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/avx512cdvl-intrinsics.ll

150 lines
6.5 KiB
LLVM
Raw Normal View History

AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512cd -mattr=+avx512vl| FileCheck %s
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
define <4 x i32> @test_int_x86_avx512_mask_vplzcnt_d_128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2) {
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-LABEL: test_int_x86_avx512_mask_vplzcnt_d_128:
[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
; CHECK: ## %bb.0:
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vplzcntd %xmm0, %xmm2
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vplzcntd %xmm0, %xmm1 {%k1}
Revert r302938 "Add LiveRangeShrink pass to shrink live range within BB." This also reverts follow-ups r303292 and r303298. It broke some Chromium tests under MSan, and apparently also internal tests at Google. llvm-svn: 303369
2017-05-19 02:50:05 +08:00
; CHECK-NEXT: vpaddd %xmm2, %xmm1, %xmm1
Add LiveRangeShrink pass to shrink live range within BB. Summary: LiveRangeShrink pass moves instruction right after the definition with the same BB if the instruction and its operands all have more than one use. This pass is inexpensive and guarantees optimal live-range within BB. Reviewers: davidxl, wmi, hfinkel, MatzeB, andreadb Reviewed By: MatzeB, andreadb Subscribers: hiraditya, jyknight, sanjoy, skatkov, gberry, jholewinski, qcolombet, javed.absar, krytarowski, atrick, spatel, RKSimon, andreadb, MatzeB, mehdi_amini, mgorny, efriedma, davide, dberlin, llvm-commits Differential Revision: https://reviews.llvm.org/D32563 llvm-svn: 304371
2017-06-01 07:25:25 +08:00
; CHECK-NEXT: vplzcntd %xmm0, %xmm0 {%k1} {z}
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
%1 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> %x0, i1 false)
%2 = bitcast i8 %x2 to <8 x i1>
%extract1 = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract1, <4 x i32> %1, <4 x i32> %x1
%4 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> %x0, i1 false)
%5 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> %x0, i1 false)
%6 = bitcast i8 %x2 to <8 x i1>
%extract = shufflevector <8 x i1> %6, <8 x i1> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%7 = select <4 x i1> %extract, <4 x i32> %5, <4 x i32> zeroinitializer
%res2 = add <4 x i32> %3, %4
%res4 = add <4 x i32> %res2, %7
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
ret <4 x i32> %res4
}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
declare <4 x i32> @llvm.ctlz.v4i32(<4 x i32>, i1) #0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
define <8 x i32> @test_int_x86_avx512_mask_vplzcnt_d_256(<8 x i32> %x0, <8 x i32> %x1, i8 %x2) {
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-LABEL: test_int_x86_avx512_mask_vplzcnt_d_256:
[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
; CHECK: ## %bb.0:
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vplzcntd %ymm0, %ymm2
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vplzcntd %ymm0, %ymm1 {%k1}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vpaddd %ymm2, %ymm1, %ymm0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: retq
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
%1 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> %x0, i1 false)
%2 = bitcast i8 %x2 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x1
%4 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> %x0, i1 false)
%res2 = add <8 x i32> %3, %4
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
ret <8 x i32> %res2
}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
declare <8 x i32> @llvm.ctlz.v8i32(<8 x i32>, i1) #0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
define <2 x i64> @test_int_x86_avx512_mask_vplzcnt_q_128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2) {
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-LABEL: test_int_x86_avx512_mask_vplzcnt_q_128:
[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
; CHECK: ## %bb.0:
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vplzcntq %xmm0, %xmm2
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vplzcntq %xmm0, %xmm1 {%k1}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vpaddq %xmm2, %xmm1, %xmm0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: retq
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
%1 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> %x0, i1 false)
%2 = bitcast i8 %x2 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
%3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x1
%4 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> %x0, i1 false)
%res2 = add <2 x i64> %3, %4
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
ret <2 x i64> %res2
}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>, i1) #0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
define <4 x i64> @test_int_x86_avx512_mask_vplzcnt_q_256(<4 x i64> %x0, <4 x i64> %x1, i8 %x2) {
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-LABEL: test_int_x86_avx512_mask_vplzcnt_q_256:
[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
; CHECK: ## %bb.0:
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vplzcntq %ymm0, %ymm2
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vplzcntq %ymm0, %ymm1 {%k1}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
; CHECK-NEXT: vpaddq %ymm2, %ymm1, %ymm0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: retq
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
%1 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> %x0, i1 false)
%2 = bitcast i8 %x2 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %x1
%4 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> %x0, i1 false)
%res2 = add <4 x i64> %3, %4
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
ret <4 x i64> %res2
}
[AVX-512] Remove lzcnt intrinsics and autoupgrade them to generic ctlz intrinsics with select. Clang has been emitting cltz intrinsics for a while now. llvm-svn: 296091
2017-02-24 13:35:04 +08:00
declare <4 x i64> @llvm.ctlz.v4i64(<4 x i64>, i1) #0
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
declare <4 x i32> @llvm.x86.avx512.mask.conflict.d.128(<4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_vpconflict_d_128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpconflict_d_128:
[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
; CHECK: ## %bb.0:
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpconflictd %xmm0, %xmm2 {%k1} {z}
[AVX-512] Fix accidental uses of AH/BH/CH/DH after copies to/from mask registers We've had several bugs(PR32256, PR32241) recently that resulted from usages of AH/BH/CH/DH either before or after a copy to/from a mask register. This ultimately occurs because we create COPY_TO_REGCLASS with VK1 and GR8. Then in CopyToFromAsymmetricReg in X86InstrInfo we find a 32-bit super register for the GR8 to emit the KMOV with. But as these tests are demonstrating, its possible for the GR8 register to be a high register and we end up doing an accidental extra or insert from bits 15:8. I think the best way forward is to stop making copies directly between mask registers and GR8/GR16. Instead I think we should restrict to only copies between mask registers and GR32/GR64 and use EXTRACT_SUBREG/INSERT_SUBREG to handle the conversion from GR32 to GR16/8 or vice versa. Unfortunately, this complicates fastisel a bit more now to create the subreg extracts where we used to create GR8 copies. We can probably make a helper function to bring down the repitition. This does result in KMOVD being used for copies when BWI is available because we don't know the original mask register size. This caused a lot of deltas on tests because we have to split the checks for KMOVD vs KMOVW based on BWI. Differential Revision: https://reviews.llvm.org/D30968 llvm-svn: 298928
2017-03-29 00:35:29 +08:00
; CHECK-NEXT: vpconflictd %xmm0, %xmm1 {%k1}
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpconflictd %xmm0, %xmm0
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; CHECK-NEXT: vpaddd %xmm2, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x i32> @llvm.x86.avx512.mask.conflict.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.conflict.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 -1)
%res3 = call <4 x i32> @llvm.x86.avx512.mask.conflict.d.128(<4 x i32> %x0, <4 x i32> zeroinitializer, i8 %x2)
%res2 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res2, %res3
ret <4 x i32> %res4
}
declare <8 x i32> @llvm.x86.avx512.mask.conflict.d.256(<8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_vpconflict_d_256(<8 x i32> %x0, <8 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpconflict_d_256:
[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
; CHECK: ## %bb.0:
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpconflictd %ymm0, %ymm1 {%k1}
; CHECK-NEXT: vpconflictd %ymm0, %ymm0
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%res = call <8 x i32> @llvm.x86.avx512.mask.conflict.d.256(<8 x i32> %x0, <8 x i32> %x1, i8 %x2)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.conflict.d.256(<8 x i32> %x0, <8 x i32> %x1, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.conflict.q.128(<2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_vpconflict_q_128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpconflict_q_128:
[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
; CHECK: ## %bb.0:
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpconflictq %xmm0, %xmm1 {%k1}
; CHECK-NEXT: vpconflictq %xmm0, %xmm0
; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
%res = call <2 x i64> @llvm.x86.avx512.mask.conflict.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.conflict.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.conflict.q.256(<4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_vpconflict_q_256(<4 x i64> %x0, <4 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpconflict_q_256:
[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
; CHECK: ## %bb.0:
AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. code example , previous implementation. movzbl %dil, %eax kmovw %eax, %k0 new code kmovw %edi, %k0 Differential Revision: http://reviews.llvm.org/D16287 llvm-svn: 258045
2016-01-18 20:02:45 +08:00
; CHECK-NEXT: kmovw %edi, %k1
AVX512: Implemented encoding and intrinsics for vplzcntq, vplzcntd, vpconflictq, vpconflictd Added tests for intrinsics and encoding. Differential Revision: http://reviews.llvm.org/D11931 llvm-svn: 246750
2015-09-03 17:05:31 +08:00
; CHECK-NEXT: vpconflictq %ymm0, %ymm1 {%k1}
; CHECK-NEXT: vpconflictq %ymm0, %ymm0
; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%res = call <4 x i64> @llvm.x86.avx512.mask.conflict.q.256(<4 x i64> %x0, <4 x i64> %x1, i8 %x2)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.conflict.q.256(<4 x i64> %x0, <4 x i64> %x1, i8 -1)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}