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/and.ll

554 lines
19 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=verde -verify-machineinstrs < %s | FileCheck -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 -check-prefix=SI -check-prefix=FUNC %s
AMDGPU: Run r600 tests last llvm-svn: 268672
2016-05-06 04:07:37 +08:00
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
declare i32 @llvm.r600.read.tidig.x() #0
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: {{^}}test2:
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
; EG: AND_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: AND_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
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: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
R600/SI: Expand and of v2i32/v4i32 for SI Also add lit test for both cases on SI, and v2i32 for evergreen. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 184837
2013-06-25 21:55:23 +08:00
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
[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
%b_ptr = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 1
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load <2 x i32>, <2 x i32> addrspace(1) * %in
%b = load <2 x i32>, <2 x i32> addrspace(1) * %b_ptr
R600/SI: Expand and of v2i32/v4i32 for SI Also add lit test for both cases on SI, and v2i32 for evergreen. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 184837
2013-06-25 21:55:23 +08:00
%result = and <2 x i32> %a, %b
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test4:
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
; EG: AND_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: AND_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: AND_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: AND_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
R600/SI: Expand and of v2i32/v4i32 for SI Also add lit test for both cases on SI, and v2i32 for evergreen. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 184837
2013-06-25 21:55:23 +08:00
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_and_b32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
R600/SI: Expand and of v2i32/v4i32 for SI Also add lit test for both cases on SI, and v2i32 for evergreen. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 184837
2013-06-25 21:55:23 +08:00
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
[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
%b_ptr = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %in, i32 1
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load <4 x i32>, <4 x i32> addrspace(1) * %in
%b = load <4 x i32>, <4 x i32> addrspace(1) * %b_ptr
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
%result = and <4 x i32> %a, %b
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
ret void
}
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}s_and_i32:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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 llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_and_b32
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) {
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i32 %a, %b
store i32 %and, i32 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
; FUNC-LABEL: {{^}}s_and_constant_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 llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x12d687
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_constant_i32(i32 addrspace(1)* %out, i32 %a) {
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i32 %a, 1234567
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
; FIXME: We should really duplicate the constant so that the SALU use
; can fold into the s_and_b32 and the VALU one is materialized
; directly without copying from the SGPR.
; Second use is a VGPR use of the constant.
; FUNC-LABEL: {{^}}s_and_multi_use_constant_i32_0:
; SI: s_mov_b32 [[K:s[0-9]+]], 0x12d687
; SI-DAG: s_and_b32 [[AND:s[0-9]+]], s{{[0-9]+}}, [[K]]
; SI-DAG: v_mov_b32_e32 [[VK:v[0-9]+]], [[K]]
; SI: buffer_store_dword [[VK]]
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_multi_use_constant_i32_0(i32 addrspace(1)* %out, i32 %a, i32 %b) {
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
%and = and i32 %a, 1234567
; Just to stop future replacement of copy to vgpr + store with VALU op.
%foo = add i32 %and, %b
store volatile i32 %foo, i32 addrspace(1)* %out
store volatile i32 1234567, i32 addrspace(1)* %out
ret void
}
; Second use is another SGPR use of the constant.
; FUNC-LABEL: {{^}}s_and_multi_use_constant_i32_1:
; SI: s_mov_b32 [[K:s[0-9]+]], 0x12d687
; SI: s_and_b32 [[AND:s[0-9]+]], s{{[0-9]+}}, [[K]]
; SI: s_add_i32
; SI: s_add_i32 [[ADD:s[0-9]+]], s{{[0-9]+}}, [[K]]
; SI: buffer_store_dword [[VK]]
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_multi_use_constant_i32_1(i32 addrspace(1)* %out, i32 %a, i32 %b) {
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
%and = and i32 %a, 1234567
%foo = add i32 %and, 1234567
%bar = add i32 %foo, %b
store volatile i32 %bar, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}v_and_i32_vgpr_vgpr:
; SI: v_and_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i32_vgpr_vgpr(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) {
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
%tid = call i32 @llvm.r600.read.tidig.x() #0
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
%gep.b = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
%a = load i32, i32 addrspace(1)* %gep.a
%b = load i32, i32 addrspace(1)* %gep.b
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i32 %a, %b
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
store i32 %and, i32 addrspace(1)* %gep.out
ret void
}
; FUNC-LABEL: {{^}}v_and_i32_sgpr_vgpr:
; SI-DAG: s_load_dword [[SA:s[0-9]+]]
; SI-DAG: {{buffer|flat}}_load_dword [[VB:v[0-9]+]]
; SI: v_and_b32_e32 v{{[0-9]+}}, [[SA]], [[VB]]
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i32_sgpr_vgpr(i32 addrspace(1)* %out, i32 %a, i32 addrspace(1)* %bptr) {
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
%tid = call i32 @llvm.r600.read.tidig.x() #0
%gep.b = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
%b = load i32, i32 addrspace(1)* %gep.b
%and = and i32 %a, %b
store i32 %and, i32 addrspace(1)* %gep.out
ret void
}
; FUNC-LABEL: {{^}}v_and_i32_vgpr_sgpr:
; SI-DAG: s_load_dword [[SA:s[0-9]+]]
; SI-DAG: {{buffer|flat}}_load_dword [[VB:v[0-9]+]]
; SI: v_and_b32_e32 v{{[0-9]+}}, [[SA]], [[VB]]
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i32_vgpr_sgpr(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 %b) {
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
%tid = call i32 @llvm.r600.read.tidig.x() #0
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
%a = load i32, i32 addrspace(1)* %gep.a
%and = and i32 %a, %b
store i32 %and, i32 addrspace(1)* %gep.out
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
ret void
}
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
; FUNC-LABEL: {{^}}v_and_constant_i32
; SI: v_and_b32_e32 v{{[0-9]+}}, 0x12d687, v{{[0-9]+}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_constant_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) {
[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 = load i32, i32 addrspace(1)* %aptr, align 4
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i32 %a, 1234567
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
; FUNC-LABEL: {{^}}v_and_inline_imm_64_i32
; SI: v_and_b32_e32 v{{[0-9]+}}, 64, v{{[0-9]+}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_inline_imm_64_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) {
[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 = load i32, i32 addrspace(1)* %aptr, align 4
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i32 %a, 64
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_and_inline_imm_neg_16_i32
; SI: v_and_b32_e32 v{{[0-9]+}}, -16, v{{[0-9]+}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_inline_imm_neg_16_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) {
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load i32, i32 addrspace(1)* %aptr, align 4
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i32 %a, -16
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}s_and_i64
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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_and_b64
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i64 %a, %b
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
R600/SI: Fix select on i1 llvm-svn: 213096
2014-07-16 05:44:37 +08:00
; FIXME: Should use SGPRs
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: {{^}}s_and_i1:
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: v_and_b32
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_i1(i1 addrspace(1)* %out, i1 %a, i1 %b) {
R600/SI: Fix select on i1 llvm-svn: 213096
2014-07-16 05:44:37 +08:00
%and = and i1 %a, %b
store i1 %and, i1 addrspace(1)* %out
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_constant_i64:
; SI-DAG: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000{{$}}
; SI-DAG: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80{{$}}
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_constant_i64(i64 addrspace(1)* %out, i64 %a) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%and = and i64 %a, 549756338176
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}s_and_multi_use_constant_i64:
; XSI-DAG: s_mov_b32 s[[KLO:[0-9]+]], 0x80000{{$}}
; XSI-DAG: s_mov_b32 s[[KHI:[0-9]+]], 0x80{{$}}
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[}}[[KLO]]:[[KHI]]{{\]}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_multi_use_constant_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%and0 = and i64 %a, 549756338176
%and1 = and i64 %b, 549756338176
store volatile i64 %and0, i64 addrspace(1)* %out
store volatile i64 %and1, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}s_and_32_bit_constant_i64:
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x12d687{{$}}
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_32_bit_constant_i64(i64 addrspace(1)* %out, i64 %a) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%and = and i64 %a, 1234567
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_multi_use_inline_imm_i64:
AMDGPU: Re-visit nodes in performAndCombine This fixes test regressions when i64 loads/stores are made promote. llvm-svn: 267240
2016-04-23 06:48:38 +08:00
; SI: s_load_dword [[A:s[0-9]+]]
; SI: s_load_dword [[B:s[0-9]+]]
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: s_load_dwordx2
AMDGPU/SI: Enable the post-ra scheduler Summary: This includes a hazard recognizer implementation to replace some of the hazard handling we had during frame index elimination. Reviewers: arsenm Subscribers: qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18602 llvm-svn: 268143
2016-04-30 08:23:06 +08:00
; SI: s_load_dwordx2
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
AMDGPU: Re-visit nodes in performAndCombine This fixes test regressions when i64 loads/stores are made promote. llvm-svn: 267240
2016-04-23 06:48:38 +08:00
; SI: s_lshl_b32 [[A]], [[A]], 1
; SI: s_lshl_b32 [[B]], [[B]], 1
; SI: s_and_b32 s{{[0-9]+}}, [[A]], 62
; SI: s_and_b32 s{{[0-9]+}}, [[B]], 62
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_multi_use_inline_imm_i64(i64 addrspace(1)* %out, i64 %a, i64 %b, i64 %c) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%shl.a = shl i64 %a, 1
%shl.b = shl i64 %b, 1
%and0 = and i64 %shl.a, 62
%and1 = and i64 %shl.b, 62
%add0 = add i64 %and0, %c
%add1 = add i64 %and1, %c
store volatile i64 %add0, i64 addrspace(1)* %out
store volatile i64 %add1, i64 addrspace(1)* %out
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
; FUNC-LABEL: {{^}}v_and_i64:
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: v_and_b32
; SI: v_and_b32
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) {
[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 = load i64, i64 addrspace(1)* %aptr, align 8
%b = load i64, i64 addrspace(1)* %bptr, align 8
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i64 %a, %b
store i64 %and, i64 addrspace(1)* %out, align 8
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
; FUNC-LABEL: {{^}}v_and_constant_i64:
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, 0xab19b207, {{v[0-9]+}}
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, 0x11e, {{v[0-9]+}}
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_constant_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
%a = load i64, i64 addrspace(1)* %aptr, align 8
%and = and i64 %a, 1231231234567
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}v_and_multi_use_constant_i64:
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 llvm-svn: 279995
2016-08-30 03:42:52 +08:00
; SI-DAG: buffer_load_dwordx2 v{{\[}}[[LO0:[0-9]+]]:[[HI0:[0-9]+]]{{\]}}
; SI-DAG: buffer_load_dwordx2 v{{\[}}[[LO1:[0-9]+]]:[[HI1:[0-9]+]]{{\]}}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-DAG: s_movk_i32 [[KHI:s[0-9]+]], 0x11e{{$}}
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 llvm-svn: 279995
2016-08-30 03:42:52 +08:00
; SI-DAG: s_mov_b32 [[KLO:s[0-9]+]], 0xab19b207{{$}}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, [[KLO]], v[[LO0]]
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, [[KHI]], v[[HI0]]
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, [[KLO]], v[[LO1]]
; SI-DAG: v_and_b32_e32 {{v[0-9]+}}, [[KHI]], v[[HI1]]
; SI: buffer_store_dwordx2
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_multi_use_constant_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%a = load volatile i64, i64 addrspace(1)* %aptr
%b = load volatile i64, i64 addrspace(1)* %aptr
%and0 = and i64 %a, 1231231234567
%and1 = and i64 %b, 1231231234567
store volatile i64 %and0, i64 addrspace(1)* %out
store volatile i64 %and1, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}v_and_multi_use_inline_imm_i64:
; SI: buffer_load_dwordx2 v{{\[}}[[LO0:[0-9]+]]:[[HI0:[0-9]+]]{{\]}}
; SI-NOT: and
; SI: buffer_load_dwordx2 v{{\[}}[[LO1:[0-9]+]]:[[HI1:[0-9]+]]{{\]}}
; SI-NOT: and
; SI: v_and_b32_e32 v[[RESLO0:[0-9]+]], 63, v[[LO0]]
AMDGPU/SI: Enable lanemask tracking in misched Summary: This results in higher register usage, but should make it easier for the compiler to hide latency. This pass is a prerequisite for some more scheduler improvements, and I think the increase register usage with this patch is acceptable, because when combined with the scheduler improvements, the total register usage will decrease. shader-db stats: 2382 shaders in 478 tests Totals: SGPRS: 48672 -> 49088 (0.85 %) VGPRS: 34148 -> 34847 (2.05 %) Code Size: 1285816 -> 1289128 (0.26 %) bytes LDS: 28 -> 28 (0.00 %) blocks Scratch: 492544 -> 573440 (16.42 %) bytes per wave Max Waves: 6856 -> 6846 (-0.15 %) Wait states: 0 -> 0 (0.00 %) Depends on D18451 Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18452 llvm-svn: 264876
2016-03-31 00:35:09 +08:00
; SI: v_and_b32_e32 v[[RESLO1:[0-9]+]], 63, v[[LO1]]
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 llvm-svn: 279995
2016-08-30 03:42:52 +08:00
; SI: buffer_store_dwordx2 v{{\[}}[[RESLO0]]
AMDGPU/SI: Enable lanemask tracking in misched Summary: This results in higher register usage, but should make it easier for the compiler to hide latency. This pass is a prerequisite for some more scheduler improvements, and I think the increase register usage with this patch is acceptable, because when combined with the scheduler improvements, the total register usage will decrease. shader-db stats: 2382 shaders in 478 tests Totals: SGPRS: 48672 -> 49088 (0.85 %) VGPRS: 34148 -> 34847 (2.05 %) Code Size: 1285816 -> 1289128 (0.26 %) bytes LDS: 28 -> 28 (0.00 %) blocks Scratch: 492544 -> 573440 (16.42 %) bytes per wave Max Waves: 6856 -> 6846 (-0.15 %) Wait states: 0 -> 0 (0.00 %) Depends on D18451 Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18452 llvm-svn: 264876
2016-03-31 00:35:09 +08:00
; SI: buffer_store_dwordx2 v{{\[}}[[RESLO1]]
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_multi_use_inline_imm_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%a = load volatile i64, i64 addrspace(1)* %aptr
%b = load volatile i64, i64 addrspace(1)* %aptr
%and0 = and i64 %a, 63
%and1 = and i64 %b, 63
store volatile i64 %and0, i64 addrspace(1)* %out
store volatile i64 %and1, i64 addrspace(1)* %out
ret void
}
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; FUNC-LABEL: {{^}}v_and_i64_32_bit_constant:
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: buffer_load_dword [[VAL:v[0-9]+]]
; SI-NOT: and
; SI: v_and_b32_e32 {{v[0-9]+}}, 0x12d687, [[VAL]]
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i64_32_bit_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load i64, i64 addrspace(1)* %aptr, align 8
R600: Add more and testcases llvm-svn: 210453
2014-06-09 16:36:53 +08:00
%and = and i64 %a, 1234567
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. llvm-svn: 217789
2014-09-16 01:15:02 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}v_and_inline_imm_i64:
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: buffer_load_dword v{{[0-9]+}}
; SI-NOT: and
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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: v_and_b32_e32 {{v[0-9]+}}, 64, {{v[0-9]+}}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_inline_imm_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
[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 = load i64, i64 addrspace(1)* %aptr, align 8
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. llvm-svn: 217789
2014-09-16 01:15:02 +08:00
%and = and i64 %a, 64
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; FIXME: Should be able to reduce load width
; FUNC-LABEL: {{^}}v_and_inline_neg_imm_i64:
; SI: buffer_load_dwordx2 v{{\[}}[[VAL_LO:[0-9]+]]:[[VAL_HI:[0-9]+]]{{\]}}
; SI-NOT: and
; SI: v_and_b32_e32 v[[VAL_LO]], -8, v[[VAL_LO]]
; SI-NOT: and
; SI: buffer_store_dwordx2 v{{\[}}[[VAL_LO]]:[[VAL_HI]]{{\]}}
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_inline_neg_imm_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%a = load i64, i64 addrspace(1)* %aptr, align 8
%and = and i64 %a, -8
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_64_i64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: s_load_dword
; SI-NOT: and
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 64
; SI-NOT: and
; SI: buffer_store_dword
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_64_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. llvm-svn: 217789
2014-09-16 01:15:02 +08:00
%and = and i64 %a, 64
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_64_i64_noshrink:
AMDGPU: Re-visit nodes in performAndCombine This fixes test regressions when i64 loads/stores are made promote. llvm-svn: 267240
2016-04-23 06:48:38 +08:00
; SI: s_load_dword [[A:s[0-9]+]]
; SI: s_lshl_b32 [[A]], [[A]], 1{{$}}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
AMDGPU: Re-visit nodes in performAndCombine This fixes test regressions when i64 loads/stores are made promote. llvm-svn: 267240
2016-04-23 06:48:38 +08:00
; SI: s_and_b32 s{{[0-9]+}}, [[A]], 64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
; SI: s_add_u32
; SI-NEXT: s_addc_u32
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_64_i64_noshrink(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a, i64 %b) {
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
%shl = shl i64 %a, 1
%and = and i64 %shl, 64
%add = add i64 %and, %b
store i64 %add, i64 addrspace(1)* %out, align 8
ret void
}
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_1_i64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 1
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_1_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 1
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}s_and_inline_imm_1.0_i64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 1.0
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0x3ff00000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_1.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 4607182418800017408
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}s_and_inline_imm_neg_1.0_i64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, -1.0
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0xbff00000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_neg_1.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 13830554455654793216
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}s_and_inline_imm_0.5_i64
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0.5
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0x3fe00000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_0.5_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 4602678819172646912
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_neg_0.5_i64:
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, -0.5
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0xbfe00000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_neg_0.5_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 13826050856027422720
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_2.0_i64:
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 2.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_2.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 4611686018427387904
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_neg_2.0_i64:
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, -2.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_neg_2.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 13835058055282163712
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_4.0_i64:
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 4.0
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0x40100000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 4616189618054758400
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_neg_4.0_i64:
; XSI: s_and_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, -4.0
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 {{s[0-9]+}}, {{s[0-9]+}}, 0xc0100000
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_neg_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 13839561654909534208
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; Test with the 64-bit integer bitpattern for a 32-bit float in the
; low 32-bits, which is not a valid 64-bit inline immmediate.
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_f32_4.0_i64:
MachineScheduler: Fully compare top/bottom candidates In bidirectional scheduling this gives more stable results than just comparing the "reason" fields of the top/bottom node because the reason field may be higher depending on what other nodes are in the queue. Differential Revision: http://reviews.llvm.org/D19401 llvm-svn: 273755
2016-06-25 08:23:00 +08:00
; SI: s_load_dwordx2
AMDGPU/SI: Implement a custom MachineSchedStrategy Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 llvm-svn: 279995
2016-08-30 03:42:52 +08:00
; SI: s_load_dword s
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI-NOT: and
; SI: s_and_b32 s[[K_HI:[0-9]+]], s{{[0-9]+}}, 4.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_f32_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 1082130432
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_imm_f32_neg_4.0_i64:
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 s[[K_HI:[0-9]+]], s{{[0-9]+}}, -4.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_imm_f32_neg_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, -1065353216
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
; Shift into upper 32-bits
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 s[[K_HI:[0-9]+]], s{{[0-9]+}}, 4.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_high_imm_f32_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 4647714815446351872
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Split 64-bit and of constant up This breaks the tests that were meant for testing 64-bit inline immediates, so move those to shl where they won't be broken up. This should be repeated for the other related bit ops. llvm-svn: 258095
2016-01-19 06:01:13 +08:00
; FUNC-LABEL: {{^}}s_and_inline_high_imm_f32_neg_4.0_i64:
; SI: s_load_dwordx2
; SI: s_load_dwordx2
; SI-NOT: and
; SI: s_and_b32 s[[K_HI:[0-9]+]], s{{[0-9]+}}, -4.0
; SI-NOT: and
; SI: buffer_store_dwordx2
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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @s_and_inline_high_imm_f32_neg_4.0_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 %a) {
R600/SI: Allow f64 inline immediates in i64 operands This requires considering the size of the operand when checking immediate legality. llvm-svn: 229135
2015-02-14 03:05:03 +08:00
%and = and i64 %a, 13871086852301127680
store i64 %and, i64 addrspace(1)* %out, align 8
ret void
}
AMDGPU: Add some more tests for literal operands llvm-svn: 248600
2015-09-26 02:21:47 +08:00
attributes #0 = { nounwind readnone }