1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 21:42:54 +02:00
llvm-mirror/test/Transforms/FunctionAttrs/nocapture.ll

196 lines
5.1 KiB
LLVM
Raw Normal View History

; RUN: opt < %s -functionattrs -S | FileCheck %s
@g = global i32* null ; <i32**> [#uses=1]
; CHECK: define i32* @c1(i32* readnone %q)
define i32* @c1(i32* %q) {
ret i32* %q
}
; CHECK: define void @c2(i32* %q)
; It would also be acceptable to mark %q as readnone. Update @c3 too.
define void @c2(i32* %q) {
store i32* %q, i32** @g
ret void
}
; CHECK: define void @c3(i32* %q)
define void @c3(i32* %q) {
call void @c2(i32* %q)
ret void
}
; CHECK: define i1 @c4(i32* %q, i32 %bitno)
define i1 @c4(i32* %q, i32 %bitno) {
%tmp = ptrtoint i32* %q to i32
%tmp2 = lshr i32 %tmp, %bitno
%bit = trunc i32 %tmp2 to i1
br i1 %bit, label %l1, label %l0
l0:
ret i1 0 ; escaping value not caught by def-use chaining.
l1:
ret i1 1 ; escaping value not caught by def-use chaining.
}
@lookup_table = global [2 x i1] [ i1 0, i1 1 ]
; CHECK: define i1 @c5(i32* %q, i32 %bitno)
define i1 @c5(i32* %q, i32 %bitno) {
%tmp = ptrtoint i32* %q to i32
%tmp2 = lshr i32 %tmp, %bitno
%bit = and i32 %tmp2, 1
; subtle escape mechanism follows
[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
2015-02-27 20:29:02 +01:00
%lookup = getelementptr [2 x i1], [2 x i1]* @lookup_table, i32 0, i32 %bit
%val = load i1, i1* %lookup
ret i1 %val
}
declare void @throw_if_bit_set(i8*, i8) readonly
; CHECK: define i1 @c6(i8* readonly %q, i8 %bit)
define i1 @c6(i8* %q, i8 %bit) {
invoke void @throw_if_bit_set(i8* %q, i8 %bit)
to label %ret0 unwind label %ret1
ret0:
ret i1 0
ret1:
%exn = landingpad {i8*, i32} personality i32 (...)* @__gxx_personality_v0
cleanup
ret i1 1
}
declare i32 @__gxx_personality_v0(...)
define i1* @lookup_bit(i32* %q, i32 %bitno) readnone nounwind {
%tmp = ptrtoint i32* %q to i32
%tmp2 = lshr i32 %tmp, %bitno
%bit = and i32 %tmp2, 1
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-27 20:29:02 +01:00
%lookup = getelementptr [2 x i1], [2 x i1]* @lookup_table, i32 0, i32 %bit
ret i1* %lookup
}
; CHECK: define i1 @c7(i32* readonly %q, i32 %bitno)
define i1 @c7(i32* %q, i32 %bitno) {
%ptr = call i1* @lookup_bit(i32* %q, i32 %bitno)
%val = load i1, i1* %ptr
ret i1 %val
}
; CHECK: define i32 @nc1(i32* %q, i32* nocapture %p, i1 %b)
define i32 @nc1(i32* %q, i32* %p, i1 %b) {
e:
br label %l
l:
%x = phi i32* [ %p, %e ]
%y = phi i32* [ %q, %e ]
%tmp = bitcast i32* %x to i32* ; <i32*> [#uses=2]
%tmp2 = select i1 %b, i32* %tmp, i32* %y
%val = load i32, i32* %tmp2 ; <i32> [#uses=1]
store i32 0, i32* %tmp
store i32* %y, i32** @g
ret i32 %val
}
; CHECK: define i32 @nc1_addrspace(i32* %q, i32 addrspace(1)* nocapture %p, i1 %b)
define i32 @nc1_addrspace(i32* %q, i32 addrspace(1)* %p, i1 %b) {
e:
br label %l
l:
%x = phi i32 addrspace(1)* [ %p, %e ]
%y = phi i32* [ %q, %e ]
%tmp = addrspacecast i32 addrspace(1)* %x to i32* ; <i32*> [#uses=2]
%tmp2 = select i1 %b, i32* %tmp, i32* %y
%val = load i32, i32* %tmp2 ; <i32> [#uses=1]
store i32 0, i32* %tmp
store i32* %y, i32** @g
ret i32 %val
}
; CHECK: define void @nc2(i32* nocapture %p, i32* %q)
define void @nc2(i32* %p, i32* %q) {
%1 = call i32 @nc1(i32* %q, i32* %p, i1 0) ; <i32> [#uses=0]
ret void
}
; CHECK: define void @nc3(void ()* nocapture %p)
define void @nc3(void ()* %p) {
call void %p()
ret void
}
declare void @external(i8*) readonly nounwind
; CHECK: define void @nc4(i8* nocapture readonly %p)
define void @nc4(i8* %p) {
call void @external(i8* %p)
ret void
}
; CHECK: define void @nc5(void (i8*)* nocapture %f, i8* nocapture %p)
define void @nc5(void (i8*)* %f, i8* %p) {
call void %f(i8* %p) readonly nounwind
call void %f(i8* nocapture %p)
ret void
}
; CHECK: define void @test1_1(i8* nocapture readnone %x1_1, i8* %y1_1)
; It would be acceptable to add readnone to %y1_1 and %y1_2.
define void @test1_1(i8* %x1_1, i8* %y1_1) {
call i8* @test1_2(i8* %x1_1, i8* %y1_1)
store i32* null, i32** @g
ret void
}
; CHECK: define i8* @test1_2(i8* nocapture readnone %x1_2, i8* %y1_2)
define i8* @test1_2(i8* %x1_2, i8* %y1_2) {
call void @test1_1(i8* %x1_2, i8* %y1_2)
store i32* null, i32** @g
ret i8* %y1_2
}
; CHECK: define void @test2(i8* nocapture readnone %x2)
define void @test2(i8* %x2) {
call void @test2(i8* %x2)
store i32* null, i32** @g
ret void
}
; CHECK: define void @test3(i8* nocapture readnone %x3, i8* nocapture readnone %y3, i8* nocapture readnone %z3)
define void @test3(i8* %x3, i8* %y3, i8* %z3) {
call void @test3(i8* %z3, i8* %y3, i8* %x3)
store i32* null, i32** @g
ret void
}
; CHECK: define void @test4_1(i8* %x4_1)
define void @test4_1(i8* %x4_1) {
call i8* @test4_2(i8* %x4_1, i8* %x4_1, i8* %x4_1)
store i32* null, i32** @g
ret void
}
; CHECK: define i8* @test4_2(i8* nocapture readnone %x4_2, i8* readnone %y4_2, i8* nocapture readnone %z4_2)
define i8* @test4_2(i8* %x4_2, i8* %y4_2, i8* %z4_2) {
call void @test4_1(i8* null)
store i32* null, i32** @g
ret i8* %y4_2
}
declare i8* @test5_1(i8* %x5_1)
; CHECK: define void @test5_2(i8* %x5_2)
define void @test5_2(i8* %x5_2) {
call i8* @test5_1(i8* %x5_2)
store i32* null, i32** @g
ret void
}
declare void @test6_1(i8* %x6_1, i8* nocapture %y6_1, ...)
; CHECK: define void @test6_2(i8* %x6_2, i8* nocapture %y6_2, i8* %z6_2)
define void @test6_2(i8* %x6_2, i8* %y6_2, i8* %z6_2) {
call void (i8*, i8*, ...)* @test6_1(i8* %x6_2, i8* %y6_2, i8* %z6_2)
store i32* null, i32** @g
ret void
}