maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/StructurizeCFG/post-order-traversal-bug.ll

101 lines
4.1 KiB
LLVM
Raw Normal View History

StructurizeCFG: Use a reverse post-order traversal We were previously doing a post-order traversal and operating on the list in reverse, however this would occasionaly cause backedges for loops to be visited before some of the other blocks in the loop. We know use a reverse post-order traversal, which avoids this issue. The reverse post-order traversal is not completely ideal, so we need to manually fixup the list to ensure that inner loop backedges are visited before outer loop backedges. llvm-svn: 228186
2015-02-05 04:49:44 +08:00
; RUN: opt -S -structurizecfg %s -o - | FileCheck %s
; The structurize cfg pass used to do a post-order traversal to generate a list
; of ; basic blocks and then operate on the list in reverse. This led to bugs,
; because sometimes successors would be visited before their predecessors.
; The fix for this was to do a reverse post-order traversal which is what the
; algorithm requires.
; Function Attrs: nounwind
define void @test(float* nocapture %out, i32 %K1, float* nocapture readonly %nr) {
; CHECK: entry:
; CHECK: br label %for.body
entry:
br label %for.body
; CHECK: for.body:
; CHECK: br i1 %{{[0-9]+}}, label %lor.lhs.false, label %Flow
for.body: ; preds = %for.body.backedge, %entry
%indvars.iv = phi i64 [ %indvars.iv.be, %for.body.backedge ], [ 1, %entry ]
%best_val.027 = phi float [ %best_val.027.be, %for.body.backedge ], [ 5.000000e+01, %entry ]
%prev_start.026 = phi i32 [ %tmp26, %for.body.backedge ], [ 0, %entry ]
%best_count.025 = phi i32 [ %best_count.025.be, %for.body.backedge ], [ 0, %entry ]
%tmp0 = trunc i64 %indvars.iv to i32
%cmp1 = icmp eq i32 %tmp0, %K1
br i1 %cmp1, label %if.then, label %lor.lhs.false
; CHECK: lor.lhs.false:
; CHECK: br label %Flow
lor.lhs.false: ; preds = %for.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
2015-02-28 03:29:02 +08:00
%arrayidx = getelementptr inbounds float, float* %nr, i64 %indvars.iv
StructurizeCFG: Use a reverse post-order traversal We were previously doing a post-order traversal and operating on the list in reverse, however this would occasionaly cause backedges for loops to be visited before some of the other blocks in the loop. We know use a reverse post-order traversal, which avoids this issue. The reverse post-order traversal is not completely ideal, so we need to manually fixup the list to ensure that inner loop backedges are visited before outer loop backedges. llvm-svn: 228186
2015-02-05 04:49:44 +08:00
%tmp1 = load float* %arrayidx, align 4
%tmp2 = add nsw i64 %indvars.iv, -1
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%arrayidx2 = getelementptr inbounds float, float* %nr, i64 %tmp2
StructurizeCFG: Use a reverse post-order traversal We were previously doing a post-order traversal and operating on the list in reverse, however this would occasionaly cause backedges for loops to be visited before some of the other blocks in the loop. We know use a reverse post-order traversal, which avoids this issue. The reverse post-order traversal is not completely ideal, so we need to manually fixup the list to ensure that inner loop backedges are visited before outer loop backedges. llvm-svn: 228186
2015-02-05 04:49:44 +08:00
%tmp3 = load float* %arrayidx2, align 4
%cmp3 = fcmp une float %tmp1, %tmp3
br i1 %cmp3, label %if.then, label %for.body.1
; CHECK: Flow:
; CHECK: br i1 %{{[0-9]+}}, label %if.then, label %Flow1
; CHECK: if.then:
; CHECK: br label %Flow1
if.then: ; preds = %lor.lhs.false, %for.body
%sub4 = sub nsw i32 %tmp0, %prev_start.026
%tmp4 = add nsw i64 %indvars.iv, -1
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%arrayidx8 = getelementptr inbounds float, float* %nr, i64 %tmp4
StructurizeCFG: Use a reverse post-order traversal We were previously doing a post-order traversal and operating on the list in reverse, however this would occasionaly cause backedges for loops to be visited before some of the other blocks in the loop. We know use a reverse post-order traversal, which avoids this issue. The reverse post-order traversal is not completely ideal, so we need to manually fixup the list to ensure that inner loop backedges are visited before outer loop backedges. llvm-svn: 228186
2015-02-05 04:49:44 +08:00
%tmp5 = load float* %arrayidx8, align 4
br i1 %cmp1, label %for.end, label %for.body.1
; CHECK: for.end:
; CHECK: ret void
for.end: ; preds = %for.body.1, %if.then
%best_val.0.lcssa = phi float [ %best_val.233, %for.body.1 ], [ %tmp5, %if.then ]
store float %best_val.0.lcssa, float* %out, align 4
ret void
; CHECK: Flow1
; CHECK: br i1 %{{[0-9]}}, label %for.body.1, label %Flow2
; CHECK: for.body.1:
; CHECK: br i1 %{{[0-9]+}}, label %for.body.6, label %Flow3
for.body.1: ; preds = %if.then, %lor.lhs.false
%best_val.233 = phi float [ %tmp5, %if.then ], [ %best_val.027, %lor.lhs.false ]
%best_count.231 = phi i32 [ %sub4, %if.then ], [ %best_count.025, %lor.lhs.false ]
%indvars.iv.next.454 = add nsw i64 %indvars.iv, 5
%tmp22 = trunc i64 %indvars.iv.next.454 to i32
%cmp1.5 = icmp eq i32 %tmp22, %K1
br i1 %cmp1.5, label %for.end, label %for.body.6
; CHECK: Flow2:
; CHECK: br i1 %{{[0-9]+}}, label %for.end, label %for.body
; CHECK: for.body.6:
; CHECK: br i1 %cmp5.6, label %if.then6.6, label %for.body.backedge
for.body.6: ; preds = %for.body.1
%indvars.iv.next.559 = add nsw i64 %indvars.iv, 6
%tmp26 = trunc i64 %indvars.iv.next.559 to i32
%sub4.6 = sub nsw i32 %tmp26, %tmp22
%cmp5.6 = icmp slt i32 %best_count.231, %sub4.6
br i1 %cmp5.6, label %if.then6.6, label %for.body.backedge
; CHECK: if.then6.6
; CHECK: br label %for.body.backedge
if.then6.6: ; preds = %for.body.6
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%arrayidx8.6 = getelementptr inbounds float, float* %nr, i64 %indvars.iv.next.454
StructurizeCFG: Use a reverse post-order traversal We were previously doing a post-order traversal and operating on the list in reverse, however this would occasionaly cause backedges for loops to be visited before some of the other blocks in the loop. We know use a reverse post-order traversal, which avoids this issue. The reverse post-order traversal is not completely ideal, so we need to manually fixup the list to ensure that inner loop backedges are visited before outer loop backedges. llvm-svn: 228186
2015-02-05 04:49:44 +08:00
%tmp29 = load float* %arrayidx8.6, align 4
br label %for.body.backedge
; CHECK: Flow3:
; CHECK: br label %Flow2
; CHECK: for.body.backedge:
; CHECK: br label %Flow3
for.body.backedge: ; preds = %if.then6.6, %for.body.6
%best_val.027.be = phi float [ %tmp29, %if.then6.6 ], [ %best_val.233, %for.body.6 ]
%best_count.025.be = phi i32 [ %sub4.6, %if.then6.6 ], [ %best_count.231, %for.body.6 ]
%indvars.iv.be = add nsw i64 %indvars.iv, 7
br label %for.body
}