RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-11-24 04:09:45 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
9435879900
llvm/test/CodeGen/AMDGPU/cttz_zero_undef.ll

79 lines
3.5 KiB
LLVM
Raw Normal View History

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> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292982 91177308-0d34-0410-b5e6-96231b3b80d8
2017-01-24 22:02:15 +00:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
R600: Implement zero undef variants of ctlz/cttz v2: use ffbh/l if available v3: Rebase on top of Matt's SI patches Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Tom Stellard <tom@stellard.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213072 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-15 15:51:09 +00:00
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
declare i32 @llvm.cttz.i32(i32, i1) nounwind readnone
declare <2 x i32> @llvm.cttz.v2i32(<2 x i32>, i1) nounwind readnone
declare <4 x i32> @llvm.cttz.v4i32(<4 x i32>, i1) nounwind readnone
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}s_cttz_zero_undef_i32:
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: s_load_dword [[VAL:s[0-9]+]],
; SI: s_ff1_i32_b32 [[SRESULT:s[0-9]+]], [[VAL]]
; SI: v_mov_b32_e32 [[VRESULT:v[0-9]+]], [[SRESULT]]
; SI: buffer_store_dword [[VRESULT]],
; SI: s_endpgm
R600: Implement zero undef variants of ctlz/cttz v2: use ffbh/l if available v3: Rebase on top of Matt's SI patches Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Tom Stellard <tom@stellard.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213072 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-15 15:51:09 +00:00
; EG: MEM_RAT_CACHELESS STORE_RAW [[RESULT:T[0-9]+\.[XYZW]]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-21 21:39:51 +00:00
define amdgpu_kernel void @s_cttz_zero_undef_i32(i32 addrspace(1)* noalias %out, i32 %val) nounwind {
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
%cttz = call i32 @llvm.cttz.i32(i32 %val, i1 true) nounwind readnone
store i32 %cttz, i32 addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}v_cttz_zero_undef_i32:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
; SI: {{buffer|flat}}_load_dword [[VAL:v[0-9]+]],
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: v_ffbl_b32_e32 [[RESULT:v[0-9]+]], [[VAL]]
; SI: buffer_store_dword [[RESULT]],
; SI: s_endpgm
R600: Implement zero undef variants of ctlz/cttz v2: use ffbh/l if available v3: Rebase on top of Matt's SI patches Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Tom Stellard <tom@stellard.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213072 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-15 15:51:09 +00:00
; EG: MEM_RAT_CACHELESS STORE_RAW [[RESULT:T[0-9]+\.[XYZW]]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-21 21:39:51 +00:00
define amdgpu_kernel void @v_cttz_zero_undef_i32(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %valptr) nounwind {
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
%tid = call i32 @llvm.r600.read.tidig.x()
%in.gep = getelementptr i32, i32 addrspace(1)* %valptr, i32 %tid
%val = load i32, i32 addrspace(1)* %in.gep, align 4
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
%cttz = call i32 @llvm.cttz.i32(i32 %val, i1 true) nounwind readnone
store i32 %cttz, i32 addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}v_cttz_zero_undef_v2i32:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
; SI: {{buffer|flat}}_load_dwordx2
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: v_ffbl_b32_e32
; SI: v_ffbl_b32_e32
; SI: buffer_store_dwordx2
; SI: s_endpgm
R600: Implement zero undef variants of ctlz/cttz v2: use ffbh/l if available v3: Rebase on top of Matt's SI patches Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Tom Stellard <tom@stellard.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213072 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-15 15:51:09 +00:00
; EG: MEM_RAT_CACHELESS STORE_RAW [[RESULT:T[0-9]+]]{{\.[XYZW]}}
; EG: FFBL_INT {{\*? *}}[[RESULT]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-21 21:39:51 +00:00
define amdgpu_kernel void @v_cttz_zero_undef_v2i32(<2 x i32> addrspace(1)* noalias %out, <2 x i32> addrspace(1)* noalias %valptr) nounwind {
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
%tid = call i32 @llvm.r600.read.tidig.x()
%in.gep = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %valptr, i32 %tid
%val = load <2 x i32>, <2 x i32> addrspace(1)* %in.gep, align 8
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
%cttz = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> %val, i1 true) nounwind readnone
store <2 x i32> %cttz, <2 x i32> addrspace(1)* %out, align 8
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; FUNC-LABEL: {{^}}v_cttz_zero_undef_v4i32:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
; SI: {{buffer|flat}}_load_dwordx4
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: v_ffbl_b32_e32
; SI: v_ffbl_b32_e32
; SI: v_ffbl_b32_e32
; SI: v_ffbl_b32_e32
; SI: buffer_store_dwordx4
; SI: s_endpgm
R600: Implement zero undef variants of ctlz/cttz v2: use ffbh/l if available v3: Rebase on top of Matt's SI patches Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Tom Stellard <tom@stellard.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213072 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-15 15:51:09 +00:00
; EG: MEM_RAT_CACHELESS STORE_RAW [[RESULT:T[0-9]+]]{{\.[XYZW]}}
; EG: FFBL_INT {{\*? *}}[[RESULT]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
; EG: FFBL_INT {{\*? *}}[[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-21 21:39:51 +00:00
define amdgpu_kernel void @v_cttz_zero_undef_v4i32(<4 x i32> addrspace(1)* noalias %out, <4 x i32> addrspace(1)* noalias %valptr) nounwind {
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307097 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-04 17:32:00 +00:00
%tid = call i32 @llvm.r600.read.tidig.x()
%in.gep = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %valptr, i32 %tid
%val = load <4 x i32>, <4 x i32> addrspace(1)* %in.gep, align 16
R600/SI: Match cttz_zero_undef git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211116 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-17 17:36:27 +00:00
%cttz = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> %val, i1 true) nounwind readnone
store <4 x i32> %cttz, <4 x i32> addrspace(1)* %out, align 16
ret void
}
Reference in New Issue Copy Permalink