1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 12:33:33 +02:00
llvm-mirror/test/Transforms/InstCombine/addrspacecast.ll

148 lines
6.3 KiB
LLVM
Raw Normal View History

; RUN: opt -instcombine -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-p1:32:32:32-p2:16:16:16-n8:16:32:64"
declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) nounwind
declare void @llvm.memcpy.p0i8.p1i8.i32(i8*, i8 addrspace(1)*, i32, i32, i1) nounwind
declare void @llvm.memcpy.p0i8.p2i8.i32(i8*, i8 addrspace(2)*, i32, i32, i1) nounwind
define i32* @combine_redundant_addrspacecast(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_redundant_addrspacecast(
; CHECK: addrspacecast i32 addrspace(1)* %x to i32*
; CHECK-NEXT: ret
%y = addrspacecast i32 addrspace(1)* %x to i32 addrspace(3)*
%z = addrspacecast i32 addrspace(3)* %y to i32*
ret i32* %z
}
define <4 x i32*> @combine_redundant_addrspacecast_vector(<4 x i32 addrspace(1)*> %x) nounwind {
; CHECK-LABEL: @combine_redundant_addrspacecast_vector(
; CHECK: addrspacecast <4 x i32 addrspace(1)*> %x to <4 x i32*>
; CHECK-NEXT: ret
%y = addrspacecast <4 x i32 addrspace(1)*> %x to <4 x i32 addrspace(3)*>
%z = addrspacecast <4 x i32 addrspace(3)*> %y to <4 x i32*>
ret <4 x i32*> %z
}
define float* @combine_redundant_addrspacecast_types(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_redundant_addrspacecast_types(
; CHECK-NEXT: bitcast i32 addrspace(1)* %x to float addrspace(1)*
; CHECK-NEXT: addrspacecast float addrspace(1)* %1 to float*
; CHECK-NEXT: ret
%y = addrspacecast i32 addrspace(1)* %x to i32 addrspace(3)*
%z = addrspacecast i32 addrspace(3)* %y to float*
ret float* %z
}
define <4 x float*> @combine_redundant_addrspacecast_types_vector(<4 x i32 addrspace(1)*> %x) nounwind {
; CHECK-LABEL: @combine_redundant_addrspacecast_types_vector(
; CHECK-NEXT: bitcast <4 x i32 addrspace(1)*> %x to <4 x float addrspace(1)*>
; CHECK-NEXT: addrspacecast <4 x float addrspace(1)*> %1 to <4 x float*>
; CHECK-NEXT: ret
%y = addrspacecast <4 x i32 addrspace(1)*> %x to <4 x i32 addrspace(3)*>
%z = addrspacecast <4 x i32 addrspace(3)*> %y to <4 x float*>
ret <4 x float*> %z
}
define float addrspace(2)* @combine_addrspacecast_bitcast_1(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_addrspacecast_bitcast_1(
; CHECK-NEXT: bitcast i32 addrspace(1)* %x to float addrspace(1)*
; CHECK-NEXT: addrspacecast float addrspace(1)* %1 to float addrspace(2)*
; CHECK-NEXT: ret
%y = addrspacecast i32 addrspace(1)* %x to i32 addrspace(2)*
%z = bitcast i32 addrspace(2)* %y to float addrspace(2)*
ret float addrspace(2)* %z
}
define i32 addrspace(2)* @combine_addrspacecast_bitcast_2(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_addrspacecast_bitcast_2(
; CHECK: addrspacecast i32 addrspace(1)* %x to i32 addrspace(2)*
; CHECK-NEXT: ret
%y = addrspacecast i32 addrspace(1)* %x to float addrspace(2)*
%z = bitcast float addrspace(2)* %y to i32 addrspace(2)*
ret i32 addrspace(2)* %z
}
define i32 addrspace(2)* @combine_bitcast_addrspacecast_1(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_bitcast_addrspacecast_1(
; CHECK: addrspacecast i32 addrspace(1)* %x to i32 addrspace(2)*
; CHECK-NEXT: ret
%y = bitcast i32 addrspace(1)* %x to i8 addrspace(1)*
%z = addrspacecast i8 addrspace(1)* %y to i32 addrspace(2)*
ret i32 addrspace(2)* %z
}
define float addrspace(2)* @combine_bitcast_addrspacecast_2(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_bitcast_addrspacecast_2(
; CHECK: bitcast i32 addrspace(1)* %x to float addrspace(1)*
; CHECK: addrspacecast float addrspace(1)* %1 to float addrspace(2)*
; CHECK-NEXT: ret
%y = bitcast i32 addrspace(1)* %x to i8 addrspace(1)*
%z = addrspacecast i8 addrspace(1)* %y to float addrspace(2)*
ret float addrspace(2)* %z
}
define float addrspace(2)* @combine_addrspacecast_types(i32 addrspace(1)* %x) nounwind {
; CHECK-LABEL: @combine_addrspacecast_types(
; CHECK-NEXT: bitcast i32 addrspace(1)* %x to float addrspace(1)*
; CHECK-NEXT: addrspacecast float addrspace(1)* %1 to float addrspace(2)*
; CHECK-NEXT: ret
%y = addrspacecast i32 addrspace(1)* %x to float addrspace(2)*
ret float addrspace(2)* %y
}
define <4 x float addrspace(2)*> @combine_addrspacecast_types_vector(<4 x i32 addrspace(1)*> %x) nounwind {
; CHECK-LABEL: @combine_addrspacecast_types_vector(
; CHECK-NEXT: bitcast <4 x i32 addrspace(1)*> %x to <4 x float addrspace(1)*>
; CHECK-NEXT: addrspacecast <4 x float addrspace(1)*> %1 to <4 x float addrspace(2)*>
; CHECK-NEXT: ret
%y = addrspacecast <4 x i32 addrspace(1)*> %x to <4 x float addrspace(2)*>
ret <4 x float addrspace(2)*> %y
}
define i32 @canonicalize_addrspacecast([16 x i32] addrspace(1)* %arr) {
; CHECK-LABEL: @canonicalize_addrspacecast(
[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
; CHECK-NEXT: getelementptr inbounds [16 x i32], [16 x i32] addrspace(1)* %arr, i32 0, i32 0
; CHECK-NEXT: addrspacecast i32 addrspace(1)* %{{[a-zA-Z0-9]+}} to i32*
; CHECK-NEXT: load i32, i32*
; CHECK-NEXT: ret i32
%p = addrspacecast [16 x i32] addrspace(1)* %arr to i32*
%v = load i32, i32* %p
ret i32 %v
}
@const_array = addrspace(2) constant [60 x i8] [i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22,
i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22,
i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22,
i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22,
i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22 ]
declare void @foo(i8*) nounwind
; A copy from a constant addrspacecast'ed global
; CHECK-LABEL: @memcpy_addrspacecast(
; CHECK-NOT: call void @llvm.memcpy
define i32 @memcpy_addrspacecast() nounwind {
entry:
%alloca = alloca i8, i32 48
call void @llvm.memcpy.p0i8.p1i8.i32(i8* %alloca, i8 addrspace(1)* addrspacecast (i8 addrspace(2)* getelementptr inbounds ([60 x i8], [60 x i8] addrspace(2)* @const_array, i16 0, i16 4) to i8 addrspace(1)*), i32 48, i32 4, i1 false) nounwind
br label %loop.body
loop.body:
%i = phi i32 [ 0, %entry ], [ %i.inc, %loop.body ]
%sum = phi i32 [ 0, %entry ], [ %sum.inc, %loop.body]
[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
%ptr = getelementptr i8, i8* %alloca, i32 %i
%load = load i8, i8* %ptr
%ext = zext i8 %load to i32
%sum.inc = add i32 %sum, %ext
%i.inc = add i32 %i, 1
%cmp = icmp ne i32 %i, 48
br i1 %cmp, label %loop.body, label %end
end:
ret i32 %sum.inc
}