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/R600/cvt_f32_ubyte.ll

197 lines
7.6 KiB
LLVM
Raw Normal View History

R600/SI: Add a stub GCNTargetMachine This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. llvm-svn: 225277
2015-01-07 02:00:21 +08:00
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
R600/SI: Enable all tests that pass on VI without changes llvm-svn: 227214
2015-01-28 01:27:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_i8_to_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: buffer_load_ubyte [[LOADREG:v[0-9]+]],
; SI-NOT: bfe
; SI-NOT: lshr
; SI: v_cvt_f32_ubyte0_e32 [[CONV:v[0-9]+]], [[LOADREG]]
; SI: buffer_store_dword [[CONV]],
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_i8_to_f32(float addrspace(1)* noalias %out, i8 addrspace(1)* noalias %in) nounwind {
%load = load i8 addrspace(1)* %in, align 1
%cvt = uitofp i8 %load to float
store float %cvt, float addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v2i8_to_v2f32:
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_load_ushort [[LOADREG:v[0-9]+]],
; SI-NOT: bfe
; SI-NOT: lshr
; SI-NOT: and
; SI-DAG: v_cvt_f32_ubyte1_e32 v[[HIRESULT:[0-9]+]], [[LOADREG]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v[[LORESULT:[0-9]+]], [[LOADREG]]
; SI: buffer_store_dwordx2 v{{\[}}[[LORESULT]]:[[HIRESULT]]{{\]}},
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v2i8_to_v2f32(<2 x float> addrspace(1)* noalias %out, <2 x i8> addrspace(1)* noalias %in) nounwind {
Implement new way of expanding extloads. Now that the source and destination types can be specified, allow doing an expansion that doesn't use an EXTLOAD of the result type. Try to do a legal extload to an intermediate type and extend that if possible. This generalizes the special case custom lowering of extloads R600 has been using to work around this problem. This also happens to fix a bug that would incorrectly use more aligned loads than should be used. llvm-svn: 225925
2015-01-14 09:35:17 +08:00
%load = load <2 x i8> addrspace(1)* %in, align 2
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
%cvt = uitofp <2 x i8> %load to <2 x float>
store <2 x float> %cvt, <2 x float> addrspace(1)* %out, align 16
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v3i8_to_v3f32:
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-NOT: bfe
; SI-NOT: v_cvt_f32_ubyte3_e32
; SI-DAG: v_cvt_f32_ubyte2_e32
; SI-DAG: v_cvt_f32_ubyte1_e32
; SI-DAG: v_cvt_f32_ubyte0_e32
; SI: buffer_store_dwordx2 v{{\[}}[[LORESULT]]:[[HIRESULT]]{{\]}},
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v3i8_to_v3f32(<3 x float> addrspace(1)* noalias %out, <3 x i8> addrspace(1)* noalias %in) nounwind {
R600/SI: Fix bad code with unaligned byte vector loads Don't do the v4i8 -> v4f32 combine if the load will need to be expanded due to alignment. This stops adding instructions to repack into a single register that the v_cvt_ubyteN_f32 instructions read. llvm-svn: 225926
2015-01-14 09:35:22 +08:00
%load = load <3 x i8> addrspace(1)* %in, align 4
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
%cvt = uitofp <3 x i8> %load to <3 x float>
store <3 x float> %cvt, <3 x float> addrspace(1)* %out, align 16
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v4i8_to_v4f32:
Implement new way of expanding extloads. Now that the source and destination types can be specified, allow doing an expansion that doesn't use an EXTLOAD of the result type. Try to do a legal extload to an intermediate type and extend that if possible. This generalizes the special case custom lowering of extloads R600 has been using to work around this problem. This also happens to fix a bug that would incorrectly use more aligned loads than should be used. llvm-svn: 225925
2015-01-14 09:35:17 +08:00
; SI: buffer_load_dword [[LOADREG: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 llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI-NOT: bfe
; SI-NOT: lshr
; SI-DAG: v_cvt_f32_ubyte3_e32 v[[HIRESULT:[0-9]+]], [[LOADREG]]
; SI-DAG: v_cvt_f32_ubyte2_e32 v{{[0-9]+}}, [[LOADREG]]
; SI-DAG: v_cvt_f32_ubyte1_e32 v{{[0-9]+}}, [[LOADREG]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v[[LORESULT:[0-9]+]], [[LOADREG]]
; SI: buffer_store_dwordx4 v{{\[}}[[LORESULT]]:[[HIRESULT]]{{\]}},
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v4i8_to_v4f32(<4 x float> addrspace(1)* noalias %out, <4 x i8> addrspace(1)* noalias %in) nounwind {
Implement new way of expanding extloads. Now that the source and destination types can be specified, allow doing an expansion that doesn't use an EXTLOAD of the result type. Try to do a legal extload to an intermediate type and extend that if possible. This generalizes the special case custom lowering of extloads R600 has been using to work around this problem. This also happens to fix a bug that would incorrectly use more aligned loads than should be used. llvm-svn: 225925
2015-01-14 09:35:17 +08:00
%load = load <4 x i8> addrspace(1)* %in, align 4
%cvt = uitofp <4 x i8> %load to <4 x float>
store <4 x float> %cvt, <4 x float> addrspace(1)* %out, align 16
ret void
}
; This should not be adding instructions to shift into the correct
; position in the word for the component.
; SI-LABEL: {{^}}load_v4i8_to_v4f32_unaligned:
; SI: buffer_load_ubyte [[LOADREG3:v[0-9]+]]
R600/SI: Define a schedule model and enable the generic machine scheduler The schedule model is not complete yet, and could be improved. llvm-svn: 227461
2015-01-30 00:55:25 +08:00
; SI: buffer_load_ubyte [[LOADREG2:v[0-9]+]]
; SI: buffer_load_ubyte [[LOADREG1:v[0-9]+]]
; SI: buffer_load_ubyte [[LOADREG0:v[0-9]+]]
R600/SI: Fix bad code with unaligned byte vector loads Don't do the v4i8 -> v4f32 combine if the load will need to be expanded due to alignment. This stops adding instructions to repack into a single register that the v_cvt_ubyteN_f32 instructions read. llvm-svn: 225926
2015-01-14 09:35:22 +08:00
; SI-NOT: v_lshlrev_b32
; SI-NOT: v_or_b32
Implement new way of expanding extloads. Now that the source and destination types can be specified, allow doing an expansion that doesn't use an EXTLOAD of the result type. Try to do a legal extload to an intermediate type and extend that if possible. This generalizes the special case custom lowering of extloads R600 has been using to work around this problem. This also happens to fix a bug that would incorrectly use more aligned loads than should be used. llvm-svn: 225925
2015-01-14 09:35:17 +08:00
R600/SI: Fix bad code with unaligned byte vector loads Don't do the v4i8 -> v4f32 combine if the load will need to be expanded due to alignment. This stops adding instructions to repack into a single register that the v_cvt_ubyteN_f32 instructions read. llvm-svn: 225926
2015-01-14 09:35:22 +08:00
; SI-DAG: v_cvt_f32_ubyte0_e32 v[[LORESULT:[0-9]+]], [[LOADREG0]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v{{[0-9]+}}, [[LOADREG1]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v{{[0-9]+}}, [[LOADREG2]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v[[HIRESULT:[0-9]+]], [[LOADREG3]]
Implement new way of expanding extloads. Now that the source and destination types can be specified, allow doing an expansion that doesn't use an EXTLOAD of the result type. Try to do a legal extload to an intermediate type and extend that if possible. This generalizes the special case custom lowering of extloads R600 has been using to work around this problem. This also happens to fix a bug that would incorrectly use more aligned loads than should be used. llvm-svn: 225925
2015-01-14 09:35:17 +08:00
; SI: buffer_store_dwordx4 v{{\[}}[[LORESULT]]:[[HIRESULT]]{{\]}},
define void @load_v4i8_to_v4f32_unaligned(<4 x float> addrspace(1)* noalias %out, <4 x i8> addrspace(1)* noalias %in) nounwind {
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
%load = load <4 x i8> addrspace(1)* %in, align 1
%cvt = uitofp <4 x i8> %load to <4 x float>
store <4 x float> %cvt, <4 x float> addrspace(1)* %out, align 16
ret void
}
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
; XXX - This should really still be able to use the v_cvt_f32_ubyte0
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
; for each component, but computeKnownBits doesn't handle vectors very
; well.
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v4i8_to_v4f32_2_uses:
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_load_ubyte
; SI: buffer_load_ubyte
; SI: buffer_load_ubyte
; SI: buffer_load_ubyte
; SI: v_cvt_f32_ubyte0_e32
; SI: v_cvt_f32_ubyte0_e32
; SI: v_cvt_f32_ubyte0_e32
; SI: v_cvt_f32_ubyte0_e32
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
; XXX - replace with this when v4i8 loads aren't scalarized anymore.
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
; XSI: buffer_load_dword
; XSI: v_cvt_f32_u32_e32
; XSI: v_cvt_f32_u32_e32
; XSI: v_cvt_f32_u32_e32
; XSI: v_cvt_f32_u32_e32
; SI: s_endpgm
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v4i8_to_v4f32_2_uses(<4 x float> addrspace(1)* noalias %out, <4 x i8> addrspace(1)* noalias %out2, <4 x i8> addrspace(1)* noalias %in) nounwind {
%load = load <4 x i8> addrspace(1)* %in, align 4
%cvt = uitofp <4 x i8> %load to <4 x float>
store <4 x float> %cvt, <4 x float> addrspace(1)* %out, align 16
%add = add <4 x i8> %load, <i8 9, i8 9, i8 9, i8 9> ; Second use of %load
store <4 x i8> %add, <4 x i8> addrspace(1)* %out2, align 4
ret void
}
; Make sure this doesn't crash.
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v7i8_to_v7f32:
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_endpgm
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v7i8_to_v7f32(<7 x float> addrspace(1)* noalias %out, <7 x i8> addrspace(1)* noalias %in) nounwind {
%load = load <7 x i8> addrspace(1)* %in, align 1
%cvt = uitofp <7 x i8> %load to <7 x float>
store <7 x float> %cvt, <7 x float> addrspace(1)* %out, align 16
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}load_v8i8_to_v8f32:
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_load_dwordx2 v{{\[}}[[LOLOAD:[0-9]+]]:[[HILOAD:[0-9]+]]{{\]}},
; SI-NOT: bfe
; SI-NOT: lshr
; SI-DAG: v_cvt_f32_ubyte3_e32 v{{[0-9]+}}, v[[LOLOAD]]
; SI-DAG: v_cvt_f32_ubyte2_e32 v{{[0-9]+}}, v[[LOLOAD]]
; SI-DAG: v_cvt_f32_ubyte1_e32 v{{[0-9]+}}, v[[LOLOAD]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v{{[0-9]+}}, v[[LOLOAD]]
; SI-DAG: v_cvt_f32_ubyte3_e32 v{{[0-9]+}}, v[[HILOAD]]
; SI-DAG: v_cvt_f32_ubyte2_e32 v{{[0-9]+}}, v[[HILOAD]]
; SI-DAG: v_cvt_f32_ubyte1_e32 v{{[0-9]+}}, v[[HILOAD]]
; SI-DAG: v_cvt_f32_ubyte0_e32 v{{[0-9]+}}, v[[HILOAD]]
; SI-NOT: bfe
; SI-NOT: lshr
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
; SI: buffer_store_dword
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @load_v8i8_to_v8f32(<8 x float> addrspace(1)* noalias %out, <8 x i8> addrspace(1)* noalias %in) nounwind {
R600/SI: 64-bit and larger memory access must be at least 4-byte aligned This is true for SI only. CI+ supports unaligned memory accesses, but this requires driver support, so for now we disallow unaligned accesses for all GCN targets. llvm-svn: 227822
2015-02-03 02:02:28 +08:00
%load = load <8 x i8> addrspace(1)* %in, align 8
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
%cvt = uitofp <8 x i8> %load to <8 x float>
store <8 x float> %cvt, <8 x float> addrspace(1)* %out, align 16
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}i8_zext_inreg_i32_to_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: buffer_load_dword [[LOADREG:v[0-9]+]],
; SI: v_add_i32_e32 [[ADD:v[0-9]+]], 2, [[LOADREG]]
; SI-NEXT: v_cvt_f32_ubyte0_e32 [[CONV:v[0-9]+]], [[ADD]]
; SI: buffer_store_dword [[CONV]],
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @i8_zext_inreg_i32_to_f32(float addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%load = load i32 addrspace(1)* %in, align 4
%add = add i32 %load, 2
%inreg = and i32 %add, 255
%cvt = uitofp i32 %inreg to float
store float %cvt, float addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}i8_zext_inreg_hi1_to_f32:
R600/SI: Use v_cvt_f32_ubyte* instructions This eliminates extra extract instructions when loading an i8 vector to a float vector. llvm-svn: 210666
2014-06-12 01:50:44 +08:00
define void @i8_zext_inreg_hi1_to_f32(float addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%load = load i32 addrspace(1)* %in, align 4
%inreg = and i32 %load, 65280
%shr = lshr i32 %inreg, 8
%cvt = uitofp i32 %shr to float
store float %cvt, float addrspace(1)* %out, align 4
ret void
}
; We don't get these ones because of the zext, but instcombine removes
; them so it shouldn't really matter.
define void @i8_zext_i32_to_f32(float addrspace(1)* noalias %out, i8 addrspace(1)* noalias %in) nounwind {
%load = load i8 addrspace(1)* %in, align 1
%ext = zext i8 %load to i32
%cvt = uitofp i32 %ext to float
store float %cvt, float addrspace(1)* %out, align 4
ret void
}
define void @v4i8_zext_v4i32_to_v4f32(<4 x float> addrspace(1)* noalias %out, <4 x i8> addrspace(1)* noalias %in) nounwind {
%load = load <4 x i8> addrspace(1)* %in, align 1
%ext = zext <4 x i8> %load to <4 x i32>
%cvt = uitofp <4 x i32> %ext to <4 x float>
store <4 x float> %cvt, <4 x float> addrspace(1)* %out, align 16
ret void
}