2012-09-28 05:21:18 +08:00
|
|
|
; Test lib call simplification of __memset_chk calls with various values
|
|
|
|
|
; for dstlen and len.
|
|
|
|
|
;
|
|
|
|
|
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
|
; rdar://7719085
|
|
|
|
|
|
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
|
|
|
|
|
|
|
|
|
|
%struct.T = type { [100 x i32], [100 x i32], [1024 x i8] }
|
|
|
|
|
@t = common global %struct.T zeroinitializer
|
|
|
|
|
|
|
|
|
|
; Check cases where dstlen >= len.
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
define i8* @test_simplify1() {
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @test_simplify1(
|
2012-09-28 05:21:18 +08:00
|
|
|
%dst = bitcast %struct.T* @t to i8*
|
|
|
|
|
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
|
|
|
|
|
%ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 1824)
|
|
|
|
|
ret i8* %ret
|
2012-09-28 05:21:18 +08:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
define i8* @test_simplify2() {
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @test_simplify2(
|
2012-09-28 05:21:18 +08:00
|
|
|
%dst = bitcast %struct.T* @t to i8*
|
|
|
|
|
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
|
|
|
|
|
%ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 3648)
|
|
|
|
|
ret i8* %ret
|
2012-09-28 05:21:18 +08:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
define i8* @test_simplify3() {
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @test_simplify3(
|
2012-09-28 05:21:18 +08:00
|
|
|
%dst = bitcast %struct.T* @t to i8*
|
|
|
|
|
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false)
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*)
|
|
|
|
|
%ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 -1)
|
|
|
|
|
ret i8* %ret
|
2012-09-28 05:21:18 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Check cases where dstlen < len.
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
define i8* @test_no_simplify1() {
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @test_no_simplify1(
|
2012-09-28 05:21:18 +08:00
|
|
|
%dst = bitcast %struct.T* @t to i8*
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
; CHECK-NEXT: %ret = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 400)
|
|
|
|
|
; CHECK-NEXT: ret i8* %ret
|
|
|
|
|
%ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 400)
|
|
|
|
|
ret i8* %ret
|
2012-09-28 05:21:18 +08:00
|
|
|
}
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
define i8* @test_no_simplify2() {
|
2013-07-14 09:42:54 +08:00
|
|
|
; CHECK-LABEL: @test_no_simplify2(
|
2012-09-28 05:21:18 +08:00
|
|
|
%dst = bitcast %struct.T* @t to i8*
|
|
|
|
|
|
[SimplifyLibCalls] Don't confuse strcpy_chk for stpcpy_chk.
This was introduced in a faulty refactoring (r225640, mea culpa):
the tests weren't testing the return values, so, for both
__strcpy_chk and __stpcpy_chk, we would return the end of the
buffer (matching stpcpy) instead of the beginning (for strcpy).
The root cause was the prefix "__" being ignored when comparing,
which made us always pick LibFunc::stpcpy_chk.
Pass the LibFunc::Func directly to avoid this kind of error.
Also, make the testcases as explicit as possible to prevent this.
The now-useful testcases expose another, entangled, stpcpy problem,
with the further simplification. This was introduced in a
refactoring (r225640) to match the original behavior.
However, this leads to problems when successive simplifications
generate several similar instructions, none of which are removed
by the custom replaceAllUsesWith.
For instance, InstCombine (the main user) doesn't erase the
instruction in its custom RAUW. When trying to simplify say
__stpcpy_chk:
- first, an stpcpy is created (fortified simplifier),
- second, a memcpy is created (normal simplifier), but the
stpcpy call isn't removed.
- third, InstCombine later revisits the instructions,
and simplifies the first stpcpy to a memcpy. We now have
two memcpys.
llvm-svn: 227250
2015-01-28 05:52:16 +08:00
|
|
|
; CHECK-NEXT: %ret = call i8* @__memset_chk(i8* bitcast (%struct.T* @t to i8*), i32 0, i64 1824, i64 0)
|
|
|
|
|
; CHECK-NEXT: ret i8* %ret
|
|
|
|
|
%ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 0)
|
|
|
|
|
ret i8* %ret
|
2012-09-28 05:21:18 +08:00
|
|
|
}
|
|
|
|
|
|
2015-10-02 06:43:53 +08:00
|
|
|
; Test that RAUW in SimplifyLibCalls for __memset_chk generates valid IR
|
|
|
|
|
define i32 @test_rauw(i8* %a, i8* %b, i8** %c) {
|
|
|
|
|
; CHECK-LABEL: test_rauw
|
|
|
|
|
entry:
|
|
|
|
|
%call49 = call i64 @strlen(i8* %a)
|
|
|
|
|
%add180 = add i64 %call49, 1
|
2017-03-22 04:08:59 +08:00
|
|
|
%yo107 = call i64 @llvm.objectsize.i64.p0i8(i8* %b, i1 false, i1 false)
|
2015-10-02 06:43:53 +08:00
|
|
|
%call50 = call i8* @__memmove_chk(i8* %b, i8* %a, i64 %add180, i64 %yo107)
|
|
|
|
|
; CHECK: %strlen = call i64 @strlen(i8* %b)
|
2016-02-12 06:30:41 +08:00
|
|
|
; CHECK-NEXT: %strchr2 = getelementptr i8, i8* %b, i64 %strlen
|
2015-10-02 06:43:53 +08:00
|
|
|
%call51i = call i8* @strrchr(i8* %b, i32 0)
|
|
|
|
|
%d = load i8*, i8** %c, align 8
|
|
|
|
|
%sub182 = ptrtoint i8* %d to i64
|
|
|
|
|
%sub183 = ptrtoint i8* %b to i64
|
|
|
|
|
%sub184 = sub i64 %sub182, %sub183
|
|
|
|
|
%add52.i.i = add nsw i64 %sub184, 1
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %strchr2
|
2015-10-02 06:43:53 +08:00
|
|
|
%call185 = call i8* @__memset_chk(i8* %call51i, i32 0, i64 %add52.i.i, i64 -1)
|
|
|
|
|
ret i32 4
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i8* @__memmove_chk(i8*, i8*, i64, i64)
|
|
|
|
|
declare i8* @strrchr(i8*, i32)
|
|
|
|
|
declare i64 @strlen(i8* nocapture)
|
2017-03-22 04:08:59 +08:00
|
|
|
declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1)
|
2015-10-02 06:43:53 +08:00
|
|
|
|
2012-09-28 05:21:18 +08:00
|
|
|
declare i8* @__memset_chk(i8*, i32, i64, i64)
|
2016-01-20 07:07:10 +08:00
|
|
|
|
|
|
|
|
; FIXME: memset(malloc(x), 0, x) -> calloc(1, x)
|
|
|
|
|
|
|
|
|
|
define float* @pr25892(i64 %size) #0 {
|
|
|
|
|
entry:
|
|
|
|
|
%call = tail call i8* @malloc(i64 %size) #1
|
|
|
|
|
%cmp = icmp eq i8* %call, null
|
|
|
|
|
br i1 %cmp, label %cleanup, label %if.end
|
|
|
|
|
if.end:
|
|
|
|
|
%bc = bitcast i8* %call to float*
|
2017-03-22 04:08:59 +08:00
|
|
|
%call2 = tail call i64 @llvm.objectsize.i64.p0i8(i8* nonnull %call, i1 false, i1 false)
|
2016-01-20 07:07:10 +08:00
|
|
|
%call3 = tail call i8* @__memset_chk(i8* nonnull %call, i32 0, i64 %size, i64 %call2) #1
|
|
|
|
|
br label %cleanup
|
|
|
|
|
cleanup:
|
|
|
|
|
%retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
|
|
|
|
|
ret float* %retval.0
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @pr25892(
|
|
|
|
|
; CHECK: entry:
|
|
|
|
|
; CHECK-NEXT: %call = tail call i8* @malloc(i64 %size)
|
|
|
|
|
; CHECK-NEXT: %cmp = icmp eq i8* %call, null
|
|
|
|
|
; CHECK-NEXT: br i1 %cmp, label %cleanup, label %if.end
|
|
|
|
|
; CHECK: if.end:
|
|
|
|
|
; CHECK-NEXT: %bc = bitcast i8* %call to float*
|
2017-03-22 04:08:59 +08:00
|
|
|
; CHECK-NEXT: %call2 = tail call i64 @llvm.objectsize.i64.p0i8(i8* nonnull %call, i1 false, i1 false)
|
2016-01-20 07:07:10 +08:00
|
|
|
; CHECK-NEXT: %call3 = tail call i8* @__memset_chk(i8* nonnull %call, i32 0, i64 %size, i64 %call2)
|
|
|
|
|
; CHECK-NEXT: br label %cleanup
|
|
|
|
|
; CHECK: cleanup:
|
|
|
|
|
; CHECK-NEXT: %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
|
|
|
|
|
; CHECK-NEXT: ret float* %retval.0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare noalias i8* @malloc(i64) #1
|
|
|
|
|
|
|
|
|
|
attributes #0 = { nounwind ssp uwtable }
|
|
|
|
|
attributes #1 = { nounwind }
|
|
|
|
|
attributes #2 = { nounwind readnone }
|
|
|
|
|
|