2013-08-02 05:42:05 +08:00
|
|
|
; RUN: llc < %s -relocation-model=static -mcpu=yonah | FileCheck %s
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
|
2015-02-18 04:08:21 +08:00
|
|
|
; The double argument is at 4(esp) which is 16-byte aligned, but we
|
|
|
|
|
; are required to read in extra bytes of memory in order to fold the
|
|
|
|
|
; load. Bad Things may happen when reading/processing undefined bytes,
|
|
|
|
|
; so don't fold the load.
|
|
|
|
|
; PR22371 / http://reviews.llvm.org/D7474
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
|
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
|
|
|
|
|
target triple = "i686-apple-darwin8"
|
|
|
|
|
@G = external global double
|
|
|
|
|
|
2011-02-14 06:25:43 +08:00
|
|
|
define void @test({ double, double }* byval %z, double* %P) nounwind {
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
entry:
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp3 = load double, double* @G, align 16 ; <double> [#uses=1]
|
2012-08-04 07:29:17 +08:00
|
|
|
%tmp4 = tail call double @fabs( double %tmp3 ) readnone ; <double> [#uses=1]
|
2011-11-27 14:54:59 +08:00
|
|
|
store volatile double %tmp4, double* %P
|
[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
|
|
|
%tmp = getelementptr { double, double }, { double, double }* %z, i32 0, i32 0 ; <double*> [#uses=1]
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp1 = load volatile double, double* %tmp, align 8 ; <double> [#uses=1]
|
2012-08-04 07:29:17 +08:00
|
|
|
%tmp2 = tail call double @fabs( double %tmp1 ) readnone ; <double> [#uses=1]
|
2009-06-05 06:49:04 +08:00
|
|
|
%tmp6 = fadd double %tmp4, %tmp2 ; <double> [#uses=1]
|
2011-11-27 14:54:59 +08:00
|
|
|
store volatile double %tmp6, double* %P, align 8
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
ret void
|
2015-02-18 04:08:21 +08:00
|
|
|
|
|
|
|
|
; CHECK-LABEL: test:
|
|
|
|
|
; CHECK: movsd {{.*}}G, %xmm{{.*}}
|
|
|
|
|
; CHECK: andpd %xmm{{.*}}, %xmm{{.*}}
|
|
|
|
|
; CHECK: movsd 4(%esp), %xmm{{.*}}
|
|
|
|
|
; CHECK: andpd %xmm{{.*}}, %xmm{{.*}}
|
|
|
|
|
|
|
|
|
|
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
}
|
|
|
|
|
|
2011-02-14 06:25:43 +08:00
|
|
|
define void @test2() alignstack(16) nounwind {
|
2010-02-20 02:17:13 +08:00
|
|
|
entry:
|
2015-02-18 04:08:21 +08:00
|
|
|
; CHECK-LABEL: test2:
|
|
|
|
|
; CHECK: andl{{.*}}$-16, %esp
|
2010-02-20 02:17:13 +08:00
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Use a call to force a spill.
|
2011-02-14 06:25:43 +08:00
|
|
|
define <2 x double> @test3(<2 x double> %x, <2 x double> %y) alignstack(32) nounwind {
|
2010-02-20 02:17:13 +08:00
|
|
|
entry:
|
2015-02-18 04:08:21 +08:00
|
|
|
; CHECK-LABEL: test3:
|
|
|
|
|
; CHECK: andl{{.*}}$-32, %esp
|
2010-02-20 02:17:13 +08:00
|
|
|
call void @test2()
|
2010-05-04 06:36:46 +08:00
|
|
|
%A = fmul <2 x double> %x, %y
|
2010-02-20 02:17:13 +08:00
|
|
|
ret <2 x double> %A
|
|
|
|
|
}
|
|
|
|
|
|
Infer alignment of loads and increase their alignment when we can tell they are
from the stack. This allows us to compile stack-align.ll to:
_test:
movsd LCPI1_0, %xmm0
movapd %xmm0, %xmm1
*** andpd 4(%esp), %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
instead of:
_test:
movsd LCPI1_0, %xmm0
** movsd 4(%esp), %xmm1
** andpd %xmm0, %xmm1
andpd _G, %xmm0
addsd %xmm1, %xmm0
movl 20(%esp), %eax
movsd %xmm0, (%eax)
ret
llvm-svn: 46401
2008-01-27 03:45:50 +08:00
|
|
|
declare double @fabs(double)
|
2010-02-20 02:17:13 +08:00
|
|
|
|
2011-02-14 06:25:43 +08:00
|
|
|
; The pointer is already known aligned, so and x,-16 is eliminable.
|
|
|
|
|
define i32 @test4() nounwind {
|
|
|
|
|
entry:
|
|
|
|
|
%buffer = alloca [2048 x i8], align 16
|
|
|
|
|
%0 = ptrtoint [2048 x i8]* %buffer to i32
|
|
|
|
|
%and = and i32 %0, -16
|
|
|
|
|
ret i32 %and
|
2013-07-14 04:38:47 +08:00
|
|
|
; CHECK-LABEL: test4:
|
2011-02-14 06:25:43 +08:00
|
|
|
; CHECK-NOT: and
|
|
|
|
|
; CHECK: ret
|
|
|
|
|
}
|
2016-04-10 07:34:42 +08:00
|
|
|
|
|
|
|
|
%struct.sixteen = type { [16 x i8] }
|
|
|
|
|
|
|
|
|
|
; Accessing stack parameters shouldn't assume stack alignment. Here we should
|
|
|
|
|
; emit two 8-byte loads, followed by two 8-byte stores.
|
|
|
|
|
define x86_stdcallcc void @test5(%struct.sixteen* byval nocapture readonly align 4 %s) #0 {
|
|
|
|
|
%d.sroa.0 = alloca [16 x i8], align 1
|
|
|
|
|
%1 = getelementptr inbounds [16 x i8], [16 x i8]* %d.sroa.0, i32 0, i32 0
|
2017-04-11 04:18:21 +08:00
|
|
|
call void @llvm.lifetime.start.p0i8(i64 16, i8* %1)
|
2016-04-10 07:34:42 +08:00
|
|
|
%2 = getelementptr inbounds %struct.sixteen, %struct.sixteen* %s, i32 0, i32 0, i32 0
|
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
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %2, i32 16, i1 true)
|
2017-04-11 04:18:21 +08:00
|
|
|
call void @llvm.lifetime.end.p0i8(i64 16, i8* %1)
|
2016-04-10 07:34:42 +08:00
|
|
|
ret void
|
|
|
|
|
; CHECK-LABEL: test5:
|
|
|
|
|
; CHECK: and
|
|
|
|
|
; CHECK: movsd
|
|
|
|
|
; CHECK-NEXT: movsd
|
|
|
|
|
; CHECK-NEXT: movsd
|
|
|
|
|
; CHECK-NEXT: movsd
|
|
|
|
|
}
|
|
|
|
|
|
2017-04-11 04:18:21 +08:00
|
|
|
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) argmemonly nounwind
|
2016-04-10 07:34:42 +08:00
|
|
|
|
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
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) argmemonly nounwind
|
2016-04-10 07:34:42 +08:00
|
|
|
|
2017-04-11 04:18:21 +08:00
|
|
|
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) argmemonly nounwind
|
2016-04-10 07:34:42 +08:00
|
|
|
|
|
|
|
|
attributes #0 = { nounwind alignstack=16 "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" }
|