maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Other/constant-fold-gep.ll

488 lines
20 KiB
LLVM
Raw Normal View History

Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; "PLAIN" - No optimizations. This tests the default target layout
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; constant folder.
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; RUN: opt -S -o - < %s | FileCheck --check-prefix=PLAIN %s
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; "OPT" - Optimizations but no targetdata. This tests default target layout
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; folding in the optimizers.
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; RUN: opt -S -o - -instcombine -globalopt < %s | FileCheck --check-prefix=OPT %s
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; "TO" - Optimizations and targetdata. This tests target-dependent
; folding in the optimizers.
; RUN: opt -S -o - -instcombine -globalopt -default-data-layout="e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64" < %s | FileCheck --check-prefix=TO %s
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; "SCEV" - ScalarEvolution with default target layout
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; RUN: opt -analyze -scalar-evolution < %s | FileCheck --check-prefix=SCEV %s
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; The automatic constant folder in opt does not have targetdata access, so
; it can't fold gep arithmetic, in general. However, the constant folder run
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; from instcombine and global opt can use targetdata.
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: @G8 = global i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -1)
; PLAIN: @G1 = global i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -1)
; PLAIN: @F8 = global i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -2)
; PLAIN: @F1 = global i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -2)
; PLAIN: @H8 = global i8* getelementptr (i8, i8* null, i32 -1)
; PLAIN: @H1 = global i1* getelementptr (i1, i1* null, i32 -1)
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: @G8 = global i8* null
; OPT: @G1 = global i1* null
; OPT: @F8 = global i8* inttoptr (i64 -1 to i8*)
; OPT: @F1 = global i1* inttoptr (i64 -1 to i1*)
; OPT: @H8 = global i8* inttoptr (i64 -1 to i8*)
; OPT: @H1 = global i1* inttoptr (i64 -1 to i1*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: @G8 = global i8* null
; TO: @G1 = global i1* null
; TO: @F8 = global i8* inttoptr (i64 -1 to i8*)
; TO: @F1 = global i1* inttoptr (i64 -1 to i1*)
; TO: @H8 = global i8* inttoptr (i64 -1 to i8*)
; TO: @H1 = global i1* inttoptr (i64 -1 to i1*)
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
@G8 = global i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -1)
@G1 = global i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -1)
@F8 = global i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -2)
@F1 = global i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -2)
@H8 = global i8* getelementptr (i8, i8* inttoptr (i32 0 to i8*), i32 -1)
@H1 = global i1* getelementptr (i1, i1* inttoptr (i32 0 to i1*), i32 -1)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; The target-independent folder should be able to do some clever
; simplifications on sizeof, alignof, and offsetof expressions. The
; target-dependent folder should fold these down to constants.
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: @a = constant i64 mul (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2310)
; PLAIN: @b = constant i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64)
; PLAIN: @c = constant i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2)
; PLAIN: @d = constant i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 11)
; PLAIN: @e = constant i64 ptrtoint (double* getelementptr ({ double, float, double, double }, { double, float, double, double }* null, i64 0, i32 2) to i64)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: @f = constant i64 1
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: @g = constant i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64)
; PLAIN: @h = constant i64 ptrtoint (i1** getelementptr (i1*, i1** null, i32 1) to i64)
; PLAIN: @i = constant i64 ptrtoint (i1** getelementptr ({ i1, i1* }, { i1, i1* }* null, i64 0, i32 1) to i64)
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: @a = constant i64 18480
; OPT: @b = constant i64 8
; OPT: @c = constant i64 16
; OPT: @d = constant i64 88
; OPT: @e = constant i64 16
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: @f = constant i64 1
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: @g = constant i64 8
; OPT: @h = constant i64 8
; OPT: @i = constant i64 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: @a = constant i64 18480
; TO: @b = constant i64 8
; TO: @c = constant i64 16
; TO: @d = constant i64 88
; TO: @e = constant i64 16
; TO: @f = constant i64 1
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; TO: @g = constant i64 8
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; TO: @h = constant i64 8
; TO: @i = constant i64 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
@a = constant i64 mul (i64 3, i64 mul (i64 ptrtoint ({[7 x double], [7 x double]}* getelementptr ({[7 x double], [7 x double]}, {[7 x double], [7 x double]}* null, i64 11) to i64), i64 5))
@b = constant i64 ptrtoint ([13 x double]* getelementptr ({i1, [13 x double]}, {i1, [13 x double]}* null, i64 0, i32 1) to i64)
@c = constant i64 ptrtoint (double* getelementptr ({double, double, double, double}, {double, double, double, double}* null, i64 0, i32 2) to i64)
@d = constant i64 ptrtoint (double* getelementptr ([13 x double], [13 x double]* null, i64 0, i32 11) to i64)
@e = constant i64 ptrtoint (double* getelementptr ({double, float, double, double}, {double, float, double, double}* null, i64 0, i32 2) to i64)
@f = constant i64 ptrtoint (<{ i16, i128 }>* getelementptr ({i1, <{ i16, i128 }>}, {i1, <{ i16, i128 }>}* null, i64 0, i32 1) to i64)
@g = constant i64 ptrtoint ({double, double}* getelementptr ({i1, {double, double}}, {i1, {double, double}}* null, i64 0, i32 1) to i64)
@h = constant i64 ptrtoint (double** getelementptr (double*, double** null, i64 1) to i64)
@i = constant i64 ptrtoint (double** getelementptr ({i1, double*}, {i1, double*}* null, i64 0, i32 1) to i64)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; The target-dependent folder should cast GEP indices to integer-sized pointers.
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: @M = constant i64* getelementptr (i64, i64* null, i32 1)
; PLAIN: @N = constant i64* getelementptr ({ i64, i64 }, { i64, i64 }* null, i32 0, i32 1)
; PLAIN: @O = constant i64* getelementptr ([2 x i64], [2 x i64]* null, i32 0, i32 1)
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: @M = constant i64* inttoptr (i64 8 to i64*)
; OPT: @N = constant i64* inttoptr (i64 8 to i64*)
; OPT: @O = constant i64* inttoptr (i64 8 to i64*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: @M = constant i64* inttoptr (i64 8 to i64*)
; TO: @N = constant i64* inttoptr (i64 8 to i64*)
; TO: @O = constant i64* inttoptr (i64 8 to i64*)
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
@M = constant i64* getelementptr (i64, i64* null, i32 1)
@N = constant i64* getelementptr ({ i64, i64 }, { i64, i64 }* null, i32 0, i32 1)
@O = constant i64* getelementptr ([2 x i64], [2 x i64]* null, i32 0, i32 1)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
Make constant folding for GEPs a bit more aggressive. llvm-svn: 146639
2011-12-15 12:33:48 +08:00
; Fold GEP of a GEP. Very simple cases are folded without targetdata.
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: @Y = global [3 x { i32, i32 }]* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 2)
; PLAIN: @Z = global i32* getelementptr inbounds (i32, i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 0), i64 1)
; OPT: @Y = global [3 x { i32, i32 }]* getelementptr ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 2)
; OPT: @Z = global i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 1)
; TO: @Y = global [3 x { i32, i32 }]* getelementptr ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 2)
; TO: @Z = global i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 1)
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
@ext = external global [3 x { i32, i32 }]
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
@Y = global [3 x { i32, i32 }]* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 1), i64 1)
@Z = global i32* getelementptr inbounds (i32, i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 0), i64 1)
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; Duplicate all of the above as function return values rather than
; global initializers.
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i8* @goo8() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -1) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i1* @goo1() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -1) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i1* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i8* @foo8() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -2) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i1* @foo1() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -2) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i1* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i8* @hoo8() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i8* getelementptr (i8, i8* null, i32 -1) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i1* @hoo1() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i1* getelementptr (i1, i1* null, i32 -1) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i1* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i8* @goo8() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i8* null
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i1* @goo1() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i1* null
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i8* @foo8() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i8* inttoptr (i64 -1 to i8*)
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i1* @foo1() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i1* inttoptr (i64 -1 to i1*)
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i8* @hoo8() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i8* inttoptr (i64 -1 to i8*)
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i1* @hoo1() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i1* inttoptr (i64 -1 to i1*)
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i8* @goo8() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i8* null
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i1* @goo1() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i1* null
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i8* @foo8() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i8* inttoptr (i64 -1 to i8*)
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i1* @foo1() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i1* inttoptr (i64 -1 to i1*)
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i8* @hoo8() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i8* inttoptr (i64 -1 to i8*)
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i1* @hoo1() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i1* inttoptr (i64 -1 to i1*)
; TO: }
; SCEV: Classifying expressions for: @goo8
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -1) to i8*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> (-1 + inttoptr (i32 1 to i8*))
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @goo1
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -1) to i1*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> (-1 + inttoptr (i32 1 to i1*))
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @foo8
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -2) to i8*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> (-2 + inttoptr (i32 1 to i8*))
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @foo1
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -2) to i1*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> (-2 + inttoptr (i32 1 to i1*))
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @hoo8
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> -1
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @hoo1
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> -1
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
define i8* @goo8() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -1) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
define i1* @goo1() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -1) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i1* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
define i8* @foo8() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 1 to i8*), i32 -2) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
define i1* @foo1() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 1 to i1*), i32 -2) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i1* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
define i8* @hoo8() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i8* getelementptr (i8, i8* inttoptr (i32 0 to i8*), i32 -1) to i8*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i8* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
define i1* @hoo1() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i1* getelementptr (i1, i1* inttoptr (i32 0 to i1*), i32 -1) to i1*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i1* %t
}
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fa() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 mul (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2310) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fb() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fc() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fd() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 11) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fe() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 ptrtoint (double* getelementptr ({ double, float, double, double }, { double, float, double, double }* null, i64 0, i32 2) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @ff() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: %t = bitcast i64 1 to i64
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fg() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64) to i64
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fh() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 ptrtoint (i1** getelementptr (i1*, i1** null, i32 1) to i64) to i64
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64 @fi() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64 ptrtoint (i1** getelementptr ({ i1, i1* }, { i1, i1* }* null, i64 0, i32 1) to i64) to i64
Teach the constant folder about union types. llvm-svn: 97142
2010-02-26 00:45:19 +08:00
; PLAIN: ret i64 %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fa() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 18480
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fb() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fc() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 16
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fd() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 88
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fe() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 16
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @ff() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: ret i64 1
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fg() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 8
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fh() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 8
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64 @fi() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64 8
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fa() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 18480
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fb() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 8
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fc() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 16
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fd() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 88
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fe() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 16
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @ff() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64 1
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fg() #0 {
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; TO: ret i64 8
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fh() #0 {
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; TO: ret i64 8
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64 @fi() #0 {
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; TO: ret i64 8
; TO: }
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @fa
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 mul (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2310) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> (2310 * sizeof(double))
; SCEV: Classifying expressions for: @fb
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> alignof(double)
; SCEV: Classifying expressions for: @fc
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 2) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> (2 * sizeof(double))
; SCEV: Classifying expressions for: @fd
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 mul nuw (i64 ptrtoint (double* getelementptr (double, double* null, i32 1) to i64), i64 11) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> (11 * sizeof(double))
; SCEV: Classifying expressions for: @fe
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 ptrtoint (double* getelementptr ({ double, float, double, double }, { double, float, double, double }* null, i64 0, i32 2) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> offsetof({ double, float, double, double }, 2)
; SCEV: Classifying expressions for: @ff
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: %t = bitcast i64 1 to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: --> 1
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; SCEV: Classifying expressions for: @fg
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 ptrtoint (double* getelementptr ({ i1, double }, { i1, double }* null, i64 0, i32 1) to i64) to i64
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
; SCEV: --> alignof(double)
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; SCEV: Classifying expressions for: @fh
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 ptrtoint (i1** getelementptr (i1*, i1** null, i32 1) to i64) to i64
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; SCEV: --> sizeof(i1*)
; SCEV: Classifying expressions for: @fi
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64 ptrtoint (i1** getelementptr ({ i1, i1* }, { i1, i1* }* null, i64 0, i32 1) to i64) to i64
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
; SCEV: --> alignof(i1*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
define i64 @fa() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 mul (i64 3, i64 mul (i64 ptrtoint ({[7 x double], [7 x double]}* getelementptr ({[7 x double], [7 x double]}, {[7 x double], [7 x double]}* null, i64 11) to i64), i64 5)) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
define i64 @fb() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint ([13 x double]* getelementptr ({i1, [13 x double]}, {i1, [13 x double]}* null, i64 0, i32 1) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
define i64 @fc() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (double* getelementptr ({double, double, double, double}, {double, double, double, double}* null, i64 0, i32 2) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
define i64 @fd() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (double* getelementptr ([13 x double], [13 x double]* null, i64 0, i32 11) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
define i64 @fe() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (double* getelementptr ({double, float, double, double}, {double, float, double, double}* null, i64 0, i32 2) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
define i64 @ff() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (<{ i16, i128 }>* getelementptr ({i1, <{ i16, i128 }>}, {i1, <{ i16, i128 }>}* null, i64 0, i32 1) to i64) to i64
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64 %t
}
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
define i64 @fg() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint ({double, double}* getelementptr ({i1, {double, double}}, {i1, {double, double}}* null, i64 0, i32 1) to i64) to i64
Factor out alignof expression folding into a separate function and generalize it to handle more cases. llvm-svn: 95045
2010-02-02 09:41:39 +08:00
ret i64 %t
}
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
define i64 @fh() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (double** getelementptr (double*, double** null, i32 1) to i64) to i64
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
ret i64 %t
}
define i64 @fi() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64 ptrtoint (double** getelementptr ({i1, double*}, {i1, double*}* null, i64 0, i32 1) to i64) to i64
Canonicalize sizeof and alignof on pointer types to a canonical pointer type. llvm-svn: 95769
2010-02-10 14:13:07 +08:00
ret i64 %t
}
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64* @fM() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64* getelementptr (i64, i64* null, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64* %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64* @fN() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64* getelementptr ({ i64, i64 }, { i64, i64 }* null, i32 0, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64* %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i64* @fO() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i64* getelementptr ([2 x i64], [2 x i64]* null, i32 0, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; PLAIN: ret i64* %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64* @fM() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64* inttoptr (i64 8 to i64*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64* @fN() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64* inttoptr (i64 8 to i64*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i64* @fO() #0 {
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; OPT: ret i64* inttoptr (i64 8 to i64*)
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64* @fM() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64* inttoptr (i64 8 to i64*)
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64* @fN() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64* inttoptr (i64 8 to i64*)
; TO: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i64* @fO() #0 {
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; TO: ret i64* inttoptr (i64 8 to i64*)
; TO: }
; SCEV: Classifying expressions for: @fM
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64* getelementptr (i64, i64* null, i32 1) to i64*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @fN
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64* getelementptr ({ i64, i64 }, { i64, i64 }* null, i32 0, i32 1) to i64*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
; SCEV: Classifying expressions for: @fO
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i64* getelementptr ([2 x i64], [2 x i64]* null, i32 0, i32 1) to i64*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> 8
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
define i64* @fM() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64* getelementptr (i64, i64* null, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64* %t
}
define i64* @fN() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64* getelementptr ({ i64, i64 }, { i64, i64 }* null, i32 0, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64* %t
}
define i64* @fO() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i64* getelementptr ([2 x i64], [2 x i64]* null, i32 0, i32 1) to i64*
Generalize target-independent folding rules for sizeof to handle more cases, and implement target-independent folding rules for alignof and offsetof. Also, reassociate reassociative operators when it leads to more folding. Generalize ScalarEvolution's isOffsetOf to recognize offsetof on arrays. Rename getAllocSizeExpr to getSizeOfExpr, and getFieldOffsetExpr to getOffsetOfExpr, for consistency with analagous ConstantExpr routines. Make the target-dependent folder promote GEP array indices to pointer-sized integers, to make implicit casting explicit and exposed to subsequent folding. And add a bunch of testcases for this new functionality, and a bunch of related existing functionality. llvm-svn: 94987
2010-02-02 02:27:38 +08:00
ret i64* %t
Remove the folding rule getelementptr (i8* inttoptr (i64 1 to i8*), i32 -1) to inttoptr (i64 0 to i8*) from the VMCore constant folder. It didn't handle sign-extension properly in the case where the source integer is smaller than a pointer size. And, it relied on an assumption about sizeof(i8). The Analysis constant folder still folds these kinds of things; it has access to TargetData, so it can do them right. Add a testcase which tests that the VMCore constant folder doesn't miscompile this, and that the Analysis folder does fold it. llvm-svn: 94750
2010-01-29 02:08:26 +08:00
}
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; PLAIN: define i32* @fZ() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; PLAIN: %t = bitcast i32* getelementptr inbounds (i32, i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 0), i64 1) to i32*
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
; PLAIN: ret i32* %t
; PLAIN: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; OPT: define i32* @fZ() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; OPT: ret i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 1)
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
; OPT: }
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; TO: define i32* @fZ() #0 {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; TO: ret i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 1)
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
; TO: }
; SCEV: Classifying expressions for: @fZ
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; SCEV: %t = bitcast i32* getelementptr inbounds (i32, i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 0), i64 1) to i32*
Make DataLayout Non-Optional in the Module Summary: DataLayout keeps the string used for its creation. As a side effect it is no longer needed in the Module. This is "almost" NFC, the string is no longer canonicalized, you can't rely on two "equals" DataLayout having the same string returned by getStringRepresentation(). Get rid of DataLayoutPass: the DataLayout is in the Module The DataLayout is "per-module", let's enforce this by not duplicating it more than necessary. One more step toward non-optionality of the DataLayout in the module. Make DataLayout Non-Optional in the Module Module->getDataLayout() will never returns nullptr anymore. Reviewers: echristo Subscribers: resistor, llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D7992 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 231270
2015-03-05 02:43:29 +08:00
; SCEV: --> (12 + @ext)
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
define i32* @fZ() nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
%t = bitcast i32* getelementptr inbounds (i32, i32* getelementptr inbounds ([3 x { i32, i32 }], [3 x { i32, i32 }]* @ext, i64 0, i64 1, i32 0), i64 1) to i32*
Constant-fold GEP-of-GEP into a single GEP. llvm-svn: 98178
2010-03-11 03:31:51 +08:00
ret i32* %t
}
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
IR: Don't constant fold GEP bitcasts between different address spaces PR15262 reported a bug where the following instruction: i8 getelementptr inbounds i8* bitcast ([4 x i8] addrspace(12)* @buf to i8*), i32 2 was getting folded into: addrspace(12)* getelementptr inbounds ([4 x i8] addrspace(12)* @buf, i32 0, i32 2) This caused instcombine to crash because the original instruction and the folded instruction have different types. The issue was fixed by disallowing bitcasts between different address spaces to be folded away. llvm-svn: 176156
2013-02-27 10:26:42 +08:00
; PR15262 - Check GEP folding with casts between address spaces.
@p0 = global [4 x i8] zeroinitializer, align 1
@p12 = addrspace(12) global [4 x i8] zeroinitializer, align 1
define i8* @different_addrspace() nounwind noinline {
; OPT: different_addrspace
[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
%p = getelementptr inbounds i8, i8* addrspacecast ([4 x i8] addrspace(12)* @p12 to i8*),
IR: Don't constant fold GEP bitcasts between different address spaces PR15262 reported a bug where the following instruction: i8 getelementptr inbounds i8* bitcast ([4 x i8] addrspace(12)* @buf to i8*), i32 2 was getting folded into: addrspace(12)* getelementptr inbounds ([4 x i8] addrspace(12)* @buf, i32 0, i32 2) This caused instcombine to crash because the original instruction and the folded instruction have different types. The issue was fixed by disallowing bitcasts between different address spaces to be folded away. llvm-svn: 176156
2013-02-27 10:26:42 +08:00
i32 2
ret i8* %p
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; OPT: ret i8* getelementptr ([4 x i8], [4 x i8]* addrspacecast ([4 x i8] addrspace(12)* @p12 to [4 x i8]*), i64 0, i64 2)
IR: Don't constant fold GEP bitcasts between different address spaces PR15262 reported a bug where the following instruction: i8 getelementptr inbounds i8* bitcast ([4 x i8] addrspace(12)* @buf to i8*), i32 2 was getting folded into: addrspace(12)* getelementptr inbounds ([4 x i8] addrspace(12)* @buf, i32 0, i32 2) This caused instcombine to crash because the original instruction and the folded instruction have different types. The issue was fixed by disallowing bitcasts between different address spaces to be folded away. llvm-svn: 176156
2013-02-27 10:26:42 +08:00
}
define i8* @same_addrspace() nounwind noinline {
; OPT: same_addrspace
[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
%p = getelementptr inbounds i8, i8* bitcast ([4 x i8] * @p0 to i8*), i32 2
IR: Don't constant fold GEP bitcasts between different address spaces PR15262 reported a bug where the following instruction: i8 getelementptr inbounds i8* bitcast ([4 x i8] addrspace(12)* @buf to i8*), i32 2 was getting folded into: addrspace(12)* getelementptr inbounds ([4 x i8] addrspace(12)* @buf, i32 0, i32 2) This caused instcombine to crash because the original instruction and the folded instruction have different types. The issue was fixed by disallowing bitcasts between different address spaces to be folded away. llvm-svn: 176156
2013-02-27 10:26:42 +08:00
ret i8* %p
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
; OPT: ret i8* getelementptr inbounds ([4 x i8], [4 x i8]* @p0, i64 0, i64 2)
IR: Don't constant fold GEP bitcasts between different address spaces PR15262 reported a bug where the following instruction: i8 getelementptr inbounds i8* bitcast ([4 x i8] addrspace(12)* @buf to i8*), i32 2 was getting folded into: addrspace(12)* getelementptr inbounds ([4 x i8] addrspace(12)* @buf, i32 0, i32 2) This caused instcombine to crash because the original instruction and the folded instruction have different types. The issue was fixed by disallowing bitcasts between different address spaces to be folded away. llvm-svn: 176156
2013-02-27 10:26:42 +08:00
}
IR: Fold away compares between GV GEPs and GVs A GEP of a non-weak global variable will not be equivalent to another non-weak global variable or a GEP of such a variable. Differential Revision: http://reviews.llvm.org/D4238 llvm-svn: 212360
2014-07-05 06:05:26 +08:00
@gv1 = internal global i32 1
@gv2 = internal global [1 x i32] [ i32 2 ]
@gv3 = internal global [1 x i32] [ i32 2 ]
; Handled by TI-independent constant folder
define i1 @gv_gep_vs_gv() {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
ret i1 icmp eq (i32* getelementptr inbounds ([1 x i32], [1 x i32]* @gv2, i32 0, i32 0), i32* @gv1)
IR: Fold away compares between GV GEPs and GVs A GEP of a non-weak global variable will not be equivalent to another non-weak global variable or a GEP of such a variable. Differential Revision: http://reviews.llvm.org/D4238 llvm-svn: 212360
2014-07-05 06:05:26 +08:00
}
; PLAIN: gv_gep_vs_gv
; PLAIN: ret i1 false
define i1 @gv_gep_vs_gv_gep() {
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
ret i1 icmp eq (i32* getelementptr inbounds ([1 x i32], [1 x i32]* @gv2, i32 0, i32 0), i32* getelementptr inbounds ([1 x i32], [1 x i32]* @gv3, i32 0, i32 0))
IR: Fold away compares between GV GEPs and GVs A GEP of a non-weak global variable will not be equivalent to another non-weak global variable or a GEP of such a variable. Differential Revision: http://reviews.llvm.org/D4238 llvm-svn: 212360
2014-07-05 06:05:26 +08:00
}
; PLAIN: gv_gep_vs_gv_gep
; PLAIN: ret i1 false
Modify the LLVM assembly output so that it uses references to represent function attributes. This makes the LLVM assembly look better. E.g.: define void @foo() #0 { ret void } attributes #0 = { nounwind noinline ssp } llvm-svn: 175605
2013-02-20 15:21:42 +08:00
; CHECK: attributes #0 = { nounwind }