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/f16c-intrinsics.ll

350 lines
16 KiB
LLVM
Raw Normal View History

[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86] Add patterns for folding a v16i8 with the VEX vcvtph2ps intrinsics. Disable the peephole pass to prove that the pattern is working. llvm-svn: 317547
2017-11-07 15:13:06 +08:00
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx,+f16c -show-mc-encoding -disable-peephole | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+f16c -show-mc-encoding -disable-peephole | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vl -show-mc-encoding -disable-peephole | FileCheck %s --check-prefix=X32-AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl -show-mc-encoding -disable-peephole | FileCheck %s --check-prefix=X64-AVX512VL
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
define <4 x float> @test_x86_vcvtph2ps_128(<8 x i16> %a0) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtph2ps_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
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: vcvtph2ps %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0xc0]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtph2ps_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
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtph2ps %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtph2ps_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
; X32-AVX512VL: # %bb.0:
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X32-AVX512VL-NEXT: vcvtph2ps %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0xc0]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtph2ps_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
; X64-AVX512VL: # %bb.0:
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0xc0]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
%res = call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> %a0) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16>) nounwind readonly
[X86] Add a test for a 128-bit vector load feeding a cvtph2ps intrinsic. The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed. llvm-svn: 317546
2017-11-07 15:13:05 +08:00
define <4 x float> @test_x86_vcvtph2ps_128_m(<8 x i16>* nocapture %a) {
; X32-LABEL: test_x86_vcvtph2ps_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86] Add a test for a 128-bit vector load feeding a cvtph2ps intrinsic. The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed. llvm-svn: 317546
2017-11-07 15:13:05 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtph2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x00]
; X32-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_x86_vcvtph2ps_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Add a test for a 128-bit vector load feeding a cvtph2ps intrinsic. The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed. llvm-svn: 317546
2017-11-07 15:13:05 +08:00
; X64-NEXT: vcvtph2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x07]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtph2ps_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0:
[X86] Add a test for a 128-bit vector load feeding a cvtph2ps intrinsic. The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed. llvm-svn: 317546
2017-11-07 15:13:05 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-AVX512VL-NEXT: vcvtph2ps (%eax), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x00]
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtph2ps_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0:
[X86] Add a test for a 128-bit vector load feeding a cvtph2ps intrinsic. The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed. llvm-svn: 317546
2017-11-07 15:13:05 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps (%rdi), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x07]
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
%load = load <8 x i16>, <8 x i16>* %a
%res = call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> %load) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
define <8 x float> @test_x86_vcvtph2ps_256(<8 x i16> %a0) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtph2ps_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
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: vcvtph2ps %xmm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x13,0xc0]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtph2ps_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
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtph2ps %xmm0, %ymm0 # encoding: [0xc4,0xe2,0x7d,0x13,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtph2ps_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
; X32-AVX512VL: # %bb.0:
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X32-AVX512VL-NEXT: vcvtph2ps %xmm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x13,0xc0]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtph2ps_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
; X64-AVX512VL: # %bb.0:
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps %xmm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x13,0xc0]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
%res = call <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16> %a0) ; <<8 x float>> [#uses=1]
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16>) nounwind readonly
Make the test actually test what it's supposed to test. Add a test for the from memory variant of vcvtph2ps for 256-bit. llvm-svn: 227446
2015-01-29 23:19:54 +08:00
define <8 x float> @test_x86_vcvtph2ps_256_m(<8 x i16>* nocapture %a) nounwind {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtph2ps_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtph2ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7d,0x13,0x00]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtph2ps_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtph2ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7d,0x13,0x07]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtph2ps_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X32-AVX512VL-NEXT: vcvtph2ps (%eax), %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x13,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtph2ps_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0:
[X86] Add support for using EVEX instructions for the legacy vcvtph2ps intrinsics. Looks like there's some missed load folding opportunities for i64 loads. llvm-svn: 317544
2017-11-07 15:13:03 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps (%rdi), %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x13,0x07]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[X86] Remove alignment from a load in the f16c intrinsic test. The alignment shouldn't be required for load folding. llvm-svn: 317545
2017-11-07 15:13:04 +08:00
%load = load <8 x i16>, <8 x i16>* %a
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
%res = tail call <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16> %load)
ret <8 x float> %res
Make the test actually test what it's supposed to test. Add a test for the from memory variant of vcvtph2ps for 256-bit. llvm-svn: 227446
2015-01-29 23:19:54 +08:00
}
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
define <8 x i16> @test_x86_vcvtps2ph_128(<4 x float> %a0) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_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
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_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
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_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
; X32-AVX512VL: # %bb.0:
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_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
; X64-AVX512VL: # %bb.0:
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
%res = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float>, i32) nounwind readonly
define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_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
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
; X32-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_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
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_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
; X32-AVX512VL: # %bb.0:
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_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
; X64-AVX512VL: # %bb.0:
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
Add intrinsics for X86 vcvtps2ph and vcvtph2ps instructions llvm-svn: 143682
2011-11-04 14:59:21 +08:00
%res = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float>, i32) nounwind readonly
X86: Pattern match scalar loads + vcvtph2ps into just vcvtph2ps. vcvtph2ps only reads the lower 64 bits of the address passed to the intrinsic. llvm-svn: 206579
2014-04-18 18:45:33 +08:00
define <4 x float> @test_x86_vcvtps2ph_128_scalar(i64* %ptr) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_128_scalar:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtph2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x00]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_128_scalar:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtph2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x07]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_128_scalar:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Add patterns to fold a 64-bit load into the EVEX vcvtph2ps instructions. llvm-svn: 317548
2017-11-07 15:13:07 +08:00
; X32-AVX512VL-NEXT: vcvtph2ps (%eax), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_scalar:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0:
[X86] Add patterns to fold a 64-bit load into the EVEX vcvtph2ps instructions. llvm-svn: 317548
2017-11-07 15:13:07 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps (%rdi), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x07]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%load = load i64, i64* %ptr
X86: Pattern match scalar loads + vcvtph2ps into just vcvtph2ps. vcvtph2ps only reads the lower 64 bits of the address passed to the intrinsic. llvm-svn: 206579
2014-04-18 18:45:33 +08:00
%ins1 = insertelement <2 x i64> undef, i64 %load, i32 0
%ins2 = insertelement <2 x i64> %ins1, i64 0, i32 1
%bc = bitcast <2 x i64> %ins2 to <8 x i16>
%res = tail call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> %bc) #2
ret <4 x float> %res
}
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
The isel pattern that selects the memory-register form of VCVTPH2PS (64 to 128-bit) matches against the pattern fragment 'vzmovl_v2i64' (a zero-extended 64-bit load). However, a change in r248784 teaches the instruction combiner that only the lower 64 bits of the input to a 128-bit vcvtph2ps are used. This means the instruction combiner will ordinarily optimize away the upper 64-bit insertelement instruction in the zero-extension and so we no longer select the memory-register form. To fix this a new pattern has been added. Differential Revision: http://reviews.llvm.org/D16067 llvm-svn: 257470
2016-01-12 19:48:25 +08:00
define <4 x float> @test_x86_vcvtps2ph_128_scalar2(i64* %ptr) {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_128_scalar2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtph2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x00]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_128_scalar2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtph2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x79,0x13,0x07]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_128_scalar2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0:
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Add patterns to fold a 64-bit load into the EVEX vcvtph2ps instructions. llvm-svn: 317548
2017-11-07 15:13:07 +08:00
; X32-AVX512VL-NEXT: vcvtph2ps (%eax), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x00]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_scalar2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0:
[X86] Add patterns to fold a 64-bit load into the EVEX vcvtph2ps instructions. llvm-svn: 317548
2017-11-07 15:13:07 +08:00
; X64-AVX512VL-NEXT: vcvtph2ps (%rdi), %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x13,0x07]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
The isel pattern that selects the memory-register form of VCVTPH2PS (64 to 128-bit) matches against the pattern fragment 'vzmovl_v2i64' (a zero-extended 64-bit load). However, a change in r248784 teaches the instruction combiner that only the lower 64 bits of the input to a 128-bit vcvtph2ps are used. This means the instruction combiner will ordinarily optimize away the upper 64-bit insertelement instruction in the zero-extension and so we no longer select the memory-register form. To fix this a new pattern has been added. Differential Revision: http://reviews.llvm.org/D16067 llvm-svn: 257470
2016-01-12 19:48:25 +08:00
%load = load i64, i64* %ptr
%ins = insertelement <2 x i64> undef, i64 %load, i32 0
%bc = bitcast <2 x i64> %ins to <8 x i16>
%res = tail call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> %bc)
ret <4 x float> %res
}
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
define void @test_x86_vcvtps2ph_256_m(<8 x i16>* nocapture %d, <8 x float> %a) nounwind {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtps2ph $3, %ymm0, (%eax) # encoding: [0xc4,0xe3,0x7d,0x1d,0x00,0x03]
; X32-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $3, %ymm0, (%rdi) # encoding: [0xc4,0xe3,0x7d,0x1d,0x07,0x03]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $3, %ymm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0x00,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_256_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0: # %entry
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $3, %ymm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0x07,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a, i32 3)
store <8 x i16> %0, <8 x i16>* %d, align 16
ret void
}
define void @test_x86_vcvtps2ph_128_m(<4 x i16>* nocapture %d, <4 x float> %a) nounwind {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: vpmovzxwd %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x33,0xc0]
; X32-AVX512VL-NEXT: # xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; X32-AVX512VL-NEXT: vpmovdw %xmm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x08,0x33,0x00]
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0: # %entry
[X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. Rely on EVEX->VEX to convert back. Missed store folding opportunities will be fixed in a subsequent commit. llvm-svn: 317661
2017-11-08 12:00:30 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: vpmovzxwd %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x33,0xc0]
; X64-AVX512VL-NEXT: # xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; X64-AVX512VL-NEXT: vpmovdw %xmm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x08,0x33,0x07]
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a, i32 3)
%1 = shufflevector <8 x i16> %0, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
store <4 x i16> %1, <4 x i16>* %d, align 8
ret void
}
define void @test_x86_vcvtps2ph_128_m2(double* nocapture %hf4x16, <4 x float> %f4x32) #0 {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_128_m2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_128_m2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Add patterns to fold EVEX store with EVEX encoded vcvtps2ph instructions. Remove bad pattern that had vf432 vcvtps2ph storing 128-bits. llvm-svn: 317662
2017-11-08 12:00:31 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0: # %entry
[X86] Add patterns to fold EVEX store with EVEX encoded vcvtps2ph instructions. Remove bad pattern that had vf432 vcvtps2ph storing 128-bits. llvm-svn: 317662
2017-11-08 12:00:31 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4x32, i32 3)
%1 = bitcast <8 x i16> %0 to <2 x double>
%vecext = extractelement <2 x double> %1, i32 0
store double %vecext, double* %hf4x16, align 8
ret void
}
define void @test_x86_vcvtps2ph_128_m3(i64* nocapture %hf4x16, <4 x float> %f4x32) #0 {
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
; X32-LABEL: test_x86_vcvtps2ph_128_m3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X32-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
; X32-NEXT: retl # encoding: [0xc3]
[X86][F16C] Regenerated f16c tests llvm-svn: 279621
2016-08-24 19:56:15 +08:00
;
; X64-LABEL: test_x86_vcvtps2ph_128_m3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
; X64-NEXT: retq # encoding: [0xc3]
;
; X32-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32-AVX512VL: # %bb.0: # %entry
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
[X86] Add patterns to fold EVEX store with EVEX encoded vcvtps2ph instructions. Remove bad pattern that had vf432 vcvtps2ph storing 128-bits. llvm-svn: 317662
2017-11-08 12:00:31 +08:00
; X32-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X32-AVX512VL-NEXT: retl # encoding: [0xc3]
;
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64-AVX512VL: # %bb.0: # %entry
[X86] Add patterns to fold EVEX store with EVEX encoded vcvtps2ph instructions. Remove bad pattern that had vf432 vcvtps2ph storing 128-bits. llvm-svn: 317662
2017-11-08 12:00:31 +08:00
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
[X86] Add AVX512VL command line to f16c intrinsic test to show missed EVEX opportunities for the legacy intrinsics. llvm-svn: 317543
2017-11-07 15:13:01 +08:00
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
[x86] Add store-folded memop patterns for vcvtps2ph Differential Revision: http://reviews.llvm.org/D7296 llvm-svn: 235517
2015-04-23 00:11:19 +08:00
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4x32, i32 3)
%1 = bitcast <8 x i16> %0 to <2 x i64>
%vecext = extractelement <2 x i64> %1, i32 0
store i64 %vecext, i64* %hf4x16, align 8
ret void
}