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/AMDGPU/llvm.AMDGPU.clamp.ll

57 lines
2.5 KiB
LLVM
Raw Normal View History

AMDGPU: Remove last AMDIL intrinsics llvm-svn: 275309
2016-07-14 03:42:06 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=SI -check-prefix=FUNC %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=SI -check-prefix=FUNC %s
R600: Add a few tests I forgot to add. These belong with r210827 llvm-svn: 211253
2014-06-19 12:24:43 +08:00
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
R600/SI: Get rid of FCLAMP_SI pseudo It's not necessary. Also use complex patterns to allow src modifier usage. llvm-svn: 221916
2014-11-14 03:49:04 +08:00
declare float @llvm.fabs.f32(float) nounwind readnone
R600: Add a few tests I forgot to add. These belong with r210827 llvm-svn: 211253
2014-06-19 12:24:43 +08:00
declare float @llvm.AMDGPU.clamp.f32(float, float, float) nounwind readnone
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}clamp_0_1_f32:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_load_dword [[ARG:s[0-9]+]],
AMDGPU: Support commuting with immediate in src0 llvm-svn: 280970
2016-09-09 01:19:29 +08:00
; SI: v_add_f32_e64 [[RESULT:v[0-9]+]], [[ARG]], 0 clamp{{$}}
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
R600: Add a few tests I forgot to add. These belong with r210827 llvm-svn: 211253
2014-06-19 12:24:43 +08:00
; EG: MOV_SAT
define void @clamp_0_1_f32(float addrspace(1)* %out, float %src) nounwind {
%clamp = call float @llvm.AMDGPU.clamp.f32(float %src, float 0.0, float 1.0) nounwind readnone
store float %clamp, float addrspace(1)* %out, align 4
ret void
}
R600/SI: Get rid of FCLAMP_SI pseudo It's not necessary. Also use complex patterns to allow src modifier usage. llvm-svn: 221916
2014-11-14 03:49:04 +08:00
; FUNC-LABEL: {{^}}clamp_fabs_0_1_f32:
; SI: s_load_dword [[ARG:s[0-9]+]],
AMDGPU: Support commuting with immediate in src0 llvm-svn: 280970
2016-09-09 01:19:29 +08:00
; SI: v_add_f32_e64 [[RESULT:v[0-9]+]], |[[ARG]]|, 0 clamp{{$}}
R600/SI: Get rid of FCLAMP_SI pseudo It's not necessary. Also use complex patterns to allow src modifier usage. llvm-svn: 221916
2014-11-14 03:49:04 +08:00
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @clamp_fabs_0_1_f32(float addrspace(1)* %out, float %src) nounwind {
%src.fabs = call float @llvm.fabs.f32(float %src) nounwind readnone
%clamp = call float @llvm.AMDGPU.clamp.f32(float %src.fabs, float 0.0, float 1.0) nounwind readnone
store float %clamp, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}clamp_fneg_0_1_f32:
; SI: s_load_dword [[ARG:s[0-9]+]],
AMDGPU: Support commuting with immediate in src0 llvm-svn: 280970
2016-09-09 01:19:29 +08:00
; SI: v_add_f32_e64 [[RESULT:v[0-9]+]], -[[ARG]], 0 clamp{{$}}
R600/SI: Get rid of FCLAMP_SI pseudo It's not necessary. Also use complex patterns to allow src modifier usage. llvm-svn: 221916
2014-11-14 03:49:04 +08:00
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @clamp_fneg_0_1_f32(float addrspace(1)* %out, float %src) nounwind {
%src.fneg = fsub float -0.0, %src
%clamp = call float @llvm.AMDGPU.clamp.f32(float %src.fneg, float 0.0, float 1.0) nounwind readnone
store float %clamp, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}clamp_fneg_fabs_0_1_f32:
; SI: s_load_dword [[ARG:s[0-9]+]],
AMDGPU: Support commuting with immediate in src0 llvm-svn: 280970
2016-09-09 01:19:29 +08:00
; SI: v_add_f32_e64 [[RESULT:v[0-9]+]], -|[[ARG]]|, 0 clamp{{$}}
R600/SI: Get rid of FCLAMP_SI pseudo It's not necessary. Also use complex patterns to allow src modifier usage. llvm-svn: 221916
2014-11-14 03:49:04 +08:00
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @clamp_fneg_fabs_0_1_f32(float addrspace(1)* %out, float %src) nounwind {
%src.fabs = call float @llvm.fabs.f32(float %src) nounwind readnone
%src.fneg.fabs = fsub float -0.0, %src.fabs
%clamp = call float @llvm.AMDGPU.clamp.f32(float %src.fneg.fabs, float 0.0, float 1.0) nounwind readnone
store float %clamp, float addrspace(1)* %out, align 4
ret void
}