Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
; RUN: opt < %s -basicaa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
|
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
|
|
|
|
|
target triple = "arm-apple-ios"
|
|
|
|
|
|
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*, i32) nounwind readonly
|
|
|
|
|
declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>, i32) nounwind
|
|
|
|
|
|
|
|
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
|
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
|
|
|
|
|
|
|
|
|
|
declare void @a_readonly_func(i8 *) noinline nounwind readonly
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @test1(i8* %p, <8 x i16> %y) {
|
|
|
|
|
entry:
|
[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
|
|
|
%q = getelementptr i8, i8* %p, i64 16
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
%a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) nounwind
|
|
|
|
|
call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16)
|
|
|
|
|
%b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) nounwind
|
|
|
|
|
%c = add <8 x i16> %a, %b
|
|
|
|
|
ret <8 x i16> %c
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test1:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %p, i8* %q
|
2015-08-14 01:40:04 +08:00
|
|
|
; CHECK: Just Ref: Ptr: i8* %p <-> %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %q <-> %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
; CHECK: NoModRef: Ptr: i8* %p <-> call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %q <-> call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16)
|
2015-08-14 01:40:04 +08:00
|
|
|
; CHECK: Just Ref: Ptr: i8* %p <-> %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %q <-> %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4 <-> call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16)
|
|
|
|
|
; CHECK: NoModRef: %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4 <-> %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16) <-> %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16) <-> %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4 <-> %a = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4
|
|
|
|
|
; CHECK: NoModRef: %b = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %p, i32 16) #4 <-> call void @llvm.arm.neon.vst1.v8i16(i8* %q, <8 x i16> %y, i32 16)
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2(i8* %P, i8* %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2:
|
|
|
|
|
|
|
|
|
|
; CHECK: MayAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2a(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2a:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2b(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
[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
|
|
|
%R = getelementptr i8, i8* %P, i64 12
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2b:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %R
|
|
|
|
|
; CHECK: NoAlias: i8* %Q, i8* %R
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2c(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
[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
|
|
|
%R = getelementptr i8, i8* %P, i64 11
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2c:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %R
|
|
|
|
|
; CHECK: NoAlias: i8* %Q, i8* %R
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2d(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
[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
|
|
|
%R = getelementptr i8, i8* %P, i64 -12
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2d:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %R
|
|
|
|
|
; CHECK: NoAlias: i8* %Q, i8* %R
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test2e(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
[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
|
|
|
%R = getelementptr i8, i8* %P, i64 -11
|
Improve BasicAA CS-CS queries (redux)
This reverts, "r213024 - Revert r212572 "improve BasicAA CS-CS queries", it
causes PR20303." with a fix for the bug in pr20303. As it turned out, the
relevant code was both wrong and over-conservative (because, as with the code
it replaced, it would return the overall ModRef mask even if just Ref had been
implied by the argument aliasing results). Hopefully, this correctly fixes both
problems.
Thanks to Nick Lewycky for reducing the test case for pr20303 (which I've
cleaned up a little and added in DSE's test directory). The BasicAA test has
also been updated to check for this error.
Original commit message:
BasicAA contains knowledge of certain intrinsics, such as memcpy and memset,
and uses that information to form more-accurate answers to CallSite vs. Loc
ModRef queries. Unfortunately, it did not use this information when answering
CallSite vs. CallSite queries.
Generically, when an intrinsic takes one or more pointers and the intrinsic is
marked only to read/write from its arguments, the offset/size is unknown. As a
result, the generic code that answers CallSite vs. CallSite (and CallSite vs.
Loc) queries in AA uses UnknownSize when forming Locs from an intrinsic's
arguments. While BasicAA's CallSite vs. Loc override could use more-accurate
size information for some intrinsics, it did not do the same for CallSite vs.
CallSite queries.
This change refactors the intrinsic-specific logic in BasicAA into a generic AA
query function: getArgLocation, which is overridden by BasicAA to supply the
intrinsic-specific knowledge, and used by AA's generic implementation. This
allows the intrinsic-specific knowledge to be used by both CallSite vs. Loc and
CallSite vs. CallSite queries, and simplifies the BasicAA implementation.
Currently, only one function, Mac's memset_pattern16, is handled by BasicAA
(all the rest are intrinsics). As a side-effect of this refactoring, BasicAA's
getModRefBehavior override now also returns OnlyAccessesArgumentPointees for
this function (which is an improvement).
llvm-svn: 213219
2014-07-17 09:28:25 +08:00
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test2e:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %R
|
|
|
|
|
; CHECK: NoAlias: i8* %Q, i8* %R
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test3(i8* %P, i8* %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test3:
|
|
|
|
|
|
|
|
|
|
; CHECK: MayAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test3a(i8* noalias %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test3a:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test4(i8* %P, i8* noalias %Q) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test4:
|
|
|
|
|
|
|
|
|
|
; CHECK: NoAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: NoModRef: Ptr: i8* %Q <-> tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test5(i8* %P, i8* %Q, i8* %R) nounwind ssp {
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test5:
|
|
|
|
|
|
|
|
|
|
; CHECK: MayAlias: i8* %P, i8* %Q
|
|
|
|
|
; CHECK: MayAlias: i8* %P, i8* %R
|
|
|
|
|
; CHECK: MayAlias: i8* %Q, i8* %R
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
|
|
|
|
|
; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define void @test6(i8* %P) nounwind ssp {
|
|
|
|
|
call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
|
|
|
|
|
call void @a_readonly_func(i8* %P)
|
|
|
|
|
ret void
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: Function: test6:
|
|
|
|
|
|
|
|
|
|
; CHECK: Just Mod: Ptr: i8* %P <-> call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
|
|
|
|
|
; CHECK: Just Ref: Ptr: i8* %P <-> call void @a_readonly_func(i8* %P)
|
|
|
|
|
; CHECK: Just Mod: call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false) <-> call void @a_readonly_func(i8* %P)
|
|
|
|
|
; CHECK: Just Ref: call void @a_readonly_func(i8* %P) <-> call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
|
|
|
|
|
}
|
|
|
|
|
|
2015-08-14 01:40:04 +08:00
|
|
|
attributes #0 = { nounwind readonly argmemonly }
|
|
|
|
|
attributes #1 = { nounwind argmemonly }
|
2015-07-23 22:31:18 +08:00
|
|
|
attributes #2 = { noinline nounwind readonly }
|
|
|
|
|
attributes #3 = { nounwind ssp }
|
2015-08-14 01:40:04 +08:00
|
|
|
attributes #4 = { nounwind }
|
|
|
|
|
|