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/avx512-logic.ll

864 lines
30 KiB
LLVM
Raw Normal View History

AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s --check-prefix=ALL --check-prefix=KNL
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skx | FileCheck %s --check-prefix=ALL --check-prefix=SKX
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
define <16 x i32> @vpandd(<16 x i32> %a, <16 x i32> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vpandd:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddd {{.*}}(%rip){1to16}, %zmm0, %zmm0
[AVX512] Don't use 32-bit elements version of AND/OR/XOR/ANDN during isel unless we're matching a masked op or broadcast Selecting 32-bit element logical ops without a select or broadcast requires matching a bitconvert on the inputs to the and. But that's a weird thing to rely on. It's entirely possible that one of the inputs doesn't have a bitcast and one does. Since there's no functional difference, just remove the extra patterns and save some isel table size. Differential Revision: https://reviews.llvm.org/D36854 llvm-svn: 312138
2017-08-31 00:38:33 +08:00
; ALL-NEXT: vpandq %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <16 x i32> %a, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2,
i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = and <16 x i32> %a2, %b
ret <16 x i32> %x
}
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
define <16 x i32> @vpandnd(<16 x i32> %a, <16 x i32> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: vpandnd:
[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
; ALL: ## %bb.0: ## %entry
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; ALL-NEXT: vpaddd {{.*}}(%rip){1to16}, %zmm0, %zmm0
[AVX512] Don't use 32-bit elements version of AND/OR/XOR/ANDN during isel unless we're matching a masked op or broadcast Selecting 32-bit element logical ops without a select or broadcast requires matching a bitconvert on the inputs to the and. But that's a weird thing to rely on. It's entirely possible that one of the inputs doesn't have a bitcast and one does. Since there's no functional difference, just remove the extra patterns and save some isel table size. Differential Revision: https://reviews.llvm.org/D36854 llvm-svn: 312138
2017-08-31 00:38:33 +08:00
; ALL-NEXT: vpandnq %zmm0, %zmm1, %zmm0
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; ALL-NEXT: retq
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <16 x i32> %a, <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3,
i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
%b2 = xor <16 x i32> %b, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1,
i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%x = and <16 x i32> %a2, %b2
ret <16 x i32> %x
}
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
define <16 x i32> @vpord(<16 x i32> %a, <16 x i32> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vpord:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddd {{.*}}(%rip){1to16}, %zmm0, %zmm0
[AVX512] Don't use 32-bit elements version of AND/OR/XOR/ANDN during isel unless we're matching a masked op or broadcast Selecting 32-bit element logical ops without a select or broadcast requires matching a bitconvert on the inputs to the and. But that's a weird thing to rely on. It's entirely possible that one of the inputs doesn't have a bitcast and one does. Since there's no functional difference, just remove the extra patterns and save some isel table size. Differential Revision: https://reviews.llvm.org/D36854 llvm-svn: 312138
2017-08-31 00:38:33 +08:00
; ALL-NEXT: vporq %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <16 x i32> %a, <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4,
i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = or <16 x i32> %a2, %b
ret <16 x i32> %x
}
define <16 x i32> @vpxord(<16 x i32> %a, <16 x i32> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vpxord:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddd {{.*}}(%rip){1to16}, %zmm0, %zmm0
[AVX512] Don't use 32-bit elements version of AND/OR/XOR/ANDN during isel unless we're matching a masked op or broadcast Selecting 32-bit element logical ops without a select or broadcast requires matching a bitconvert on the inputs to the and. But that's a weird thing to rely on. It's entirely possible that one of the inputs doesn't have a bitcast and one does. Since there's no functional difference, just remove the extra patterns and save some isel table size. Differential Revision: https://reviews.llvm.org/D36854 llvm-svn: 312138
2017-08-31 00:38:33 +08:00
; ALL-NEXT: vpxorq %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5,
i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = xor <16 x i32> %a2, %b
ret <16 x i32> %x
}
define <8 x i64> @vpandq(<8 x i64> %a, <8 x i64> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vpandq:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; ALL-NEXT: vpandq %zmm1, %zmm0, %zmm0
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <8 x i64> %a, <i64 6, i64 6, i64 6, i64 6, i64 6, i64 6, i64 6, i64 6>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = and <8 x i64> %a2, %b
ret <8 x i64> %x
}
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
define <8 x i64> @vpandnq(<8 x i64> %a, <8 x i64> %b) nounwind uwtable readnone ssp {
; ALL-LABEL: vpandnq:
[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
; ALL: ## %bb.0: ## %entry
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; ALL-NEXT: vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; ALL-NEXT: vpandnq %zmm0, %zmm1, %zmm0
; ALL-NEXT: retq
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
%b2 = xor <8 x i64> %b, <i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1>
%x = and <8 x i64> %a2, %b2
ret <8 x i64> %x
}
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
define <8 x i64> @vporq(<8 x i64> %a, <8 x i64> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vporq:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; ALL-NEXT: vporq %zmm1, %zmm0, %zmm0
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <8 x i64> %a, <i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = or <8 x i64> %a2, %b
ret <8 x i64> %x
}
define <8 x i64> @vpxorq(<8 x i64> %a, <8 x i64> %b) nounwind uwtable readnone ssp {
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-LABEL: vpxorq:
[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
; ALL: ## %bb.0: ## %entry
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; ALL-NEXT: vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; ALL-NEXT: vpxorq %zmm1, %zmm0, %zmm0
; ALL-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
; Force the execution domain with an add.
x86] adjust test constants to maintain coverage; NFC Increment (add 1) could be transformed to sub -1, and we'd lose coverage for these patterns. llvm-svn: 305646
2017-06-18 22:45:23 +08:00
%a2 = add <8 x i64> %a, <i64 9, i64 9, i64 9, i64 9, i64 9, i64 9, i64 9, i64 9>
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%x = xor <8 x i64> %a2, %b
ret <8 x i64> %x
}
define <8 x i64> @orq_broadcast(<8 x i64> %a) nounwind {
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; KNL-LABEL: orq_broadcast:
[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
; KNL: ## %bb.0:
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; KNL-NEXT: vporq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: orq_broadcast:
[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
; SKX: ## %bb.0:
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; SKX-NEXT: vorpd {{.*}}(%rip){1to8}, %zmm0, %zmm0
; SKX-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%b = or <8 x i64> %a, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
ret <8 x i64> %b
}
define <16 x i32> @andd512fold(<16 x i32> %y, <16 x i32>* %x) {
[AVX-512] Fix duplicate column in AVX512 execution dependency table that was preventing VMOVDQU32/VMOVDQA32 from being recognized. Fix a bug in the code that stops execution dependency fix from turning operations on 32-bit integer element types into operations on 64-bit integer element types. llvm-svn: 277327
2016-08-01 15:55:33 +08:00
; KNL-LABEL: andd512fold:
[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
; KNL: ## %bb.0: ## %entry
[AVX512] Don't use 32-bit elements version of AND/OR/XOR/ANDN during isel unless we're matching a masked op or broadcast Selecting 32-bit element logical ops without a select or broadcast requires matching a bitconvert on the inputs to the and. But that's a weird thing to rely on. It's entirely possible that one of the inputs doesn't have a bitcast and one does. Since there's no functional difference, just remove the extra patterns and save some isel table size. Differential Revision: https://reviews.llvm.org/D36854 llvm-svn: 312138
2017-08-31 00:38:33 +08:00
; KNL-NEXT: vpandq (%rdi), %zmm0, %zmm0
[AVX-512] Fix duplicate column in AVX512 execution dependency table that was preventing VMOVDQU32/VMOVDQA32 from being recognized. Fix a bug in the code that stops execution dependency fix from turning operations on 32-bit integer element types into operations on 64-bit integer element types. llvm-svn: 277327
2016-08-01 15:55:33 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: andd512fold:
[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
; SKX: ## %bb.0: ## %entry
[AVX-512] Fix duplicate column in AVX512 execution dependency table that was preventing VMOVDQU32/VMOVDQA32 from being recognized. Fix a bug in the code that stops execution dependency fix from turning operations on 32-bit integer element types into operations on 64-bit integer element types. llvm-svn: 277327
2016-08-01 15:55:33 +08:00
; SKX-NEXT: vandps (%rdi), %zmm0, %zmm0
; SKX-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load <16 x i32>, <16 x i32>* %x, align 4
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%b = and <16 x i32> %y, %a
ret <16 x i32> %b
}
define <8 x i64> @andqbrst(<8 x i64> %p1, i64* %ap) {
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; KNL-LABEL: andqbrst:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; KNL-NEXT: vpandq (%rdi){1to8}, %zmm0, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: andqbrst:
[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
; SKX: ## %bb.0: ## %entry
[AVX-512] Add execution domain fixing for logical operations with broadcast loads. This builds on the handling of masked ops since we need to keep element size the same. llvm-svn: 280464
2016-09-02 13:29:09 +08:00
; SKX-NEXT: vandpd (%rdi){1to8}, %zmm0, %zmm0
; SKX-NEXT: retq
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load i64, i64* %ap, align 8
[AVX512] Enabling bit logic lowering Added lowering tests. llvm-svn: 224132
2014-12-13 01:02:18 +08:00
%b = insertelement <8 x i64> undef, i64 %a, i32 0
%c = shufflevector <8 x i64> %b, <8 x i64> undef, <8 x i32> zeroinitializer
%d = and <8 x i64> %p1, %c
ret <8 x i64>%d
}
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
define <64 x i8> @and_v64i8(<64 x i8> %a, <64 x i8> %b) {
; KNL-LABEL: and_v64i8:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vandps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vandps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: and_v64i8:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vandps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = and <64 x i8> %a, %b
ret <64 x i8> %res
}
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
define <64 x i8> @andn_v64i8(<64 x i8> %a, <64 x i8> %b) {
; KNL-LABEL: andn_v64i8:
[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
; KNL: ## %bb.0:
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; KNL-NEXT: vandnps %ymm0, %ymm2, %ymm0
; KNL-NEXT: vandnps %ymm1, %ymm3, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: andn_v64i8:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vandnps %zmm0, %zmm1, %zmm0
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; SKX-NEXT: retq
%b2 = xor <64 x i8> %b, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1,
i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1,
i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1,
i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%res = and <64 x i8> %a, %b2
ret <64 x i8> %res
}
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
define <64 x i8> @or_v64i8(<64 x i8> %a, <64 x i8> %b) {
; KNL-LABEL: or_v64i8:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vorps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vorps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: or_v64i8:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vorps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = or <64 x i8> %a, %b
ret <64 x i8> %res
}
define <64 x i8> @xor_v64i8(<64 x i8> %a, <64 x i8> %b) {
; KNL-LABEL: xor_v64i8:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vxorps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vxorps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: xor_v64i8:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vxorps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = xor <64 x i8> %a, %b
ret <64 x i8> %res
}
define <32 x i16> @and_v32i16(<32 x i16> %a, <32 x i16> %b) {
; KNL-LABEL: and_v32i16:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vandps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vandps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: and_v32i16:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vandps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = and <32 x i16> %a, %b
ret <32 x i16> %res
}
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
define <32 x i16> @andn_v32i16(<32 x i16> %a, <32 x i16> %b) {
; KNL-LABEL: andn_v32i16:
[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
; KNL: ## %bb.0:
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; KNL-NEXT: vandnps %ymm0, %ymm2, %ymm0
; KNL-NEXT: vandnps %ymm1, %ymm3, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: andn_v32i16:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vandnps %zmm0, %zmm1, %zmm0
[AVX512] Add support for 512-bit ANDN now that all ones build vectors survive long enough to allow the matching. llvm-svn: 275046
2016-07-11 13:36:53 +08:00
; SKX-NEXT: retq
%b2 = xor <32 x i16> %b, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1,
i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%res = and <32 x i16> %a, %b2
ret <32 x i16> %res
}
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
define <32 x i16> @or_v32i16(<32 x i16> %a, <32 x i16> %b) {
; KNL-LABEL: or_v32i16:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vorps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vorps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: or_v32i16:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vorps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = or <32 x i16> %a, %b
ret <32 x i16> %res
}
define <32 x i16> @xor_v32i16(<32 x i16> %a, <32 x i16> %b) {
; KNL-LABEL: xor_v32i16:
[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
; KNL: ## %bb.0:
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; KNL-NEXT: vxorps %ymm2, %ymm0, %ymm0
; KNL-NEXT: vxorps %ymm3, %ymm1, %ymm1
; KNL-NEXT: retq
;
; SKX-LABEL: xor_v32i16:
[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
; SKX: ## %bb.0:
[AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. llvm-svn: 276393
2016-07-22 13:00:52 +08:00
; SKX-NEXT: vxorps %zmm1, %zmm0, %zmm0
AVX512BW: Enable AND/OR/XOR vector byte/word paked operation by promoting to qword that natively suppored. llvm-svn: 256157
2015-12-21 22:40:36 +08:00
; SKX-NEXT: retq
%res = xor <32 x i16> %a, %b
ret <32 x i16> %res
}
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
define <16 x float> @masked_and_v16f32(<16 x float> %a, <16 x float> %b, <16 x float> %passThru, i16 %mask, <16 x float> %c) {
; KNL-LABEL: masked_and_v16f32:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandd %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddps %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_and_v16f32:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandps %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddps %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <16 x float> %a to <16 x i32>
%b1 = bitcast <16 x float> %b to <16 x i32>
%passThru1 = bitcast <16 x float> %passThru to <16 x i32>
%mask1 = bitcast i16 %mask to <16 x i1>
%op = and <16 x i32> %a1, %b1
%select = select <16 x i1> %mask1, <16 x i32> %op, <16 x i32> %passThru1
%cast = bitcast <16 x i32> %select to <16 x float>
%add = fadd <16 x float> %c, %cast
ret <16 x float> %add
}
define <16 x float> @masked_or_v16f32(<16 x float> %a, <16 x float> %b, <16 x float> %passThru, i16 %mask, <16 x float> %c) {
; KNL-LABEL: masked_or_v16f32:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandd %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddps %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_or_v16f32:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandps %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddps %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <16 x float> %a to <16 x i32>
%b1 = bitcast <16 x float> %b to <16 x i32>
%passThru1 = bitcast <16 x float> %passThru to <16 x i32>
%mask1 = bitcast i16 %mask to <16 x i1>
%op = and <16 x i32> %a1, %b1
%select = select <16 x i1> %mask1, <16 x i32> %op, <16 x i32> %passThru1
%cast = bitcast <16 x i32> %select to <16 x float>
%add = fadd <16 x float> %c, %cast
ret <16 x float> %add
}
define <16 x float> @masked_xor_v16f32(<16 x float> %a, <16 x float> %b, <16 x float> %passThru, i16 %mask, <16 x float> %c) {
; KNL-LABEL: masked_xor_v16f32:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandd %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddps %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_xor_v16f32:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandps %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddps %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <16 x float> %a to <16 x i32>
%b1 = bitcast <16 x float> %b to <16 x i32>
%passThru1 = bitcast <16 x float> %passThru to <16 x i32>
%mask1 = bitcast i16 %mask to <16 x i1>
%op = and <16 x i32> %a1, %b1
%select = select <16 x i1> %mask1, <16 x i32> %op, <16 x i32> %passThru1
%cast = bitcast <16 x i32> %select to <16 x float>
%add = fadd <16 x float> %c, %cast
ret <16 x float> %add
}
define <8 x double> @masked_and_v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %passThru, i8 %mask, <8 x double> %c) {
; KNL-LABEL: masked_and_v8f64:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandq %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_and_v8f64:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandpd %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <8 x double> %a to <8 x i64>
%b1 = bitcast <8 x double> %b to <8 x i64>
%passThru1 = bitcast <8 x double> %passThru to <8 x i64>
%mask1 = bitcast i8 %mask to <8 x i1>
%op = and <8 x i64> %a1, %b1
%select = select <8 x i1> %mask1, <8 x i64> %op, <8 x i64> %passThru1
%cast = bitcast <8 x i64> %select to <8 x double>
%add = fadd <8 x double> %c, %cast
ret <8 x double> %add
}
define <8 x double> @masked_or_v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %passThru, i8 %mask, <8 x double> %c) {
; KNL-LABEL: masked_or_v8f64:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandq %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_or_v8f64:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandpd %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <8 x double> %a to <8 x i64>
%b1 = bitcast <8 x double> %b to <8 x i64>
%passThru1 = bitcast <8 x double> %passThru to <8 x i64>
%mask1 = bitcast i8 %mask to <8 x i1>
%op = and <8 x i64> %a1, %b1
%select = select <8 x i1> %mask1, <8 x i64> %op, <8 x i64> %passThru1
%cast = bitcast <8 x i64> %select to <8 x double>
%add = fadd <8 x double> %c, %cast
ret <8 x double> %add
}
define <8 x double> @masked_xor_v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %passThru, i8 %mask, <8 x double> %c) {
; KNL-LABEL: masked_xor_v8f64:
[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
; KNL: ## %bb.0:
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandq %zmm1, %zmm0, %zmm2 {%k1}
; KNL-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; KNL-NEXT: retq
;
; SKX-LABEL: masked_xor_v8f64:
[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
; SKX: ## %bb.0:
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add support for execution domain switching masked logical ops between floating point and integer domain. This switches PS<->D and PD<->Q. llvm-svn: 278097
2016-08-09 13:26:07 +08:00
; SKX-NEXT: vandpd %zmm1, %zmm0, %zmm2 {%k1}
; SKX-NEXT: vaddpd %zmm2, %zmm3, %zmm0
; SKX-NEXT: retq
%a1 = bitcast <8 x double> %a to <8 x i64>
%b1 = bitcast <8 x double> %b to <8 x i64>
%passThru1 = bitcast <8 x double> %passThru to <8 x i64>
%mask1 = bitcast i8 %mask to <8 x i1>
%op = and <8 x i64> %a1, %b1
%select = select <8 x i1> %mask1, <8 x i64> %op, <8 x i64> %passThru1
%cast = bitcast <8 x i64> %select to <8 x double>
%add = fadd <8 x double> %c, %cast
ret <8 x double> %add
}
[AVX-512] Add tests to show that we don't select masked logic ops if there are bitcasts between the logic op and the select. This is taken from optimized IR of clang test cases for masked logic ops. llvm-svn: 279928
2016-08-28 14:06:24 +08:00
define <8 x i64> @test_mm512_mask_and_epi32(<8 x i64> %__src, i16 zeroext %__k, <8 x i64> %__a, <8 x i64> %__b) {
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-LABEL: test_mm512_mask_and_epi32:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpandd %zmm2, %zmm1, %zmm0 {%k1}
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_and_epi32:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; SKX-NEXT: vandps %zmm2, %zmm1, %zmm0 {%k1}
; SKX-NEXT: retq
[AVX-512] Add tests to show that we don't select masked logic ops if there are bitcasts between the logic op and the select. This is taken from optimized IR of clang test cases for masked logic ops. llvm-svn: 279928
2016-08-28 14:06:24 +08:00
entry:
%and1.i.i = and <8 x i64> %__a, %__b
%0 = bitcast <8 x i64> %and1.i.i to <16 x i32>
%1 = bitcast <8 x i64> %__src to <16 x i32>
%2 = bitcast i16 %__k to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %0, <16 x i32> %1
%4 = bitcast <16 x i32> %3 to <8 x i64>
ret <8 x i64> %4
}
define <8 x i64> @test_mm512_mask_or_epi32(<8 x i64> %__src, i16 zeroext %__k, <8 x i64> %__a, <8 x i64> %__b) {
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-LABEL: test_mm512_mask_or_epi32:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpord %zmm2, %zmm1, %zmm0 {%k1}
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_or_epi32:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; SKX-NEXT: vorps %zmm2, %zmm1, %zmm0 {%k1}
; SKX-NEXT: retq
[AVX-512] Add tests to show that we don't select masked logic ops if there are bitcasts between the logic op and the select. This is taken from optimized IR of clang test cases for masked logic ops. llvm-svn: 279928
2016-08-28 14:06:24 +08:00
entry:
%or1.i.i = or <8 x i64> %__a, %__b
%0 = bitcast <8 x i64> %or1.i.i to <16 x i32>
%1 = bitcast <8 x i64> %__src to <16 x i32>
%2 = bitcast i16 %__k to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %0, <16 x i32> %1
%4 = bitcast <16 x i32> %3 to <8 x i64>
ret <8 x i64> %4
}
define <8 x i64> @test_mm512_mask_xor_epi32(<8 x i64> %__src, i16 zeroext %__k, <8 x i64> %__a, <8 x i64> %__b) {
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-LABEL: test_mm512_mask_xor_epi32:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vpxord %zmm2, %zmm1, %zmm0 {%k1}
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_xor_epi32:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Promote AND/OR/XOR to v2i64/v4i64/v8i64 even when we have AVX512F/AVX512VL. Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available. Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though. llvm-svn: 279929
2016-08-28 14:06:28 +08:00
; SKX-NEXT: vxorps %zmm2, %zmm1, %zmm0 {%k1}
; SKX-NEXT: retq
[AVX-512] Add tests to show that we don't select masked logic ops if there are bitcasts between the logic op and the select. This is taken from optimized IR of clang test cases for masked logic ops. llvm-svn: 279928
2016-08-28 14:06:24 +08:00
entry:
%xor1.i.i = xor <8 x i64> %__a, %__b
%0 = bitcast <8 x i64> %xor1.i.i to <16 x i32>
%1 = bitcast <8 x i64> %__src to <16 x i32>
%2 = bitcast i16 %__k to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %0, <16 x i32> %1
%4 = bitcast <16 x i32> %3 to <8 x i64>
ret <8 x i64> %4
}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
define <8 x double> @test_mm512_mask_xor_pd(<8 x double> %__W, i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_mask_xor_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpxorq %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_xor_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vxorpd %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%xor.i.i = xor <8 x i64> %0, %1
%2 = bitcast <8 x i64> %xor.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> %__W
ret <8 x double> %4
}
define <8 x double> @test_mm512_maskz_xor_pd(i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_maskz_xor_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpxorq %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_xor_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vxorpd %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%xor.i.i = xor <8 x i64> %0, %1
%2 = bitcast <8 x i64> %xor.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
ret <8 x double> %4
}
define <16 x float> @test_mm512_mask_xor_ps(<16 x float> %__W, i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_mask_xor_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpxord %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_xor_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vxorps %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%xor.i.i = xor <16 x i32> %0, %1
%2 = bitcast <16 x i32> %xor.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> %__W
ret <16 x float> %4
}
define <16 x float> @test_mm512_maskz_xor_ps(i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_maskz_xor_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpxord %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_xor_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vxorps %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%xor.i.i = xor <16 x i32> %0, %1
%2 = bitcast <16 x i32> %xor.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
ret <16 x float> %4
}
define <8 x double> @test_mm512_mask_or_pd(<8 x double> %__W, i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_mask_or_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vporq %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_or_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vorpd %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%or.i.i = or <8 x i64> %1, %0
%2 = bitcast <8 x i64> %or.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> %__W
ret <8 x double> %4
}
define <8 x double> @test_mm512_maskz_or_pd(i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_maskz_or_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vporq %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_or_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vorpd %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%or.i.i = or <8 x i64> %1, %0
%2 = bitcast <8 x i64> %or.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
ret <8 x double> %4
}
define <16 x float> @test_mm512_mask_or_ps(<16 x float> %__W, i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_mask_or_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpord %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_or_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vorps %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%or.i.i = or <16 x i32> %1, %0
%2 = bitcast <16 x i32> %or.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> %__W
ret <16 x float> %4
}
define <16 x float> @test_mm512_maskz_or_ps(i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_maskz_or_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpord %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_or_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vorps %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%or.i.i = or <16 x i32> %1, %0
%2 = bitcast <16 x i32> %or.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
ret <16 x float> %4
}
define <8 x double> @test_mm512_mask_and_pd(<8 x double> %__W, i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_mask_and_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandq %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_and_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandpd %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%and.i.i = and <8 x i64> %1, %0
%2 = bitcast <8 x i64> %and.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> %__W
ret <8 x double> %4
}
define <8 x double> @test_mm512_maskz_and_pd(i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_maskz_and_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandq %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_and_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandpd %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%1 = bitcast <8 x double> %__B to <8 x i64>
%and.i.i = and <8 x i64> %1, %0
%2 = bitcast <8 x i64> %and.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
ret <8 x double> %4
}
define <16 x float> @test_mm512_mask_and_ps(<16 x float> %__W, i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_mask_and_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandd %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_and_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandps %zmm1, %zmm2, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%and.i.i = and <16 x i32> %1, %0
%2 = bitcast <16 x i32> %and.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> %__W
ret <16 x float> %4
}
define <16 x float> @test_mm512_maskz_and_ps(i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_maskz_and_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandd %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_and_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandps %zmm0, %zmm1, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%1 = bitcast <16 x float> %__B to <16 x i32>
%and.i.i = and <16 x i32> %1, %0
%2 = bitcast <16 x i32> %and.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
ret <16 x float> %4
}
define <8 x double> @test_mm512_mask_andnot_pd(<8 x double> %__W, i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_mask_andnot_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandnq %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_andnot_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandnpd %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%neg.i.i = xor <8 x i64> %0, <i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1>
%1 = bitcast <8 x double> %__B to <8 x i64>
%and.i.i = and <8 x i64> %1, %neg.i.i
%2 = bitcast <8 x i64> %and.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> %__W
ret <8 x double> %4
}
define <8 x double> @test_mm512_maskz_andnot_pd(i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) {
; KNL-LABEL: test_mm512_maskz_andnot_pd:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandnq %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_andnot_pd:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandnpd %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <8 x double> %__A to <8 x i64>
%neg.i.i = xor <8 x i64> %0, <i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1>
%1 = bitcast <8 x double> %__B to <8 x i64>
%and.i.i = and <8 x i64> %1, %neg.i.i
%2 = bitcast <8 x i64> %and.i.i to <8 x double>
%3 = bitcast i8 %__U to <8 x i1>
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
ret <8 x double> %4
}
define <16 x float> @test_mm512_mask_andnot_ps(<16 x float> %__W, i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_mask_andnot_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandnd %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_mask_andnot_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandnps %zmm2, %zmm1, %zmm0 {%k1}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%neg.i.i = xor <16 x i32> %0, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%1 = bitcast <16 x float> %__B to <16 x i32>
%and.i.i = and <16 x i32> %1, %neg.i.i
%2 = bitcast <16 x i32> %and.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> %__W
ret <16 x float> %4
}
define <16 x float> @test_mm512_maskz_andnot_ps(i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) {
; KNL-LABEL: test_mm512_maskz_andnot_ps:
[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
; KNL: ## %bb.0: ## %entry
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: kmovw %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; KNL-NEXT: vpandnd %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: test_mm512_maskz_andnot_ps:
[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
; SKX: ## %bb.0: ## %entry
[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
; SKX-NEXT: kmovd %edi, %k1
[AVX-512] Add patterns to select masked logical operations if the select has a floating point type. This is needed in order to replace the masked floating point logical op intrinsics with native IR. llvm-svn: 280195
2016-08-31 13:37:52 +08:00
; SKX-NEXT: vandnps %zmm1, %zmm0, %zmm0 {%k1} {z}
[AVX-512] Add test cases for masked floating point logic operations with bitcasts between the logic ops and the select. We don't currently select masked operations for these cases. Test cases taken from optimized clang output after trying to convert the masked floating point logical op intrinsics to native IR. llvm-svn: 280194
2016-08-31 13:37:50 +08:00
; SKX-NEXT: retq
entry:
%0 = bitcast <16 x float> %__A to <16 x i32>
%neg.i.i = xor <16 x i32> %0, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%1 = bitcast <16 x float> %__B to <16 x i32>
%and.i.i = and <16 x i32> %1, %neg.i.i
%2 = bitcast <16 x i32> %and.i.i to <16 x float>
%3 = bitcast i16 %__U to <16 x i1>
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
ret <16 x float> %4
}