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/sgpr-control-flow.ll

106 lines
2.9 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: Only select SALU instructions in the entry or exit block SALU instructions ignore control flow, so it is not always safe to use them within branches. This is a partial solution to this problem until we can come up with something better. llvm-svn: 207590
2014-04-30 07:12:48 +08:00
;
;
; Most SALU instructions ignore control flow, so we need to make sure
; they don't overwrite values from other blocks.
R600/SI: Enable selecting SALU inside branches We can do this now that the FixSGPRLiveRanges pass is working. llvm-svn: 218353
2014-09-24 09:33:28 +08:00
; If the branch decision is made based on a value in an SGPR then all
; threads will execute the same code paths, so we don't need to worry
; about instructions in different blocks overwriting each other.
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: {{^}}sgpr_if_else_salu_br:
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_add
; SI: s_add
R600/SI: Only select SALU instructions in the entry or exit block SALU instructions ignore control flow, so it is not always safe to use them within branches. This is a partial solution to this problem until we can come up with something better. llvm-svn: 207590
2014-04-30 07:12:48 +08:00
R600/SI: Enable selecting SALU inside branches We can do this now that the FixSGPRLiveRanges pass is working. llvm-svn: 218353
2014-09-24 09:33:28 +08:00
define void @sgpr_if_else_salu_br(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c, i32 %d, i32 %e) {
R600/SI: Only select SALU instructions in the entry or exit block SALU instructions ignore control flow, so it is not always safe to use them within branches. This is a partial solution to this problem until we can come up with something better. llvm-svn: 207590
2014-04-30 07:12:48 +08:00
entry:
%0 = icmp eq i32 %a, 0
br i1 %0, label %if, label %else
if:
%1 = add i32 %b, %c
br label %endif
else:
%2 = add i32 %d, %e
br label %endif
endif:
%3 = phi i32 [%1, %if], [%2, %else]
%4 = add i32 %3, %a
store i32 %4, i32 addrspace(1)* %out
ret void
}
R600/SI: Enable selecting SALU inside branches We can do this now that the FixSGPRLiveRanges pass is working. llvm-svn: 218353
2014-09-24 09:33:28 +08:00
; The two S_ADD instructions should write to different registers, since
; different threads will take different control flow paths.
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: {{^}}sgpr_if_else_valu_br:
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_add_i32 [[SGPR:s[0-9]+]]
; SI-NOT: s_add_i32 [[SGPR]]
R600/SI: Enable selecting SALU inside branches We can do this now that the FixSGPRLiveRanges pass is working. llvm-svn: 218353
2014-09-24 09:33:28 +08:00
define void @sgpr_if_else_valu_br(i32 addrspace(1)* %out, float %a, i32 %b, i32 %c, i32 %d, i32 %e) {
entry:
%tid = call i32 @llvm.r600.read.tidig.x() #0
%tid_f = uitofp i32 %tid to float
%tmp1 = fcmp ueq float %tid_f, 0.0
br i1 %tmp1, label %if, label %else
if:
%tmp2 = add i32 %b, %c
br label %endif
else:
%tmp3 = add i32 %d, %e
br label %endif
endif:
%tmp4 = phi i32 [%tmp2, %if], [%tmp3, %else]
store i32 %tmp4, i32 addrspace(1)* %out
ret void
}
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
; FIXME: Should write to different SGPR pairs instead of copying to
; VALU for i1 phi.
; SI-LABEL: {{^}}sgpr_if_else_valu_cmp_phi_br:
; SI: buffer_load_dword [[AVAL:v[0-9]+]]
R600/SI: Allow commuting compares This enables very common cases to switch to the smaller encoding. All of the standard LLVM canonicalizations of comparisons are the opposite of what we want. Compares with constants are moved to the RHS, but the first operand can be an inline immediate, literal constant, or SGPR using the 32-bit VOPC encoding. There are additional bad canonicalizations that should also be fixed, such as canonicalizing ge x, k to gt x, (k + 1) if this makes k no longer an inline immediate value. llvm-svn: 232988
2015-03-24 02:45:30 +08:00
; SI: v_cmp_gt_i32_e32 [[CMP_IF:vcc]], 0, [[AVAL]]
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
; SI: v_cndmask_b32_e64 [[V_CMP:v[0-9]+]], 0, -1, [[CMP_IF]]
; SI: BB2_1:
; SI: buffer_load_dword [[AVAL:v[0-9]+]]
R600/SI: Allow commuting compares This enables very common cases to switch to the smaller encoding. All of the standard LLVM canonicalizations of comparisons are the opposite of what we want. Compares with constants are moved to the RHS, but the first operand can be an inline immediate, literal constant, or SGPR using the 32-bit VOPC encoding. There are additional bad canonicalizations that should also be fixed, such as canonicalizing ge x, k to gt x, (k + 1) if this makes k no longer an inline immediate value. llvm-svn: 232988
2015-03-24 02:45:30 +08:00
; SI: v_cmp_eq_i32_e32 [[CMP_ELSE:vcc]], 0, [[AVAL]]
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
; SI: v_cndmask_b32_e64 [[V_CMP]], 0, -1, [[CMP_ELSE]]
R600/SI: Allow commuting compares This enables very common cases to switch to the smaller encoding. All of the standard LLVM canonicalizations of comparisons are the opposite of what we want. Compares with constants are moved to the RHS, but the first operand can be an inline immediate, literal constant, or SGPR using the 32-bit VOPC encoding. There are additional bad canonicalizations that should also be fixed, such as canonicalizing ge x, k to gt x, (k + 1) if this makes k no longer an inline immediate value. llvm-svn: 232988
2015-03-24 02:45:30 +08:00
; SI: v_cmp_ne_i32_e32 [[CMP_CMP:vcc]], 0, [[V_CMP]]
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
; SI: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP_CMP]]
; SI: buffer_store_dword [[RESULT]]
define void @sgpr_if_else_valu_cmp_phi_br(i32 addrspace(1)* %out, i32 addrspace(1)* %a, i32 addrspace(1)* %b) {
entry:
%tid = call i32 @llvm.r600.read.tidig.x() #0
%tmp1 = icmp eq i32 %tid, 0
br i1 %tmp1, label %if, label %else
if:
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%gep.if = getelementptr i32, i32 addrspace(1)* %a, i32 %tid
[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
%a.val = load i32, i32 addrspace(1)* %gep.if
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
%cmp.if = icmp eq i32 %a.val, 0
br label %endif
else:
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%gep.else = getelementptr i32, i32 addrspace(1)* %b, i32 %tid
[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
%b.val = load i32, i32 addrspace(1)* %gep.else
R600/SI: Remove i1 pseudo VALU ops Select i1 logical ops directly to 64-bit SALU instructions. Vector i1 values are always really in SGPRs, with each bit for each item in the wave. This saves about 4 instructions when and/or/xoring any condition, and also helps write conditions that need to be passed in vcc. This should work correctly now that the SGPR live range fixing pass works. More work is needed to eliminate the VReg_1 pseudo regclass and possibly the entire SILowerI1Copies pass. llvm-svn: 223206
2014-12-03 13:22:35 +08:00
%cmp.else = icmp slt i32 %b.val, 0
br label %endif
endif:
%tmp4 = phi i1 [%cmp.if, %if], [%cmp.else, %else]
%ext = sext i1 %tmp4 to i32
store i32 %ext, i32 addrspace(1)* %out
ret void
}
R600/SI: Enable selecting SALU inside branches We can do this now that the FixSGPRLiveRanges pass is working. llvm-svn: 218353
2014-09-24 09:33:28 +08:00
declare i32 @llvm.r600.read.tidig.x() #0
attributes #0 = { readnone }