maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AArch64/and-mask-removal.ll

270 lines
5.4 KiB
LLVM
Raw Normal View History

Remove spurious mask operations from AArch64 add->compares on 16 and 8 bit values This patch checks for DAG patterns that are an add or a sub followed by a compare on 16 and 8 bit inputs. Since AArch64 does not support those types natively they are legalized into 32 bit values, which means that mask operations are inserted into the DAG to emulate overflow behaviour. In many cases those masks do not change the result of the processing and just introduce a dependent operation, often in the middle of a hot loop. This patch detects the relevent DAG patterns and then tests to see if the transforms are equivalent with and without the mask, removing the mask if possible. The exact mechanism of this patch was discusses in http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-July/074444.html There is a reasonably good chance there are missed oppurtunities due to similiar (but not identical) DAG patterns that could be funneled into this test, adding them should be simple if we see test cases. Tests included. rdar://13754426 llvm-svn: 216776
2014-08-30 05:00:22 +08:00
; RUN: llc -O0 -fast-isel=false -mtriple=arm64-apple-darwin < %s | FileCheck %s
@board = common global [400 x i8] zeroinitializer, align 1
@next_string = common global i32 0, align 4
@string_number = common global [400 x i32] zeroinitializer, align 4
; Function Attrs: nounwind ssp
define void @new_position(i32 %pos) {
entry:
%idxprom = sext i32 %pos to i64
[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 [400 x i8], [400 x i8]* @board, i64 0, i64 %idxprom
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp = load i8, i8* %arrayidx, align 1
Remove spurious mask operations from AArch64 add->compares on 16 and 8 bit values This patch checks for DAG patterns that are an add or a sub followed by a compare on 16 and 8 bit inputs. Since AArch64 does not support those types natively they are legalized into 32 bit values, which means that mask operations are inserted into the DAG to emulate overflow behaviour. In many cases those masks do not change the result of the processing and just introduce a dependent operation, often in the middle of a hot loop. This patch detects the relevent DAG patterns and then tests to see if the transforms are equivalent with and without the mask, removing the mask if possible. The exact mechanism of this patch was discusses in http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-July/074444.html There is a reasonably good chance there are missed oppurtunities due to similiar (but not identical) DAG patterns that could be funneled into this test, adding them should be simple if we see test cases. Tests included. rdar://13754426 llvm-svn: 216776
2014-08-30 05:00:22 +08:00
%.off = add i8 %tmp, -1
%switch = icmp ult i8 %.off, 2
br i1 %switch, label %if.then, label %if.end
if.then: ; preds = %entry
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp1 = load i32, i32* @next_string, align 4
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%arrayidx8 = getelementptr inbounds [400 x i32], [400 x i32]* @string_number, i64 0, i64 %idxprom
Remove spurious mask operations from AArch64 add->compares on 16 and 8 bit values This patch checks for DAG patterns that are an add or a sub followed by a compare on 16 and 8 bit inputs. Since AArch64 does not support those types natively they are legalized into 32 bit values, which means that mask operations are inserted into the DAG to emulate overflow behaviour. In many cases those masks do not change the result of the processing and just introduce a dependent operation, often in the middle of a hot loop. This patch detects the relevent DAG patterns and then tests to see if the transforms are equivalent with and without the mask, removing the mask if possible. The exact mechanism of this patch was discusses in http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-July/074444.html There is a reasonably good chance there are missed oppurtunities due to similiar (but not identical) DAG patterns that could be funneled into this test, adding them should be simple if we see test cases. Tests included. rdar://13754426 llvm-svn: 216776
2014-08-30 05:00:22 +08:00
store i32 %tmp1, i32* %arrayidx8, align 4
br label %if.end
if.end: ; preds = %if.then, %entry
ret void
; CHECK-LABEL: new_position
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_0(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 74
%1 = icmp ult i8 %0, -20
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_0
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test8_1(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 246
%1 = icmp uge i8 %0, 90
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_1
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_2(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 227
%1 = icmp ne i8 %0, 179
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_2
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_3(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 201
%1 = icmp eq i8 %0, 154
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_3
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_4(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, -79
%1 = icmp ne i8 %0, -40
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_4
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_5(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 133
%1 = icmp uge i8 %0, -105
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_5
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test8_6(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, -58
%1 = icmp uge i8 %0, 155
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_6
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test8_7(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 225
%1 = icmp ult i8 %0, 124
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_7
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test8_8(i8 zeroext %x) align 2 {
entry:
%0 = add i8 %x, 190
%1 = icmp uge i8 %0, 1
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test8_8
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test16_0(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, -46989
%1 = icmp ne i16 %0, -41903
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_0
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test16_2(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, 16882
%1 = icmp ule i16 %0, -24837
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_2
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test16_3(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, 29283
%1 = icmp ne i16 %0, 16947
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_3
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test16_4(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, -35551
%1 = icmp uge i16 %0, 15677
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_4
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test16_5(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, -25214
%1 = icmp ne i16 %0, -1932
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_5
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test16_6(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, -32194
%1 = icmp uge i16 %0, -41215
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_6
; CHECK-NOT: and
; CHECK: ret
}
define zeroext i1 @test16_7(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, 9272
%1 = icmp uge i16 %0, -42916
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_7
; CHECK: and
; CHECK: ret
}
define zeroext i1 @test16_8(i16 zeroext %x) align 2 {
entry:
%0 = add i16 %x, -63749
%1 = icmp ne i16 %0, 6706
br i1 %1, label %ret_true, label %ret_false
ret_false:
ret i1 false
ret_true:
ret i1 true
; CHECK-LABEL: test16_8
; CHECK-NOT: and
; CHECK: ret
}