> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
;PR25684
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
define void @trunc16i16_16i8(<16 x i16> %a) {
; SSE2-LABEL: trunc16i16_16i8:
[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: # %entry
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i16_16i8:
[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
; SSSE3: # %bb.0: # %entry
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i16_16i8:
[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
; SSE41: # %bb.0: # %entry
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i16_16i8:
[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: # %entry
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8:
[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: # %entry
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8:
[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: # %entry
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512F-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX512F-NEXT: retq
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-LABEL: trunc16i16_16i8:
[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
; AVX512VL: # %bb.0: # %entry
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512VL-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX512BW-LABEL: trunc16i16_16i8:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
; AVX512BW-NEXT: retq
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
;
; AVX512BWVL-LABEL: trunc16i16_16i8:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
entry:
%0 = trunc <16 x i16> %a to <16 x i8>
store <16 x i8> %0, <16 x i8>* undef, align 4
ret void
}
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; SSE-LABEL: trunc16i16_16i8_ashr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; SSE-NEXT: psraw $8, %xmm1
; SSE-NEXT: psraw $8, %xmm0
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc16i16_16i8_ashr:
[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: # %entry
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsraw $8, %xmm1, %xmm1
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vpsraw $8, %xmm0, %xmm0
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vpsraw $8, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
[X86][SSE] Truncate with PACKSS any input with sufficient sign-bits So far we've only been using PACKSS truncations with 'all-bits or zero-bits' patterns (vector comparison results etc.). When really we can safely use it for any case as long as the number of sign bits reach down to the last 16-bits (or 8-bits if we're truncating to bytes). The next steps after this is add the equivalent support for PACKUS and to support packing to sub-128 bit vectors for truncating stores etc. Differential Revision: https://reviews.llvm.org/D39476 llvm-svn: 317086
2017-11-01 19:47:44 +08:00
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vpsraw $8, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512F-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc16i16_16i8_ashr:
[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
; AVX512VL: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vpsraw $8, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512VL-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc16i16_16i8_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vpsraw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc16i16_16i8_ashr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BWVL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = ashr <16 x i16> %a, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%1 = trunc <16 x i16> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i16_16i8_lshr(<16 x i16> %a) {
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; SSE-LABEL: trunc16i16_16i8_lshr:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; SSE-NEXT: psrlw $8, %xmm1
; SSE-NEXT: psrlw $8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
;
; AVX1-LABEL: trunc16i16_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
[SelectionDAG] Add support for INSERT_SUBVECTOR to computeKnownBits llvm-svn: 316847
2017-10-29 06:10:40 +08:00
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512F-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc16i16_16i8_lshr:
[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
; AVX512VL: # %bb.0: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512VL-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc16i16_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BW-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc16i16_16i8_lshr:
[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: # %entry
[X86][SSE] Add vector truncation cases inspired by PR34773 We should be using PACKSS/PACKUS more aggressively when we know the state of the upper bits llvm-svn: 314597
2017-10-01 00:14:59 +08:00
; AVX512BWVL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = lshr <16 x i16> %a, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%1 = trunc <16 x i16> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
define void @trunc32i16_32i8(<32 x i16> %a) {
; SSE2-LABEL: trunc32i16_32i8:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc32i16_32i8:
[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
; SSSE3: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm4, %xmm1
; SSSE3-NEXT: pshufb %xmm4, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: pshufb %xmm4, %xmm3
; SSSE3-NEXT: pshufb %xmm4, %xmm2
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc32i16_32i8:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm4, %xmm1
; SSE41-NEXT: pshufb %xmm4, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: pshufb %xmm4, %xmm3
; SSE41-NEXT: pshufb %xmm4, %xmm2
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc32i16_32i8:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovups %ymm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc32i16_32i8:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc32i16_32i8:
[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: # %entry
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512F-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
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512F-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
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: vmovdqu %ymm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512F-NEXT: retq
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-LABEL: trunc32i16_32i8:
[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
; AVX512VL: # %bb.0: # %entry
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512VL-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
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512VL-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
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovdb %zmm1, %xmm1
[AVX-512] Teach EVEX to VEX conversion pass to handle VINSERT and VEXTRACT instructions. llvm-svn: 290869
2017-01-03 13:46:18 +08:00
; AVX512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
This is a large patch for X86 AVX-512 of an optimization for reducing code size by encoding EVEX AVX-512 instructions using the shorter VEX encoding when possible. There are cases of AVX-512 instructions that have two possible encodings. This is the case with instructions that use vector registers with low indexes of 0 - 15 and do not use the zmm registers or the mask k registers. The EVEX encoding prefix requires 4 bytes whereas the VEX prefix can take only up to 3 bytes. Consequently, using the VEX encoding for these instructions results in a code size reduction of ~2 bytes even though it is compiled with the AVX-512 features enabled. Reviewers: Craig Topper, Zvi Rackoover, Elena Demikhovsky Differential Revision: https://reviews.llvm.org/D27901 llvm-svn: 290663
2016-12-28 18:12:48 +08:00
; AVX512VL-NEXT: vmovdqu %ymm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512BW-LABEL: trunc32i16_32i8:
[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: # %entry
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512BW-NEXT: vpmovwb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512BW-NEXT: retq
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
;
; AVX512BWVL-LABEL: trunc32i16_32i8:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovwb %zmm0, (%rax)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
entry:
%0 = trunc <32 x i16> %a to <32 x i8>
store <32 x i8> %0, <32 x i8>* undef, align 4
ret void
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i32> @trunc2x4i64_8i32(<4 x i64> %a, <4 x i64> %b) {
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-LABEL: trunc2x4i64_8i32:
[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
; SSE: # %bb.0: # %entry
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
;
; AVX1-LABEL: trunc2x4i64_8i32:
[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: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc2x4i64_8i32:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc2x4i64_8i32:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc2x4i64_8i32:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2x4i64_8i32:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512VL-NEXT: vpmovqd %ymm1, %xmm1
[AVX-512] Teach EVEX to VEX conversion pass to handle VINSERT and VEXTRACT instructions. llvm-svn: 290869
2017-01-03 13:46:18 +08:00
; AVX512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2x4i64_8i32:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2x4i64_8i32:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512BWVL-NEXT: vpmovqd %ymm1, %xmm1
[AVX-512] Teach EVEX to VEX conversion pass to handle VINSERT and VEXTRACT instructions. llvm-svn: 290869
2017-01-03 13:46:18 +08:00
; AVX512BWVL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
entry:
%0 = trunc <4 x i64> %a to <4 x i32>
%1 = trunc <4 x i64> %b to <4 x i32>
%2 = shufflevector <4 x i32> %0, <4 x i32> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i32> %2
}
[X86][SSE] Added dual vector truncation tests. llvm-svn: 228857
2015-02-12 02:14:35 +08:00
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i16> @trunc2x4i64_8i16(<4 x i64> %a, <4 x i64> %b) {
; SSE2-LABEL: trunc2x4i64_8i16:
[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: # %entry
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc2x4i64_8i16:
[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
; SSSE3: # %bb.0: # %entry
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSSE3-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc2x4i64_8i16:
[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
; SSE41: # %bb.0: # %entry
[DAG] Generalize build_vector -> vector_shuffle combine for more than 2 inputs This generalizes the build_vector -> vector_shuffle combine to support any number of inputs. The idea is to create a binary tree of shuffles, where the first layer performs pairwise shuffles of the input vectors placing each input element into the correct lane, and the rest of the tree blends these shuffles together. This doesn't try to be smart and create any sort of "optimal" shuffles. The assumption is that even a "poor" shuffle sequence is better than extracting and inserting the elements one by one. Differential Revision: https://reviews.llvm.org/D24683 llvm-svn: 283480
2016-10-07 02:58:24 +08:00
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; SSE41-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE41-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc2x4i64_8i16:
[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: # %entry
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: trunc2x4i64_8i16:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX2-SLOW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-SLOW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc2x4i64_8i16:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc2x4i64_8i16:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512F-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2x4i64_8i16:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512VL-NEXT: vpmovqd %ymm1, %xmm1
[X86][AVX512] Attempt target shuffle combining to different types instead of early-out We try to prevent shuffle combining to value types that would stop the folding of masked operations, but by just returning early, we were failing to try different shuffle types. The TODOs are all still relevant here to improve codegen but we're lacking test examples. llvm-svn: 321085
2017-12-20 00:54:07 +08:00
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512VL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2x4i64_8i16:
[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: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BW-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2x4i64_8i16:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512BWVL-NEXT: vpmovqd %ymm1, %xmm1
[X86][AVX512] Attempt target shuffle combining to different types instead of early-out We try to prevent shuffle combining to value types that would stop the folding of masked operations, but by just returning early, we were failing to try different shuffle types. The TODOs are all still relevant here to improve codegen but we're lacking test examples. llvm-svn: 321085
2017-12-20 00:54:07 +08:00
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; AVX512BWVL-NEXT: vzeroupper
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
entry:
%0 = trunc <4 x i64> %a to <4 x i16>
%1 = trunc <4 x i64> %b to <4 x i16>
%2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %2
}
[X86][SSE] Added dual vector truncation tests. llvm-svn: 228857
2015-02-12 02:14:35 +08:00
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <4 x i32> @trunc2x2i64_4i32(<2 x i64> %a, <2 x i64> %b) {
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-LABEL: trunc2x2i64_4i32:
[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
; SSE: # %bb.0: # %entry
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
;
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX-LABEL: trunc2x2i64_4i32:
[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
; AVX: # %bb.0: # %entry
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-LABEL: trunc2x2i64_4i32:
[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
; AVX512: # %bb.0: # %entry
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
[X86][SSE] Added AVX512F and additional vector truncate test cases trunc16i16_16i8 is currently commented out due to PR25684 llvm-svn: 281356
2016-09-14 01:34:56 +08:00
; AVX512-NEXT: retq
[X86][SSE] Added dual vector truncation tests. llvm-svn: 228857
2015-02-12 02:14:35 +08:00
entry:
%0 = trunc <2 x i64> %a to <2 x i32>
%1 = trunc <2 x i64> %b to <2 x i32>
%2 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %2
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define i64 @trunc2i64_i64(<2 x i64> %inval) {
; SSE-LABEL: trunc2i64_i64:
[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
; SSE: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSE-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc2i64_i64:
[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
; AVX: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc2i64_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: vmovq %xmm0, %rax
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2i64_i64:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovqd %xmm0, -{{[0-9]+}}(%rsp)
; AVX512VL-NEXT: movq -{{[0-9]+}}(%rsp), %rax
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2i64_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BW-NEXT: vmovq %xmm0, %rax
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2i64_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovqd %xmm0, -{{[0-9]+}}(%rsp)
; AVX512BWVL-NEXT: movq -{{[0-9]+}}(%rsp), %rax
; AVX512BWVL-NEXT: retq
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
entry:
%0 = trunc <2 x i64> %inval to <2 x i32>
%1 = bitcast <2 x i32> %0 to i64
ret i64 %1
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <8 x i16> @trunc2x4i32_8i16(<4 x i32> %a, <4 x i32> %b) {
; SSE2-LABEL: trunc2x4i32_8i16:
[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: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-LABEL: trunc2x4i32_8i16:
[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
; SSSE3: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-LABEL: trunc2x4i32_8i16:
[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
; SSE41: # %bb.0: # %entry
[x86] Delete still more piles of complex code now that we have a good systematic lowering of v8i16. This required a slight strategy shift to prefer unpack lowerings in more places. While this isn't a cut-and-dry win in every case, it is in the overwhelming majority. There are only a few places where the old lowering would probably be a touch faster, and then only by a small margin. In some cases, this is yet another significant improvement. llvm-svn: 229859
2015-02-19 23:21:57 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc2x4i32_8i16:
[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
; AVX: # %bb.0: # %entry
[x86] Delete still more piles of complex code now that we have a good systematic lowering of v8i16. This required a slight strategy shift to prefer unpack lowerings in more places. While this isn't a cut-and-dry win in every case, it is in the overwhelming majority. There are only a few places where the old lowering would probably be a touch faster, and then only by a small margin. In some cases, this is yet another significant improvement. llvm-svn: 229859
2015-02-19 23:21:57 +08:00
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Attempt target shuffle combining to different types instead of early-out We try to prevent shuffle combining to value types that would stop the folding of masked operations, but by just returning early, we were failing to try different shuffle types. The TODOs are all still relevant here to improve codegen but we're lacking test examples. llvm-svn: 321085
2017-12-20 00:54:07 +08:00
; AVX512-LABEL: trunc2x4i32_8i16:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512-NEXT: retq
[X86][SSE] Added dual vector truncation tests. llvm-svn: 228857
2015-02-12 02:14:35 +08:00
entry:
%0 = trunc <4 x i32> %a to <4 x i16>
%1 = trunc <4 x i32> %b to <4 x i16>
%2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %2
}
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define i64 @trunc4i32_i64(<4 x i32> %inval) {
; SSE2-LABEL: trunc4i32_i64:
[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: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSE2-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-LABEL: trunc4i32_i64:
[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
; SSSE3: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSSE3-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-LABEL: trunc4i32_i64:
[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
; SSE41: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSE41-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc4i32_i64:
[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
; AVX: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc4i32_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512F-NEXT: vmovq %xmm0, %rax
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc4i32_i64:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpmovdw %xmm0, -{{[0-9]+}}(%rsp)
; AVX512VL-NEXT: movq -{{[0-9]+}}(%rsp), %rax
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc4i32_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT: vmovq %xmm0, %rax
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc4i32_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovdw %xmm0, -{{[0-9]+}}(%rsp)
; AVX512BWVL-NEXT: movq -{{[0-9]+}}(%rsp), %rax
; AVX512BWVL-NEXT: retq
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
entry:
%0 = trunc <4 x i32> %inval to <4 x i16>
%1 = bitcast <4 x i16> %0 to i64
ret i64 %1
}
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <16 x i8> @trunc2x8i16_16i8(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: trunc2x8i16_16i8:
[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: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-LABEL: trunc2x8i16_16i8:
[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
; SSSE3: # %bb.0: # %entry
[x86] Remove the insanely over-aggressive unpack lowering strategy for v16i8 shuffles, and replace it with new facilities. This uses precise patterns to match exact unpacks, and the new generalized unpack lowering only when we detect a case where we will have to shuffle both inputs anyways and they terminate in exactly a blend. This fixes all of the blend horrors that I uncovered by always lowering blends through the vector shuffle lowering. It also removes *sooooo* much of the crazy instruction sequences required for v16i8 lowering previously. Much cleaner now. The only "meh" aspect is that we sometimes use pshufb+pshufb+unpck when it would be marginally nicer to use pshufb+pshufb+por. However, the difference there is *tiny*. In many cases its a win because we re-use the pshufb mask. In others, we get to avoid the pshufb entirely. I've left a FIXME, but I'm dubious we can really do better than this. I'm actually pretty happy with this lowering now. For SSE2 this exposes some horrors that were really already there. Those will have to fixed by changing a different path through the v16i8 lowering. llvm-svn: 229846
2015-02-19 20:10:37 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-LABEL: trunc2x8i16_16i8:
[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
; SSE41: # %bb.0: # %entry
[x86] Remove the insanely over-aggressive unpack lowering strategy for v16i8 shuffles, and replace it with new facilities. This uses precise patterns to match exact unpacks, and the new generalized unpack lowering only when we detect a case where we will have to shuffle both inputs anyways and they terminate in exactly a blend. This fixes all of the blend horrors that I uncovered by always lowering blends through the vector shuffle lowering. It also removes *sooooo* much of the crazy instruction sequences required for v16i8 lowering previously. Much cleaner now. The only "meh" aspect is that we sometimes use pshufb+pshufb+unpck when it would be marginally nicer to use pshufb+pshufb+por. However, the difference there is *tiny*. In many cases its a win because we re-use the pshufb mask. In others, we get to avoid the pshufb entirely. I've left a FIXME, but I'm dubious we can really do better than this. I'm actually pretty happy with this lowering now. For SSE2 this exposes some horrors that were really already there. Those will have to fixed by changing a different path through the v16i8 lowering. llvm-svn: 229846
2015-02-19 20:10:37 +08:00
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc2x8i16_16i8:
[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
; AVX: # %bb.0: # %entry
[x86] Remove the insanely over-aggressive unpack lowering strategy for v16i8 shuffles, and replace it with new facilities. This uses precise patterns to match exact unpacks, and the new generalized unpack lowering only when we detect a case where we will have to shuffle both inputs anyways and they terminate in exactly a blend. This fixes all of the blend horrors that I uncovered by always lowering blends through the vector shuffle lowering. It also removes *sooooo* much of the crazy instruction sequences required for v16i8 lowering previously. Much cleaner now. The only "meh" aspect is that we sometimes use pshufb+pshufb+unpck when it would be marginally nicer to use pshufb+pshufb+por. However, the difference there is *tiny*. In many cases its a win because we re-use the pshufb mask. In others, we get to avoid the pshufb entirely. I've left a FIXME, but I'm dubious we can really do better than this. I'm actually pretty happy with this lowering now. For SSE2 this exposes some horrors that were really already there. Those will have to fixed by changing a different path through the v16i8 lowering. llvm-svn: 229846
2015-02-19 20:10:37 +08:00
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[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
; AVX512-LABEL: trunc2x8i16_16i8:
[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
; AVX512: # %bb.0: # %entry
[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
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512-NEXT: retq
[X86][SSE] Added dual vector truncation tests. llvm-svn: 228857
2015-02-12 02:14:35 +08:00
entry:
%0 = trunc <8 x i16> %a to <8 x i8>
%1 = trunc <8 x i16> %b to <8 x i8>
%2 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %2
}
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define i64 @trunc8i16_i64(<8 x i16> %inval) {
; SSE2-LABEL: trunc8i16_i64:
[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: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSE2-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE2-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSSE3-LABEL: trunc8i16_i64:
[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
; SSSE3: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSSE3-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSSE3-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; SSE41-LABEL: trunc8i16_i64:
[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
; SSE41: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
[X86][SSE2] Fix asm string for movq (Move Quadword) instruction. Replace "mov{d|q}" with "movq". Differential Revision: https://reviews.llvm.org/D32220 llvm-svn: 301386
2017-04-26 15:08:44 +08:00
; SSE41-NEXT: movq %xmm0, %rax
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; SSE41-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc8i16_i64:
[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
; AVX: # %bb.0: # %entry
[x86] Clean up a few test cases with the update script. NFC llvm-svn: 229349
2015-02-16 09:39:50 +08:00
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-LABEL: trunc8i16_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vmovq %xmm0, %rax
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i16_i64:
[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
; AVX512VL: # %bb.0: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vmovq %xmm0, %rax
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i16_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vmovq %xmm0, %rax
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i16_i64:
[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: # %entry
[X86][AVX512] Add AVX512VL/AVX512BWVL vector truncation tests llvm-svn: 286105
2016-11-07 21:34:29 +08:00
; AVX512BWVL-NEXT: vpmovwb %xmm0, -{{[0-9]+}}(%rsp)
; AVX512BWVL-NEXT: movq -{{[0-9]+}}(%rsp), %rax
; AVX512BWVL-NEXT: retq
[X86][SSE] Added vector integer truncation tests - based off pr15524 llvm-svn: 225137
2015-01-05 01:52:00 +08:00
entry:
%0 = trunc <8 x i16> %inval to <8 x i8>
%1 = bitcast <8 x i8> %0 to i64
ret i64 %1
}
[DAGCombiner] Add support for TRUNCATE + FP_EXTEND vector constant folding This patch adds supports for the vector constant folding of TRUNCATE and FP_EXTEND instructions and tidies up the SINT_TO_FP and UINT_TO_FP instructions to match. It also moves the vector constant folding for the FNEG and FABS instructions to use the DAG.getNode() functionality like the other unary instructions. Differential Revision: http://reviews.llvm.org/D8593 llvm-svn: 233224
2015-03-26 06:30:31 +08:00
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
define <16 x i8> @trunc16i64_16i8_const() {
; SSE-LABEL: trunc16i64_16i8_const:
[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
; SSE: # %bb.0: # %entry
[X86][SSE] Tidied up vector extend/truncation tests. NFCI. llvm-svn: 241995
2015-07-13 01:40:49 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
; SSE-NEXT: retq
;
[X86][SSE] Added extra vector truncation tests. Including cases for PR14866 llvm-svn: 245274
2015-08-18 16:37:09 +08:00
; AVX-LABEL: trunc16i64_16i8_const:
[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
; AVX: # %bb.0: # %entry
[X86][SSE] Tidied up vector extend/truncation tests. NFCI. llvm-svn: 241995
2015-07-13 01:40:49 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
[X86][SSE] Transform truncations between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. This patch transforms truncation between vectors of integers into X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in lowering phase because after type legalization, the original truncation will be turned into a BUILD_VECTOR with each element that is extracted from a vector and then truncated, and from them it is difficult to do this optimization. This greatly improves the performance of truncations on some specific types. Cost table is updated accordingly. Differential revision: http://reviews.llvm.org/D14588 llvm-svn: 256194
2015-12-22 04:42:43 +08:00
;
[X86] Add custom execution domain fixing for 128/256-bit integer logic operations with AVX512F, but not AVX512DQ. AVX512F only has integer domain logic instructions. AVX512DQ added FP domain logic instructions. Execution domain fixing runs before EVEX->VEX. So if we have AVX512F and not AVX512DQ we fail to do execution domain switching of the logic operations. This leads to mismatches in execution domain and more test differences. This patch adds custom domain fixing that switches EVEX integer logic operations to VEX fp logic operations if XMM16-31 are not used. llvm-svn: 337137
2018-07-16 07:32:36 +08:00
; AVX512-LABEL: trunc16i64_16i8_const:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX512-NEXT: retq
[DAGCombiner] Add support for TRUNCATE + FP_EXTEND vector constant folding This patch adds supports for the vector constant folding of TRUNCATE and FP_EXTEND instructions and tidies up the SINT_TO_FP and UINT_TO_FP instructions to match. It also moves the vector constant folding for the FNEG and FABS instructions to use the DAG.getNode() functionality like the other unary instructions. Differential Revision: http://reviews.llvm.org/D8593 llvm-svn: 233224
2015-03-26 06:30:31 +08:00
entry:
%0 = trunc <16 x i64> zeroinitializer to <16 x i8>
%1 = shufflevector <16 x i8> %0, <16 x i8> %0, <16 x i32> <i32 28, i32 30, i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 undef, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26>
ret <16 x i8> %1
}
[AVX512BW] Change truncStore action (v16i16->v16i18). It can be legal only with AVX512VL. Differential Revision: http://reviews.llvm.org/D24547 llvm-svn: 281445
2016-09-14 16:04:28 +08:00
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
define <8 x i16> @PR32160(<8 x i32> %x) {
[TargetLowering] SimplifyDemandedVectorElts - pass demanded elts through TRUNCATE ops llvm-svn: 326043
2018-02-25 03:28:34 +08:00
; SSE-LABEL: PR32160:
; SSE: # %bb.0:
; SSE-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,2,2,2]
; SSE-NEXT: retq
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
;
; AVX1-LABEL: PR32160:
; AVX1: # %bb.0:
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,8,9,8,9,8,9,8,9]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: PR32160:
; AVX2-SLOW: # %bb.0:
[X86][SSE] Add extract_subvector(PSHUFB) -> PSHUFB(extract_subvector()) combine Fixes PR32160 by reducing the size of PSHUFB if we only use one of the lanes. This approach can probably be generalized to handle any target shuffle (and any subvector index) but we have no test coverage at the moment. llvm-svn: 344336
2018-10-12 20:10:34 +08:00
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: PR32160:
; AVX2-FAST: # %bb.0:
[X86][SSE] Add extract_subvector(PSHUFB) -> PSHUFB(extract_subvector()) combine Fixes PR32160 by reducing the size of PSHUFB if we only use one of the lanes. This approach can probably be generalized to handle any target shuffle (and any subvector index) but we have no test coverage at the moment. llvm-svn: 344336
2018-10-12 20:10:34 +08:00
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,8,9,8,9,8,9,8,9]
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
;
; AVX512F-LABEL: PR32160:
; AVX512F: # %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR32160:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR32160:
; AVX512BW: # %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR32160:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
[X86][SSE] Add test case from PR32160 llvm-svn: 321620
2018-01-01 21:04:04 +08:00
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%shuf = trunc <8 x i32> %x to <8 x i16>
%trunc = shufflevector <8 x i16> %shuf, <8 x i16> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
ret <8 x i16> %trunc
}
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
define void @PR34773(i16* %a0, i8* %a1) {
; SSE-LABEL: PR34773:
[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
; SSE: # %bb.0:
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; SSE-NEXT: movdqu (%rdi), %xmm0
; SSE-NEXT: movdqu 16(%rdi), %xmm1
; SSE-NEXT: movdqu 32(%rdi), %xmm2
; SSE-NEXT: movdqu 48(%rdi), %xmm3
; SSE-NEXT: psrlw $8, %xmm1
; SSE-NEXT: psrlw $8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: psrlw $8, %xmm3
; SSE-NEXT: psrlw $8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: movdqu %xmm0, (%rsi)
; SSE-NEXT: movdqu %xmm2, 16(%rsi)
; SSE-NEXT: retq
;
; AVX1-LABEL: PR34773:
[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] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX1-NEXT: vmovdqu (%rdi), %ymm0
; AVX1-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
[SelectionDAG] Add support for INSERT_SUBVECTOR to computeKnownBits llvm-svn: 316847
2017-10-29 06:10:40 +08:00
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
; AVX1-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
[X86][SSE] Add PACKUS support to LowerTruncate Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317128
2017-11-02 05:52:29 +08:00
; AVX1-NEXT: vmovdqu %xmm0, (%rsi)
; AVX1-NEXT: vmovdqu %xmm1, 16(%rsi)
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: PR34773:
[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] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX2-NEXT: vmovdqu (%rdi), %ymm0
; AVX2-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX2-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
[X86][SSE] Add PACKUS support to LowerTruncate Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value. We have to account for pre-SSE41 targets not supporting PACKUSDW llvm-svn: 317128
2017-11-02 05:52:29 +08:00
; AVX2-NEXT: vmovdqu %xmm0, (%rsi)
; AVX2-NEXT: vmovdqu %xmm1, 16(%rsi)
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: PR34773:
[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:
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512F-NEXT: vmovdqu (%rdi), %ymm0
; AVX512F-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512F-NEXT: vpsrlw $8, %ymm1, %ymm1
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512F-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512F-NEXT: vpmovdb %zmm0, (%rsi)
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = 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
; AVX512F-NEXT: vpmovdb %zmm0, 16(%rsi)
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR34773:
[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
; AVX512VL: # %bb.0:
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512VL-NEXT: vmovdqu (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512VL-NEXT: vpsrlw $8, %ymm1, %ymm1
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; AVX512VL-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
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; AVX512VL-NEXT: vpmovdb %zmm0, (%rsi)
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = 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
; AVX512VL-NEXT: vpmovdb %zmm0, 16(%rsi)
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR34773:
[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:
[X86][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512BW-NEXT: vmovdqu (%rdi), %ymm0
; AVX512BW-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512BW-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
; AVX512BW-NEXT: vmovdqu %xmm0, (%rsi)
; AVX512BW-NEXT: vmovdqu %xmm1, 16(%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR34773:
[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][SSE] Tests packuswb/truncation codegen from PR34773 llvm-svn: 316033
2017-10-18 05:14:53 +08:00
; AVX512BWVL-NEXT: vpsrlw $8, (%rdi), %ymm0
; AVX512BWVL-NEXT: vpsrlw $8, 32(%rdi), %ymm1
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rsi)
; AVX512BWVL-NEXT: vpmovwb %ymm1, 16(%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%1 = getelementptr i16, i16* %a0, i64 16
%2 = getelementptr i8, i8* %a1, i64 16
%3 = bitcast i16* %a0 to <16 x i16>*
%4 = bitcast i16* %1 to <16 x i16>*
%5 = bitcast i8* %a1 to <16 x i8>*
%6 = bitcast i8* %2 to <16 x i8>*
%7 = load <16 x i16>, <16 x i16>* %3, align 2
%8 = load <16 x i16>, <16 x i16>* %4, align 2
%9 = lshr <16 x i16> %7, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%10 = lshr <16 x i16> %8, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%11 = trunc <16 x i16> %9 to <16 x i8>
%12 = trunc <16 x i16> %10 to <16 x i8>
store <16 x i8> %11, <16 x i8>* %5, align 1
store <16 x i8> %12, <16 x i8>* %6, align 1
ret void
}