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/Mips/cconv/arguments-hard-float.ll

212 lines
10 KiB
LLVM
Raw Normal View History

[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
; RUN: llc -march=mips -relocation-model=static < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=O32 --check-prefix=O32BE %s
; RUN: llc -march=mipsel -relocation-model=static < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=O32 --check-prefix=O32LE %s
Move the Mips target to storing the ABI in the TargetMachine rather than on MipsSubtargetInfo. This required a bit of massaging in the MC level to handle this since MC is a) largely a collection of disparate classes with no hierarchy, and b) there's no overarching equivalent to the TargetMachine, instead only the subtarget via MCSubtargetInfo (which is the base class of TargetSubtargetInfo). We're now storing the ABI in both the TargetMachine level and in the MC level because the AsmParser and the TargetStreamer both need to know what ABI we have to parse assembly and emit objects. The target streamer has a pointer to the one in the asm parser and is updated when the asm parser is created. This is fragile as the FIXME comment notes, but shouldn't be a problem in practice since we always create an asm parser before attempting to emit object code via the assembler. The TargetMachine now contains the ABI so that the DataLayout can be constructed dependent upon ABI. All testcases have been updated to use the -target-abi command line flag so that we can set the ABI without using a subtarget feature. Should be no change visible externally here. llvm-svn: 227102
2015-01-27 01:33:46 +08:00
; RUN-TODO: llc -march=mips64 -relocation-model=static -target-abi o32 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=O32 %s
; RUN-TODO: llc -march=mips64el -relocation-model=static -target-abi o32 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=O32 %s
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
Move the Mips target to storing the ABI in the TargetMachine rather than on MipsSubtargetInfo. This required a bit of massaging in the MC level to handle this since MC is a) largely a collection of disparate classes with no hierarchy, and b) there's no overarching equivalent to the TargetMachine, instead only the subtarget via MCSubtargetInfo (which is the base class of TargetSubtargetInfo). We're now storing the ABI in both the TargetMachine level and in the MC level because the AsmParser and the TargetStreamer both need to know what ABI we have to parse assembly and emit objects. The target streamer has a pointer to the one in the asm parser and is updated when the asm parser is created. This is fragile as the FIXME comment notes, but shouldn't be a problem in practice since we always create an asm parser before attempting to emit object code via the assembler. The TargetMachine now contains the ABI so that the DataLayout can be constructed dependent upon ABI. All testcases have been updated to use the -target-abi command line flag so that we can set the ABI without using a subtarget feature. Should be no change visible externally here. llvm-svn: 227102
2015-01-27 01:33:46 +08:00
; RUN: llc -march=mips64 -relocation-model=static -target-abi n32 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=NEW %s
; RUN: llc -march=mips64el -relocation-model=static -target-abi n32 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM32 --check-prefix=NEW %s
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
Move the Mips target to storing the ABI in the TargetMachine rather than on MipsSubtargetInfo. This required a bit of massaging in the MC level to handle this since MC is a) largely a collection of disparate classes with no hierarchy, and b) there's no overarching equivalent to the TargetMachine, instead only the subtarget via MCSubtargetInfo (which is the base class of TargetSubtargetInfo). We're now storing the ABI in both the TargetMachine level and in the MC level because the AsmParser and the TargetStreamer both need to know what ABI we have to parse assembly and emit objects. The target streamer has a pointer to the one in the asm parser and is updated when the asm parser is created. This is fragile as the FIXME comment notes, but shouldn't be a problem in practice since we always create an asm parser before attempting to emit object code via the assembler. The TargetMachine now contains the ABI so that the DataLayout can be constructed dependent upon ABI. All testcases have been updated to use the -target-abi command line flag so that we can set the ABI without using a subtarget feature. Should be no change visible externally here. llvm-svn: 227102
2015-01-27 01:33:46 +08:00
; RUN: llc -march=mips64 -relocation-model=static -target-abi n64 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM64 --check-prefix=NEW %s
; RUN: llc -march=mips64el -relocation-model=static -target-abi n64 < %s | FileCheck --check-prefix=ALL --check-prefix=SYM64 --check-prefix=NEW %s
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
; Test the floating point arguments for all ABI's and byte orders as specified
; by section 5 of MD00305 (MIPS ABIs Described).
;
; N32/N64 are identical in this area so their checks have been combined into
; the 'NEW' prefix (the N stands for New).
@bytes = global [11 x i8] zeroinitializer
@dwords = global [11 x i64] zeroinitializer
@floats = global [11 x float] zeroinitializer
@doubles = global [11 x double] zeroinitializer
define void @double_args(double %a, double %b, double %c, double %d, double %e,
double %f, double %g, double %h, double %i) nounwind {
entry:
[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
%0 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %a, double* %0
[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
%1 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 2
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %b, double* %1
[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
%2 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 3
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %c, double* %2
[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
%3 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 4
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %d, double* %3
[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
%4 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 5
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %e, double* %4
[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
%5 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 6
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %f, double* %5
[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
%6 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 7
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %g, double* %6
[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
%7 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 8
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %h, double* %7
[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
%8 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 9
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %i, double* %8
ret void
}
; ALL-LABEL: double_args:
; We won't test the way the global address is calculated in this test. This is
; just to get the register number for the other checks.
; SYM32-DAG: addiu [[R2:\$[0-9]+]], ${{[0-9]+}}, %lo(doubles)
; SYM64-DAG: ld [[R2:\$[0-9]]], %got_disp(doubles)(
; The first argument is floating point so floating point registers are used.
; The first argument is the same for O32/N32/N64 but the second argument differs
; by register
; ALL-DAG: sdc1 $f12, 8([[R2]])
; O32-DAG: sdc1 $f14, 16([[R2]])
; NEW-DAG: sdc1 $f13, 16([[R2]])
; O32 has run out of argument registers and starts using the stack
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 16($sp)
; O32-DAG: sdc1 [[F1]], 24([[R2]])
; NEW-DAG: sdc1 $f14, 24([[R2]])
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 24($sp)
; O32-DAG: sdc1 [[F1]], 32([[R2]])
; NEW-DAG: sdc1 $f15, 32([[R2]])
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 32($sp)
; O32-DAG: sdc1 [[F1]], 40([[R2]])
; NEW-DAG: sdc1 $f16, 40([[R2]])
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 40($sp)
; O32-DAG: sdc1 [[F1]], 48([[R2]])
; NEW-DAG: sdc1 $f17, 48([[R2]])
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 48($sp)
; O32-DAG: sdc1 [[F1]], 56([[R2]])
; NEW-DAG: sdc1 $f18, 56([[R2]])
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 56($sp)
; O32-DAG: sdc1 [[F1]], 64([[R2]])
; NEW-DAG: sdc1 $f19, 64([[R2]])
; N32/N64 have run out of registers and start using the stack too
; O32-DAG: ldc1 [[F1:\$f[0-9]+]], 64($sp)
; O32-DAG: sdc1 [[F1]], 72([[R2]])
; NEW-DAG: ldc1 [[F1:\$f[0-9]+]], 0($sp)
; NEW-DAG: sdc1 [[F1]], 72([[R2]])
define void @float_args(float %a, float %b, float %c, float %d, float %e,
float %f, float %g, float %h, float %i) nounwind {
entry:
[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
%0 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %a, float* %0
[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
%1 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 2
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %b, float* %1
[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
%2 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 3
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %c, float* %2
[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
%3 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 4
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %d, float* %3
[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
%4 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 5
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %e, float* %4
[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
%5 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 6
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %f, float* %5
[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
%6 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 7
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %g, float* %6
[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
%7 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 8
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %h, float* %7
[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
%8 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 9
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %i, float* %8
ret void
}
; ALL-LABEL: float_args:
; We won't test the way the global address is calculated in this test. This is
; just to get the register number for the other checks.
; SYM32-DAG: addiu [[R1:\$[0-9]+]], ${{[0-9]+}}, %lo(floats)
; SYM64-DAG: ld [[R1:\$[0-9]]], %got_disp(floats)(
; The first argument is floating point so floating point registers are used.
; The first argument is the same for O32/N32/N64 but the second argument differs
; by register
; ALL-DAG: swc1 $f12, 4([[R1]])
; O32-DAG: swc1 $f14, 8([[R1]])
; NEW-DAG: swc1 $f13, 8([[R1]])
; O32 has run out of argument registers and (in theory) starts using the stack
; I've yet to find a reference in the documentation about this but GCC uses up
; the remaining two argument slots in the GPR's first. We'll do the same for
; compatibility.
; O32-DAG: sw $6, 12([[R1]])
; NEW-DAG: swc1 $f14, 12([[R1]])
; O32-DAG: sw $7, 16([[R1]])
; NEW-DAG: swc1 $f15, 16([[R1]])
; O32 is definitely out of registers now and switches to the stack.
; O32-DAG: lwc1 [[F1:\$f[0-9]+]], 16($sp)
; O32-DAG: swc1 [[F1]], 20([[R1]])
; NEW-DAG: swc1 $f16, 20([[R1]])
; O32-DAG: lwc1 [[F1:\$f[0-9]+]], 20($sp)
; O32-DAG: swc1 [[F1]], 24([[R1]])
; NEW-DAG: swc1 $f17, 24([[R1]])
; O32-DAG: lwc1 [[F1:\$f[0-9]+]], 24($sp)
; O32-DAG: swc1 [[F1]], 28([[R1]])
; NEW-DAG: swc1 $f18, 28([[R1]])
; O32-DAG: lwc1 [[F1:\$f[0-9]+]], 28($sp)
; O32-DAG: swc1 [[F1]], 32([[R1]])
; NEW-DAG: swc1 $f19, 32([[R1]])
; N32/N64 have run out of registers and start using the stack too
; O32-DAG: lwc1 [[F1:\$f[0-9]+]], 32($sp)
; O32-DAG: swc1 [[F1]], 36([[R1]])
; NEW-DAG: lwc1 [[F1:\$f[0-9]+]], 0($sp)
; NEW-DAG: swc1 [[F1]], 36([[R1]])
define void @double_arg2(i8 %a, double %b) nounwind {
entry:
[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
%0 = getelementptr [11 x i8], [11 x i8]* @bytes, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile i8 %a, i8* %0
[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
%1 = getelementptr [11 x double], [11 x double]* @doubles, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile double %b, double* %1
ret void
}
; ALL-LABEL: double_arg2:
; We won't test the way the global address is calculated in this test. This is
; just to get the register number for the other checks.
; SYM32-DAG: addiu [[R1:\$[0-9]+]], ${{[0-9]+}}, %lo(bytes)
; SYM64-DAG: ld [[R1:\$[0-9]]], %got_disp(bytes)(
; SYM32-DAG: addiu [[R2:\$[0-9]+]], ${{[0-9]+}}, %lo(doubles)
; SYM64-DAG: ld [[R2:\$[0-9]]], %got_disp(doubles)(
; The first argument is the same in O32/N32/N64.
; ALL-DAG: sb $4, 1([[R1]])
; The first argument isn't floating point so floating point registers are not
; used in O32, but N32/N64 will still use them.
; The second slot is insufficiently aligned for double on O32 so it is skipped.
; Also, double occupies two slots on O32 and only one for N32/N64.
; O32LE-DAG: mtc1 $6, [[F1:\$f[0-9]*[02468]+]]
; O32LE-DAG: mtc1 $7, [[F2:\$f[0-9]*[13579]+]]
; O32BE-DAG: mtc1 $6, [[F2:\$f[0-9]*[13579]+]]
; O32BE-DAG: mtc1 $7, [[F1:\$f[0-9]*[02468]+]]
; O32-DAG: sdc1 [[F1]], 8([[R2]])
; NEW-DAG: sdc1 $f13, 8([[R2]])
define void @float_arg2(i8 %a, float %b) nounwind {
entry:
[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
%0 = getelementptr [11 x i8], [11 x i8]* @bytes, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile i8 %a, i8* %0
[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
%1 = getelementptr [11 x float], [11 x float]* @floats, i32 0, i32 1
[mips] Add calling convention tests covering O32, N32, and N64. Summary: I had difficulty finding tests for the N32 and N64 ABI so I've added a collection of calling convention tests based on the document MIPS ABIs Described (MD00305), the MIPSpro N32 Handbook, and the SYSV ABI. Where the documents/implementations disagree, I've used GCC to resolve the conflict. A few interesting details: * For N32, LLVM uses 64-bit pointers when saving $ra despite pointers being 32-bit. I've yet to find a supporting statement in the ABI documentation but the current behaviour matches GCC. * For O32, the non-variable portion of a varargs argument list is also subject to the rule that floating-point is passed via GPR's (on N32/N64 only the variable portion is subject to this rule). This agrees with GCC's behaviour and the SYSV ABI but contradicts part of the MIPSpro N32 Handbook which talks about O32's behaviour. * The N32 implementation has the wrong callee-saved register list. (I already have a fix for this but will commit it as a follow-up). I've left RUN-TODO lines in for O32 on MIPS64. I don't plan to support this case for now but we should revisit it. Reviewers: matheusalmeida, vmedic Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3339 llvm-svn: 206370
2014-04-16 17:59:46 +08:00
store volatile float %b, float* %1
ret void
}
; ALL-LABEL: float_arg2:
; We won't test the way the global address is calculated in this test. This is
; just to get the register number for the other checks.
; SYM32-DAG: addiu [[R1:\$[0-9]+]], ${{[0-9]+}}, %lo(bytes)
; SYM64-DAG: ld [[R1:\$[0-9]]], %got_disp(bytes)(
; SYM32-DAG: addiu [[R2:\$[0-9]+]], ${{[0-9]+}}, %lo(floats)
; SYM64-DAG: ld [[R2:\$[0-9]]], %got_disp(floats)(
; The first argument is the same in O32/N32/N64.
; ALL-DAG: sb $4, 1([[R1]])
; The first argument isn't floating point so floating point registers are not
; used in O32, but N32/N64 will still use them.
; MD00305 and GCC disagree on this one. MD00305 says that floats are treated
; as 8-byte aligned and occupy two slots on O32. GCC is treating them as 4-byte
; aligned and occupying one slot. We'll use GCC's definition.
; O32-DAG: sw $5, 4([[R2]])
; NEW-DAG: swc1 $f13, 4([[R2]])