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-trunc.ll

1034 lines
44 KiB
LLVM
Raw Normal View History

Make utils/update_llc_test_checks.py note that the assertions are autogenerated. Also update existing test cases which appear to be generated by it and weren't modified (other than addition of the header) by rerunning it. llvm-svn: 253917
2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=KNL
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f,+avx512vl,+avx512bw,+avx512dq,+fast-variable-shuffle | FileCheck %s --check-prefixes=ALL,SKX
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
attributes #0 = { nounwind }
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
define <16 x i8> @trunc_16x32_to_16x8(<16 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_16x32_to_16x8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <16 x i32> %i to <16 x i8>
ret <16 x i8> %x
}
define <8 x i16> @trunc_8x64_to_8x16(<8 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_8x64_to_8x16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqw %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i16>
ret <8 x i16> %x
}
define <16 x i16> @trunc_v16i32_to_v16i16(<16 x i32> %x) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_v16i32_to_v16i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdw %zmm0, %ymm0
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%1 = trunc <16 x i32> %x to <16 x i16>
ret <16 x i16> %1
}
define <8 x i8> @trunc_qb_512(<8 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qb_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqw %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i8>
ret <8 x i8> %x
}
define void @trunc_qb_512_mem(<8 x i64> %i, <8 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qb_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i8>
store <8 x i8> %x, <8 x i8>* %res
ret void
}
define <4 x i8> @trunc_qb_256(<4 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqd %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i8>
ret <4 x i8> %x
}
define void @trunc_qb_256_mem(<4 x i64> %i, <4 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
; KNL-NEXT: vmovd %xmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqb %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i8>
store <4 x i8> %x, <4 x i8>* %res
ret void
}
define <2 x i8> @trunc_qb_128(<2 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qb_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <2 x i64> %i to <2 x i8>
ret <2 x i8> %x
}
define void @trunc_qb_128_mem(<2 x i64> %i, <2 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
[X86][SSE] Allow folding of store/zext with PEXTRW of 0'th element Under normal circumstances we prefer the higher performance MOVD to extract the 0'th element of a v8i16 vector instead of PEXTRW. But as detailed on PR27265, this prevents the SSE41 implementation of PEXTRW from folding the store of the 0'th element. Additionally it prevents us from making use of the fact that the (SSE2) reg-reg version of PEXTRW implicitly zero-extends the i16 element to the i32/i64 destination register. This patch only preferentially lowers to MOVD if we will not be zero-extending the extracted i16, nor prevent a store from being folded (on SSSE41). Fix for PR27265. Differential Revision: https://reviews.llvm.org/D22509 llvm-svn: 276289
2016-07-21 22:54:17 +08:00
; KNL-NEXT: vpextrw $0, %xmm0, (%rdi)
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqb %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <2 x i64> %i to <2 x i8>
store <2 x i8> %x, <2 x i8>* %res
ret void
}
define <8 x i16> @trunc_qw_512(<8 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qw_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqw %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i16>
ret <8 x i16> %x
}
define void @trunc_qw_512_mem(<8 x i64> %i, <8 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qw_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqw %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i16>
store <8 x i16> %x, <8 x i16>* %res
ret void
}
define <4 x i16> @trunc_qw_256(<4 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qw_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qw_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqd %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i16>
ret <4 x i16> %x
}
define void @trunc_qw_256_mem(<4 x i64> %i, <4 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qw_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; KNL-NEXT: vmovq %xmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qw_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqw %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i16>
store <4 x i16> %x, <4 x i16>* %res
ret void
}
define <2 x i16> @trunc_qw_128(<2 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qw_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <2 x i64> %i to <2 x i16>
ret <2 x i16> %x
}
define void @trunc_qw_128_mem(<2 x i64> %i, <2 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qw_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; KNL-NEXT: vmovd %xmm0, (%rdi)
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qw_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqw %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <2 x i64> %i to <2 x i16>
store <2 x i16> %x, <2 x i16>* %res
ret void
}
define <8 x i32> @trunc_qd_512(<8 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qd_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqd %zmm0, %ymm0
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i32>
ret <8 x i32> %x
}
define void @trunc_qd_512_mem(<8 x i64> %i, <8 x i32>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qd_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovqd %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i64> %i to <8 x i32>
store <8 x i32> %x, <8 x i32>* %res
ret void
}
define <4 x i32> @trunc_qd_256(<4 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qd_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qd_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqd %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i32>
ret <4 x i32> %x
}
define void @trunc_qd_256_mem(<4 x i64> %i, <4 x i32>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qd_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovqd %zmm0, %ymm0
[AVX512] Add ExeDomain to vector extend and truncate instructions. llvm-svn: 276394
2016-07-22 13:46:44 +08:00
; KNL-NEXT: vmovdqa %xmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qd_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqd %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <4 x i64> %i to <4 x i32>
store <4 x i32> %x, <4 x i32>* %res
ret void
}
define <2 x i32> @trunc_qd_128(<2 x i64> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_qd_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <2 x i64> %i to <2 x i32>
ret <2 x i32> %x
}
define void @trunc_qd_128_mem(<2 x i64> %i, <2 x i32>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_qd_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[X86] Teach execution domain fixing to convert between VPERMILPS and VPSHUFD. llvm-svn: 313507
2017-09-18 11:29:47 +08:00
; KNL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL-NEXT: vmovlps %xmm0, (%rdi)
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_qd_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovqd %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <2 x i64> %i to <2 x i32>
store <2 x i32> %x, <2 x i32>* %res
ret void
}
define <16 x i8> @trunc_db_512(<16 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_db_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <16 x i32> %i to <16 x i8>
ret <16 x i8> %x
}
define void @trunc_db_512_mem(<16 x i32> %i, <16 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_db_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <16 x i32> %i to <16 x i8>
store <16 x i8> %x, <16 x i8>* %res
ret void
}
define <8 x i8> @trunc_db_256(<8 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_db_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_db_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdw %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <8 x i32> %i to <8 x i8>
ret <8 x i8> %x
}
define void @trunc_db_256_mem(<8 x i32> %i, <8 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_db_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdw %zmm0, %ymm0
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; KNL-NEXT: vmovq %xmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_db_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdb %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <8 x i32> %i to <8 x i8>
store <8 x i8> %x, <8 x i8>* %res
ret void
}
define <4 x i8> @trunc_db_128(<4 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_db_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <4 x i32> %i to <4 x i8>
ret <4 x i8> %x
}
define void @trunc_db_128_mem(<4 x i32> %i, <4 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_db_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
; KNL-NEXT: vmovd %xmm0, (%rdi)
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_db_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdb %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <4 x i32> %i to <4 x i8>
store <4 x i8> %x, <4 x i8>* %res
ret void
}
define <16 x i16> @trunc_dw_512(<16 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_dw_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdw %zmm0, %ymm0
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <16 x i32> %i to <16 x i16>
ret <16 x i16> %x
}
define void @trunc_dw_512_mem(<16 x i32> %i, <16 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_dw_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: vpmovdw %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <16 x i32> %i to <16 x i16>
store <16 x i16> %x, <16 x i16>* %res
ret void
}
define <8 x i16> @trunc_dw_256(<8 x i32> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_dw_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdw %zmm0, %ymm0
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_dw_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdw %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <8 x i32> %i to <8 x i16>
ret <8 x i16> %x
}
define void @trunc_dw_256_mem(<8 x i32> %i, <8 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_dw_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; KNL-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdw %zmm0, %ymm0
[AVX512] Add ExeDomain to vector extend and truncate instructions. llvm-svn: 276394
2016-07-22 13:46:44 +08:00
; KNL-NEXT: vmovdqa %xmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_dw_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdw %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <8 x i32> %i to <8 x i16>
store <8 x i16> %x, <8 x i16>* %res
ret void
}
define void @trunc_dw_128_mem(<4 x i32> %i, <4 x i16>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_dw_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; KNL-NEXT: vmovq %xmm0, (%rdi)
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_dw_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovdw %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <4 x i32> %i to <4 x i16>
store <4 x i16> %x, <4 x i16>* %res
ret void
}
define <32 x i8> @trunc_wb_512(<32 x i16> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_wb_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdb %zmm1, %xmm1
[AVX512] Add ExeDomain to vector extend and truncate instructions. llvm-svn: 276394
2016-07-22 13:46:44 +08:00
; KNL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_wb_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovwb %zmm0, %ymm0
; SKX-NEXT: retq
%x = trunc <32 x i16> %i to <32 x i8>
ret <32 x i8> %x
}
define void @trunc_wb_512_mem(<32 x i16> %i, <32 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_wb_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdb %zmm1, %xmm1
[AVX512] Add ExeDomain to vector extend and truncate instructions. llvm-svn: 276394
2016-07-22 13:46:44 +08:00
; KNL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; KNL-NEXT: vmovdqa %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_wb_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovwb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <32 x i16> %i to <32 x i8>
store <32 x i8> %x, <32 x i8>* %res
ret void
}
define <16 x i8> @trunc_wb_256(<16 x i16> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_wb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_wb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovwb %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <16 x i16> %i to <16 x i8>
ret <16 x i8> %x
}
define void @trunc_wb_256_mem(<16 x i16> %i, <16 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_wb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_wb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovwb %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: retq
%x = trunc <16 x i16> %i to <16 x i8>
store <16 x i8> %x, <16 x i8>* %res
ret void
}
define <8 x i8> @trunc_wb_128(<8 x i16> %i) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-LABEL: trunc_wb_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; ALL-NEXT: retq
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
%x = trunc <8 x i16> %i to <8 x i8>
ret <8 x i8> %x
}
define void @trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) #0 {
AVX-512: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-LABEL: trunc_wb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Optimized SIMD truncate operations for AVX512F set. Optimized <8 x i32> to <8 x i16> <4 x i64> to < 4 x i32> <16 x i16> to <16 x i8> All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set. Differential Revision: http://reviews.llvm.org/D14108 llvm-svn: 251764
2015-11-01 19:45:47 +08:00
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; KNL-NEXT: vmovq %xmm0, (%rdi)
; KNL-NEXT: retq
;
AVX-512: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-LABEL: trunc_wb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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: Implemented encoding , DAG lowering and intrinsics for Integer Truncate with/without saturation Added tests for DAG lowering ,encoding and intrinsic Differential Revision: http://reviews.llvm.org/D11218 llvm-svn: 243122
2015-07-25 01:24:15 +08:00
; SKX-NEXT: vpmovwb %xmm0, (%rdi)
; SKX-NEXT: retq
%x = trunc <8 x i16> %i to <8 x i8>
store <8 x i8> %x, <8 x i8>* %res
ret void
}
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
define void @usat_trunc_wb_256_mem(<16 x i16> %i, <16 x i8>* %res) {
; KNL-LABEL: usat_trunc_wb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[X86 Codegen] Fixed a bug in unsigned saturation PACKUSWB converts Signed word to Unsigned byte, (the same about DW) and it can't be used for umin+truncate pattern. AVX-512 VPMOVUS* instructions fit the pattern since they convert Unsigned to Unsigned. See https://llvm.org/bugs/show_bug.cgi?id=31773 Differential Revision: https://reviews.llvm.org/D29196 llvm-svn: 293431
2017-01-29 21:18:30 +08:00
; KNL-NEXT: vpminuw {{.*}}(%rip), %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Use ISD::TRUNCATE instead of X86ISD::VTRUNC when input and output types have the same number of elements. llvm-svn: 322455
2018-01-14 16:11:36 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: usat_trunc_wb_256_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: vpmovuswb %ymm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: retq
%x3 = icmp ult <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <16 x i1> %x3, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
define <16 x i8> @usat_trunc_wb_256(<16 x i16> %i) {
; KNL-LABEL: usat_trunc_wb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
[X86 Codegen] Fixed a bug in unsigned saturation PACKUSWB converts Signed word to Unsigned byte, (the same about DW) and it can't be used for umin+truncate pattern. AVX-512 VPMOVUS* instructions fit the pattern since they convert Unsigned to Unsigned. See https://llvm.org/bugs/show_bug.cgi?id=31773 Differential Revision: https://reviews.llvm.org/D29196 llvm-svn: 293431
2017-01-29 21:18:30 +08:00
; KNL-NEXT: vpminuw {{.*}}(%rip), %ymm0, %ymm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86 Codegen] Fixed a bug in unsigned saturation PACKUSWB converts Signed word to Unsigned byte, (the same about DW) and it can't be used for umin+truncate pattern. AVX-512 VPMOVUS* instructions fit the pattern since they convert Unsigned to Unsigned. See https://llvm.org/bugs/show_bug.cgi?id=31773 Differential Revision: https://reviews.llvm.org/D29196 llvm-svn: 293431
2017-01-29 21:18:30 +08:00
; KNL-NEXT: vpmovdb %zmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: usat_trunc_wb_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: vpmovuswb %ymm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: retq
%x3 = icmp ult <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <16 x i1> %x3, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
ret <16 x i8> %x6
}
define void @usat_trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) {
; KNL-LABEL: usat_trunc_wb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: vpminuw {{.*}}(%rip), %xmm0, %xmm0
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
2017-10-03 20:01:31 +08:00
; KNL-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: vmovq %xmm0, (%rdi)
; KNL-NEXT: retq
;
; SKX-LABEL: usat_trunc_wb_128_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: vpmovuswb %xmm0, (%rdi)
; SKX-NEXT: retq
%x3 = icmp ult <8 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <8 x i1> %x3, <8 x i16> %i, <8 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <8 x i16> %x5 to <8 x i8>
store <8 x i8> %x6, <8 x i8>* %res, align 1
ret void
}
define void @usat_trunc_db_512_mem(<16 x i32> %i, <16 x i8>* %res) {
; ALL-LABEL: usat_trunc_db_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpmovusdb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: retq
%x3 = icmp ult <16 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <16 x i1> %x3, <16 x i32> %i, <16 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <16 x i32> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
define void @usat_trunc_qb_512_mem(<8 x i64> %i, <8 x i8>* %res) {
; ALL-LABEL: usat_trunc_qb_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpmovusqb %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: retq
%x3 = icmp ult <8 x i64> %i, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
%x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
%x6 = trunc <8 x i64> %x5 to <8 x i8>
store <8 x i8> %x6, <8 x i8>* %res, align 1
ret void
}
define void @usat_trunc_qd_512_mem(<8 x i64> %i, <8 x i32>* %res) {
; ALL-LABEL: usat_trunc_qd_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpmovusqd %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: retq
%x3 = icmp ult <8 x i64> %i, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
%x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
%x6 = trunc <8 x i64> %x5 to <8 x i32>
store <8 x i32> %x6, <8 x i32>* %res, align 1
ret void
}
define void @usat_trunc_qw_512_mem(<8 x i64> %i, <8 x i16>* %res) {
; ALL-LABEL: usat_trunc_qw_512_mem:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpmovusqw %zmm0, (%rdi)
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; ALL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: retq
%x3 = icmp ult <8 x i64> %i, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x5 = select <8 x i1> %x3, <8 x i64> %i, <8 x i64> <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x6 = trunc <8 x i64> %x5 to <8 x i16>
store <8 x i16> %x6, <8 x i16>* %res, align 1
ret void
}
define <32 x i8> @usat_trunc_db_1024(<32 x i32> %i) {
[LegalizeVectorTypes] Have SplitVecOp_TruncateHelper fall back to SplitVecOp_UnaryOp if splitting the output type would be a legal type. SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that. The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked. llvm-svn: 347479
2018-11-23 06:56:52 +08:00
; ALL-LABEL: usat_trunc_db_1024:
; ALL: ## %bb.0:
; ALL-NEXT: vpmovusdb %zmm0, %xmm0
; ALL-NEXT: vpmovusdb %zmm1, %xmm1
; ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: retq
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
%x3 = icmp ult <32 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <32 x i1> %x3, <32 x i32> %i, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <32 x i32> %x5 to <32 x i8>
ret <32 x i8> %x6
}
define void @usat_trunc_db_1024_mem(<32 x i32> %i, <32 x i8>* %p) {
[LegalizeVectorTypes] Have SplitVecOp_TruncateHelper fall back to SplitVecOp_UnaryOp if splitting the output type would be a legal type. SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that. The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked. llvm-svn: 347479
2018-11-23 06:56:52 +08:00
; ALL-LABEL: usat_trunc_db_1024_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpmovusdb %zmm0, %xmm0
; ALL-NEXT: vpmovusdb %zmm1, %xmm1
; ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: vmovdqu %ymm0, (%rdi)
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
%x3 = icmp ult <32 x i32> %i, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <32 x i1> %x3, <32 x i32> %i, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <32 x i32> %x5 to <32 x i8>
store <32 x i8>%x6, <32 x i8>* %p, align 1
ret void
}
define <16 x i16> @usat_trunc_dw_512(<16 x i32> %i) {
; ALL-LABEL: usat_trunc_dw_512:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpmovusdw %zmm0, %ymm0
; ALL-NEXT: retq
%x3 = icmp ult <16 x i32> %i, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
%x5 = select <16 x i1> %x3, <16 x i32> %i, <16 x i32> <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
%x6 = trunc <16 x i32> %x5 to <16 x i16>
ret <16 x i16> %x6
}
define <8 x i8> @usat_trunc_wb_128(<8 x i16> %i) {
; ALL-LABEL: usat_trunc_wb_128:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ALL: ## %bb.0:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; ALL-NEXT: vpminuw {{.*}}(%rip), %xmm0, %xmm0
; ALL-NEXT: retq
%x3 = icmp ult <8 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <8 x i1> %x3, <8 x i16> %i, <8 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <8 x i16> %x5 to <8 x i8>
ret <8 x i8>%x6
}
define <16 x i16> @usat_trunc_qw_1024(<16 x i64> %i) {
[AVX512] Don't switch unmasked subvector insert/extract instructions when AVX512DQI is enabled. There's no reason to switch instructions with and without DQI. It just creates extra isel patterns and test divergences. There is however value in enabling the masked version of the instructions with DQI. This required introducing some new multiclasses to enabling this splitting. Differential Revision: https://reviews.llvm.org/D36661 llvm-svn: 311091
2017-08-17 23:40:25 +08:00
; ALL-LABEL: usat_trunc_qw_1024:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/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:
[LegalizeVectorTypes] Have SplitVecOp_TruncateHelper fall back to SplitVecOp_UnaryOp if splitting the output type would be a legal type. SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that. The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked. llvm-svn: 347479
2018-11-23 06:56:52 +08:00
; ALL-NEXT: vpmovusqw %zmm0, %xmm0
; ALL-NEXT: vpmovusqw %zmm1, %xmm1
; ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
[AVX512] Don't switch unmasked subvector insert/extract instructions when AVX512DQI is enabled. There's no reason to switch instructions with and without DQI. It just creates extra isel patterns and test divergences. There is however value in enabling the masked version of the instructions with DQI. This required introducing some new multiclasses to enabling this splitting. Differential Revision: https://reviews.llvm.org/D36661 llvm-svn: 311091
2017-08-17 23:40:25 +08:00
; ALL-NEXT: retq
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
%x3 = icmp ult <16 x i64> %i, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x5 = select <16 x i1> %x3, <16 x i64> %i, <16 x i64> <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x6 = trunc <16 x i64> %x5 to <16 x i16>
ret <16 x i16> %x6
}
define <16 x i8> @usat_trunc_db_256(<8 x i32> %x) {
; KNL-LABEL: usat_trunc_db_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; KNL: ## %bb.0:
Regenerate test (missing broadcast constant comments). NFCI. llvm-svn: 314680
2017-10-02 23:21:14 +08:00
; KNL-NEXT: vpbroadcastd {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255]
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: vpminud %ymm1, %ymm0, %ymm0
; KNL-NEXT: vpmovdw %zmm0, %ymm0
[X86] Add X86ISD::VTRUNC to computeKnownBitsForTargetNode. We have to take special care to avoid the cases where the result of the truncate would be padded with zero elements. Ideally we'd just use ISD::TRUNCATE for these cases instead. llvm-svn: 322454
2018-01-14 16:11:33 +08:00
; KNL-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; KNL-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; KNL-NEXT: retq
;
; SKX-LABEL: usat_trunc_db_256:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SKX: ## %bb.0:
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: vpminud {{.*}}(%rip){1to8}, %ymm0, %ymm0
; SKX-NEXT: vpmovdw %ymm0, %xmm0
[X86] Add X86ISD::VTRUNC to computeKnownBitsForTargetNode. We have to take special care to avoid the cases where the result of the truncate would be padded with zero elements. Ideally we'd just use ISD::TRUNCATE for these cases instead. llvm-svn: 322454
2018-01-14 16:11:33 +08:00
; SKX-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; SKX-NEXT: vzeroupper
Recommiting unsigned saturation with a bugfix. A test case that crached is added to avx512-trunc.ll. (PR31589) llvm-svn: 292479
2017-01-19 20:08:21 +08:00
; SKX-NEXT: retq
%tmp1 = icmp ult <8 x i32> %x, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%tmp2 = select <8 x i1> %tmp1, <8 x i32> %x, <8 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%tmp3 = trunc <8 x i32> %tmp2 to <8 x i8>
%tmp4 = shufflevector <8 x i8> %tmp3, <8 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %tmp4
}
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; Tests for the following unsigned saturation pattern:
; %a = icmp sgt %x, C1
; %b = select %a, %x, C2
; %c = icmp slt %b, C2
; %d = select %c, %b, C2
; %res = trunc %d
[X86] Tests for unsigned saturation downconvert detection. One more test for smax(smin(x, C2), C1) pattern. llvm-svn: 330090
2018-04-15 04:10:17 +08:00
define void @smax_usat_trunc_wb_256_mem1(<16 x i16> %i, <16 x i8>* %res) {
; KNL-LABEL: smax_usat_trunc_wb_256_mem1:
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; KNL: ## %bb.0:
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
; KNL-NEXT: vpminsw {{.*}}(%rip), %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
;
[X86] Tests for unsigned saturation downconvert detection. One more test for smax(smin(x, C2), C1) pattern. llvm-svn: 330090
2018-04-15 04:10:17 +08:00
; SKX-LABEL: smax_usat_trunc_wb_256_mem1:
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; SKX: ## %bb.0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; SKX-NEXT: vpmovuswb %ymm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
%x1 = icmp sgt <16 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x2 = select <16 x i1> %x1, <16 x i16> %i, <16 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x3 = icmp slt <16 x i16> %x2, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <16 x i1> %x3, <16 x i16> %x2, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
[X86] Tests for unsigned saturation downconvert detection. One more test for smax(smin(x, C2), C1) pattern. llvm-svn: 330090
2018-04-15 04:10:17 +08:00
; Test for smax(smin(x, C2), C1).
define void @smax_usat_trunc_wb_256_mem2(<16 x i16> %i, <16 x i8>* %res) {
; KNL-LABEL: smax_usat_trunc_wb_256_mem2:
; KNL: ## %bb.0:
; KNL-NEXT: vpminsw {{.*}}(%rip), %ymm0, %ymm0
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Tests for unsigned saturation downconvert detection. One more test for smax(smin(x, C2), C1) pattern. llvm-svn: 330090
2018-04-15 04:10:17 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
;
; SKX-LABEL: smax_usat_trunc_wb_256_mem2:
; SKX: ## %bb.0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; SKX-NEXT: vpmovuswb %ymm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. One more test for smax(smin(x, C2), C1) pattern. llvm-svn: 330090
2018-04-15 04:10:17 +08:00
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
%x1 = icmp slt <16 x i16> %i, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x2 = select <16 x i1> %x1, <16 x i16> %i, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x3 = icmp sgt <16 x i16> %x2, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x5 = select <16 x i1> %x3, <16 x i16> %x2, <16 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
define <16 x i8> @smax_usat_trunc_wb_256(<16 x i16> %i) {
; KNL-LABEL: smax_usat_trunc_wb_256:
; KNL: ## %bb.0:
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
; KNL-NEXT: vpminsw {{.*}}(%rip), %ymm0, %ymm0
[X86] Move the promotion of v16i16->v16i8 for avx512f but not avx512bw from lowering to isel. Change to use vpmovzx instead of vpmovsx. With avx512f but not avx512bw we need to extend to v16i32 then truncate that to to v16i8. Previously we emitted both nodes during lowering, but I'm trying to switch to using target independent nodes and with that switched the extend+truncate wou This patch changes the implementation to what will be necessary with that patch which helps minimize test diffs. llvm-svn: 346552
2018-11-10 04:09:53 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; KNL-NEXT: vpmovdb %zmm0, %xmm0
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
;
; SKX-LABEL: smax_usat_trunc_wb_256:
; SKX: ## %bb.0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; SKX-NEXT: vpmovuswb %ymm0, %xmm0
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
%x1 = icmp sgt <16 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x2 = select <16 x i1> %x1, <16 x i16> %i, <16 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x3 = icmp slt <16 x i16> %x2, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <16 x i1> %x3, <16 x i16> %x2, <16 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
ret <16 x i8> %x6
}
define void @smax_usat_trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) {
; KNL-LABEL: smax_usat_trunc_wb_128_mem:
; KNL: ## %bb.0:
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpmaxsw %xmm1, %xmm0, %xmm0
; KNL-NEXT: vpminsw {{.*}}(%rip), %xmm0, %xmm0
; KNL-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; KNL-NEXT: vmovq %xmm0, (%rdi)
; KNL-NEXT: retq
;
; SKX-LABEL: smax_usat_trunc_wb_128_mem:
; SKX: ## %bb.0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpmaxsw %xmm1, %xmm0, %xmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; SKX-NEXT: vpmovuswb %xmm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; SKX-NEXT: retq
%x1 = icmp sgt <8 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x2 = select <8 x i1> %x1, <8 x i16> %i, <8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x3 = icmp slt <8 x i16> %x2, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x5 = select <8 x i1> %x3, <8 x i16> %x2, <8 x i16> <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%x6 = trunc <8 x i16> %x5 to <8 x i8>
store <8 x i8> %x6, <8 x i8>* %res, align 1
ret void
}
define void @smax_usat_trunc_db_512_mem(<16 x i32> %i, <16 x i8>* %res) {
; ALL-LABEL: smax_usat_trunc_db_512_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; ALL-NEXT: vpmaxsd %zmm1, %zmm0, %zmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; ALL-NEXT: vpmovusdb %zmm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
%x1 = icmp sgt <16 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x2 = select <16 x i1> %x1, <16 x i32> %i, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x3 = icmp slt <16 x i32> %x2, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <16 x i1> %x3, <16 x i32> %x2, <16 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <16 x i32> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
define void @smax_usat_trunc_qb_512_mem(<8 x i64> %i, <8 x i8>* %res) {
; ALL-LABEL: smax_usat_trunc_qb_512_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; ALL-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; ALL-NEXT: vpmovusqb %zmm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
%x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x2 = select <8 x i1> %x1, <8 x i64> %i, <8 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x3 = icmp slt <8 x i64> %x2, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
%x5 = select <8 x i1> %x3, <8 x i64> %x2, <8 x i64> <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
%x6 = trunc <8 x i64> %x5 to <8 x i8>
store <8 x i8> %x6, <8 x i8>* %res, align 1
ret void
}
define void @smax_usat_trunc_qd_512_mem(<8 x i64> %i, <8 x i32>* %res) {
; ALL-LABEL: smax_usat_trunc_qd_512_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; ALL-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; ALL-NEXT: vpmovusqd %zmm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
%x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x2 = select <8 x i1> %x1, <8 x i64> %i, <8 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x3 = icmp slt <8 x i64> %x2, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
%x5 = select <8 x i1> %x3, <8 x i64> %x2, <8 x i64> <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
%x6 = trunc <8 x i64> %x5 to <8 x i32>
store <8 x i32> %x6, <8 x i32>* %res, align 1
ret void
}
define void @smax_usat_trunc_qw_512_mem(<8 x i64> %i, <8 x i16>* %res) {
; ALL-LABEL: smax_usat_trunc_qw_512_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; ALL-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; ALL-NEXT: vpmovusqw %zmm0, (%rdi)
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
%x1 = icmp sgt <8 x i64> %i, <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x2 = select <8 x i1> %x1, <8 x i64> %i, <8 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>
%x3 = icmp slt <8 x i64> %x2, <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x5 = select <8 x i1> %x3, <8 x i64> %x2, <8 x i64> <i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535, i64 65535>
%x6 = trunc <8 x i64> %x5 to <8 x i16>
store <8 x i16> %x6, <8 x i16>* %res, align 1
ret void
}
define <32 x i8> @smax_usat_trunc_db_1024(<32 x i32> %i) {
[LegalizeVectorTypes] Have SplitVecOp_TruncateHelper fall back to SplitVecOp_UnaryOp if splitting the output type would be a legal type. SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that. The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked. llvm-svn: 347479
2018-11-23 06:56:52 +08:00
; ALL-LABEL: smax_usat_trunc_db_1024:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm2, %xmm2, %xmm2
; ALL-NEXT: vpmaxsd %zmm2, %zmm1, %zmm1
; ALL-NEXT: vpmaxsd %zmm2, %zmm0, %zmm0
; ALL-NEXT: vpmovusdb %zmm0, %xmm0
; ALL-NEXT: vpmovusdb %zmm1, %xmm1
; ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: retq
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
%x1 = icmp sgt <32 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x2 = select <32 x i1> %x1, <32 x i32> %i, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x3 = icmp slt <32 x i32> %x2, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <32 x i1> %x3, <32 x i32> %x2, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <32 x i32> %x5 to <32 x i8>
ret <32 x i8> %x6
}
define void @smax_usat_trunc_db_1024_mem(<32 x i32> %i, <32 x i8>* %p) {
[LegalizeVectorTypes] Have SplitVecOp_TruncateHelper fall back to SplitVecOp_UnaryOp if splitting the output type would be a legal type. SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that. The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked. llvm-svn: 347479
2018-11-23 06:56:52 +08:00
; ALL-LABEL: smax_usat_trunc_db_1024_mem:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm2, %xmm2, %xmm2
; ALL-NEXT: vpmaxsd %zmm2, %zmm1, %zmm1
; ALL-NEXT: vpmaxsd %zmm2, %zmm0, %zmm0
; ALL-NEXT: vpmovusdb %zmm0, %xmm0
; ALL-NEXT: vpmovusdb %zmm1, %xmm1
; ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; ALL-NEXT: vmovdqu %ymm0, (%rdi)
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
%x1 = icmp sgt <32 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x2 = select <32 x i1> %x1, <32 x i32> %i, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x3 = icmp slt <32 x i32> %x2, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x5 = select <32 x i1> %x3, <32 x i32> %x2, <32 x i32> <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
%x6 = trunc <32 x i32> %x5 to <32 x i8>
store <32 x i8>%x6, <32 x i8>* %p, align 1
ret void
}
define <16 x i16> @smax_usat_trunc_dw_512(<16 x i32> %i) {
; ALL-LABEL: smax_usat_trunc_dw_512:
; ALL: ## %bb.0:
; ALL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; ALL-NEXT: vpmaxsd %zmm1, %zmm0, %zmm0
[X86] Improve unsigned saturation downconvert detection. Summary: New unsigned saturation downconvert patterns detection was implemented in X86 Codegen: (truncate (smin (smax (x, C1), C2)) to dest_type), where C1 >= 0 and C2 is unsigned max of destination type. (truncate (smax (smin (x, C2), C1)) to dest_type) where C1 >= 0, C2 is unsigned max of destination type and C1 <= C2. These two patterns are equivalent to: (truncate (umin (smax(x, C1), unsigned_max_of_dest_type)) to dest_type) Reviewers: RKSimon Subscribers: llvm-commits, a.elovikov Differential Revision: https://reviews.llvm.org/D45315 llvm-svn: 332336
2018-05-15 18:24:12 +08:00
; ALL-NEXT: vpmovusdw %zmm0, %ymm0
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; ALL-NEXT: retq
%x1 = icmp sgt <16 x i32> %i, <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x2 = select <16 x i1> %x1, <16 x i32> %i, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
%x3 = icmp slt <16 x i32> %x2, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
%x5 = select <16 x i1> %x3, <16 x i32> %x2, <16 x i32> <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
%x6 = trunc <16 x i32> %x5 to <16 x i16>
ret <16 x i16> %x6
}
define void @negative_test1_smax_usat_trunc_wb_256_mem(<16 x i16> %i, <16 x i8>* %res) {
; KNL-LABEL: negative_test1_smax_usat_trunc_wb_256_mem:
; KNL: ## %bb.0:
; KNL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; KNL-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
; KNL-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; KNL-NEXT: vpminsw %ymm1, %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
;
; SKX-LABEL: negative_test1_smax_usat_trunc_wb_256_mem:
; SKX: ## %bb.0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpmaxsw %ymm1, %ymm0, %ymm0
; SKX-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; SKX-NEXT: vpminsw %ymm1, %ymm0, %ymm0
; SKX-NEXT: vpmovwb %ymm0, (%rdi)
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
%x1 = icmp sgt <16 x i16> %i, <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x2 = select <16 x i1> %x1, <16 x i16> %i, <16 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>
%x3 = icmp slt <16 x i16> %x2, <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>
%x5 = select <16 x i1> %x3, <16 x i16> %x2, <16 x i16> <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>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}
define void @negative_test2_smax_usat_trunc_wb_256_mem(<16 x i16> %i, <16 x i8>* %res) {
; KNL-LABEL: negative_test2_smax_usat_trunc_wb_256_mem:
; KNL: ## %bb.0:
; KNL-NEXT: vpmaxsw {{.*}}(%rip), %ymm0, %ymm0
; KNL-NEXT: vpminsw {{.*}}(%rip), %ymm0, %ymm0
[X86] Turn X86ISD::VSEXT into X86ISD::VZEXT if the upper bits aren't demanded. This makes X86ISD::VSEXT more similar to ISD::SIGN_EXTEND and ISD::ZERO_EXTEND. I'm hoping to replace X86ISD::VSEXT/VZEXT with target independent nodes. Making the target specific nodes similar to the target independent nodes helps minimize test diffs in that patch. llvm-svn: 346539
2018-11-10 03:05:51 +08:00
; KNL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
[X86] Tests for unsigned saturation downconvert detection. llvm-svn: 330088
2018-04-15 03:09:02 +08:00
; KNL-NEXT: vpmovdb %zmm0, (%rdi)
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
;
; SKX-LABEL: negative_test2_smax_usat_trunc_wb_256_mem:
; SKX: ## %bb.0:
; SKX-NEXT: vpmaxsw {{.*}}(%rip), %ymm0, %ymm0
; SKX-NEXT: vpminsw {{.*}}(%rip), %ymm0, %ymm0
; SKX-NEXT: vpmovwb %ymm0, (%rdi)
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
%x1 = icmp sgt <16 x i16> %i, <i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10>
%x2 = select <16 x i1> %x1, <16 x i16> %i, <16 x i16> <i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10, i16 -10>
%x3 = icmp slt <16 x i16> %x2, <i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5>
%x5 = select <16 x i1> %x3, <16 x i16> %x2, <16 x i16> <i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5, i16 -5>
%x6 = trunc <16 x i16> %x5 to <16 x i8>
store <16 x i8> %x6, <16 x i8>* %res, align 1
ret void
}