2018-08-28 09:18:29 +08:00
|
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc-unknown-linux-gnu -mcpu=g4 -disable-ppc-ilp-pref | FileCheck %s
|
2016-08-04 02:17:35 +08:00
|
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=g4 -disable-ppc-ilp-pref | FileCheck %s
|
2011-12-06 01:55:22 +08:00
|
|
|
|
|
|
|
|
; ModuleID = 'tsc.c'
|
|
|
|
|
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-v128:128:128-n32:64"
|
|
|
|
|
target triple = "powerpc64-unknown-linux-gnu"
|
|
|
|
|
|
|
|
|
|
@a = common global [32000 x float] zeroinitializer, align 16
|
|
|
|
|
@b = common global [32000 x float] zeroinitializer, align 16
|
|
|
|
|
@c = common global [32000 x float] zeroinitializer, align 16
|
|
|
|
|
@d = common global [32000 x float] zeroinitializer, align 16
|
|
|
|
|
@e = common global [32000 x float] zeroinitializer, align 16
|
|
|
|
|
@aa = common global [256 x [256 x float]] zeroinitializer, align 16
|
|
|
|
|
@bb = common global [256 x [256 x float]] zeroinitializer, align 16
|
|
|
|
|
@cc = common global [256 x [256 x float]] zeroinitializer, align 16
|
|
|
|
|
|
|
|
|
|
@.str11 = private unnamed_addr constant [6 x i8] c"s122 \00", align 1
|
|
|
|
|
@.str152 = private unnamed_addr constant [14 x i8] c"S122\09 %.2f \09\09\00", align 1
|
|
|
|
|
|
|
|
|
|
declare i32 @printf(i8* nocapture, ...) nounwind
|
|
|
|
|
declare i32 @init(i8* %name) nounwind
|
|
|
|
|
declare i64 @clock() nounwind
|
|
|
|
|
declare i32 @dummy(float*, float*, float*, float*, float*, [256 x float]*, [256 x float]*, [256 x float]*, float)
|
|
|
|
|
declare void @check(i32 %name) nounwind
|
|
|
|
|
|
|
|
|
|
; CHECK: mfcr
|
|
|
|
|
; CHECK: mtcr
|
|
|
|
|
|
|
|
|
|
define i32 @s122(i32 %n1, i32 %n3) nounwind {
|
|
|
|
|
entry:
|
2015-03-14 02:20:45 +08:00
|
|
|
%call = tail call i32 @init(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str11, i64 0, i64 0))
|
2011-12-06 01:55:22 +08:00
|
|
|
%call1 = tail call i64 @clock() nounwind
|
|
|
|
|
%sub = add nsw i32 %n1, -1
|
|
|
|
|
%cmp316 = icmp slt i32 %sub, 32000
|
|
|
|
|
br i1 %cmp316, label %entry.split.us, label %for.end.7
|
|
|
|
|
|
|
|
|
|
entry.split.us: ; preds = %entry
|
|
|
|
|
%0 = sext i32 %sub to i64
|
|
|
|
|
%1 = sext i32 %n3 to i64
|
|
|
|
|
br label %for.body4.lr.ph.us
|
|
|
|
|
|
|
|
|
|
for.body4.us: ; preds = %for.body4.lr.ph.us, %for.body4.us
|
|
|
|
|
%indvars.iv20 = phi i64 [ 0, %for.body4.lr.ph.us ], [ %indvars.iv.next21, %for.body4.us ]
|
|
|
|
|
%indvars.iv = phi i64 [ %0, %for.body4.lr.ph.us ], [ %indvars.iv.next, %for.body4.us ]
|
|
|
|
|
%indvars.iv.next21 = add i64 %indvars.iv20, 1
|
|
|
|
|
%sub5.us = sub i64 31999, %indvars.iv20
|
|
|
|
|
%sext = shl i64 %sub5.us, 32
|
|
|
|
|
%idxprom.us = ashr exact i64 %sext, 32
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx.us = getelementptr inbounds [32000 x float], [32000 x float]* @b, i64 0, i64 %idxprom.us
|
2015-02-28 05:17:42 +08:00
|
|
|
%2 = load float, float* %arrayidx.us, align 4
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx7.us = getelementptr inbounds [32000 x float], [32000 x float]* @a, i64 0, i64 %indvars.iv
|
2015-02-28 05:17:42 +08:00
|
|
|
%3 = load float, float* %arrayidx7.us, align 4
|
2018-07-20 03:34:18 +08:00
|
|
|
%add8.us = tail call float asm "fadd $0, $1, $2", "=f,f,f,~{cr2}"(float %3, float %2)
|
2013-05-01 01:52:57 +08:00
|
|
|
store float %add8.us, float* %arrayidx7.us, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%indvars.iv.next = add i64 %indvars.iv, %1
|
|
|
|
|
%4 = trunc i64 %indvars.iv.next to i32
|
|
|
|
|
%cmp3.us = icmp slt i32 %4, 32000
|
|
|
|
|
br i1 %cmp3.us, label %for.body4.us, label %for.body4.lr.ph.us.1
|
|
|
|
|
|
|
|
|
|
for.body4.lr.ph.us: ; preds = %entry.split.us, %for.end.us.4
|
|
|
|
|
%nl.019.us = phi i32 [ 0, %entry.split.us ], [ %inc.us.4, %for.end.us.4 ]
|
|
|
|
|
br label %for.body4.us
|
|
|
|
|
|
|
|
|
|
for.end12: ; preds = %for.end.7, %for.end.us.4
|
|
|
|
|
%call13 = tail call i64 @clock() nounwind
|
|
|
|
|
%sub14 = sub nsw i64 %call13, %call1
|
|
|
|
|
%conv = sitofp i64 %sub14 to double
|
|
|
|
|
%div = fdiv double %conv, 1.000000e+06
|
[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction
See r230786 and r230794 for similar changes to gep and load
respectively.
Call is a bit different because it often doesn't have a single explicit
type - usually the type is deduced from the arguments, and just the
return type is explicit. In those cases there's no need to change the
IR.
When that's not the case, the IR usually contains the pointer type of
the first operand - but since typed pointers are going away, that
representation is insufficient so I'm just stripping the "pointerness"
of the explicit type away.
This does make the IR a bit weird - it /sort of/ reads like the type of
the first operand: "call void () %x(" but %x is actually of type "void
()*" and will eventually be just of type "ptr". But this seems not too
bad and I don't think it would benefit from repeating the type
("void (), void () * %x(" and then eventually "void (), ptr %x(") as has
been done with gep and load.
This also has a side benefit: since the explicit type is no longer a
pointer, there's no ambiguity between an explicit type and a function
that returns a function pointer. Previously this case needed an explicit
type (eg: a function returning a void() function was written as
"call void () () * @x(" rather than "call void () * @x(" because of the
ambiguity between a function returning a pointer to a void() function
and a function returning void).
No ambiguity means even function pointer return types can just be
written alone, without writing the whole function's type.
This leaves /only/ the varargs case where the explicit type is required.
Given the special type syntax in call instructions, the regex-fu used
for migration was a bit more involved in its own unique way (as every
one of these is) so here it is. Use it in conjunction with the apply.sh
script and associated find/xargs commands I've provided in rr230786 to
migrate your out of tree tests. Do let me know if any of this doesn't
cover your cases & we can iterate on a more general script/regexes to
help others with out of tree tests.
About 9 test cases couldn't be automatically migrated - half of those
were functions returning function pointers, where I just had to manually
delete the function argument types now that we didn't need an explicit
function type there. The other half were typedefs of function types used
in calls - just had to manually drop the * from those.
import fileinput
import sys
import re
pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)')
addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$")
func_end = re.compile("(?:void.*|\)\s*)\*$")
def conv(match, line):
if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)):
return line
return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():]
for line in sys.stdin:
sys.stdout.write(conv(re.search(pat, line), line))
llvm-svn: 235145
2015-04-17 07:24:18 +08:00
|
|
|
%call15 = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str152, i64 0, i64 0), double %div) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
tail call void @check(i32 1)
|
|
|
|
|
ret i32 0
|
|
|
|
|
|
|
|
|
|
for.body4.lr.ph.us.1: ; preds = %for.body4.us
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10.us = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
br label %for.body4.us.1
|
|
|
|
|
|
|
|
|
|
for.body4.us.1: ; preds = %for.body4.us.1, %for.body4.lr.ph.us.1
|
|
|
|
|
%indvars.iv20.1 = phi i64 [ 0, %for.body4.lr.ph.us.1 ], [ %indvars.iv.next21.1, %for.body4.us.1 ]
|
|
|
|
|
%indvars.iv.1 = phi i64 [ %0, %for.body4.lr.ph.us.1 ], [ %indvars.iv.next.1, %for.body4.us.1 ]
|
|
|
|
|
%indvars.iv.next21.1 = add i64 %indvars.iv20.1, 1
|
|
|
|
|
%sub5.us.1 = sub i64 31999, %indvars.iv20.1
|
|
|
|
|
%sext23 = shl i64 %sub5.us.1, 32
|
|
|
|
|
%idxprom.us.1 = ashr exact i64 %sext23, 32
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx.us.1 = getelementptr inbounds [32000 x float], [32000 x float]* @b, i64 0, i64 %idxprom.us.1
|
2015-02-28 05:17:42 +08:00
|
|
|
%5 = load float, float* %arrayidx.us.1, align 4
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx7.us.1 = getelementptr inbounds [32000 x float], [32000 x float]* @a, i64 0, i64 %indvars.iv.1
|
2015-02-28 05:17:42 +08:00
|
|
|
%6 = load float, float* %arrayidx7.us.1, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%add8.us.1 = fadd float %6, %5
|
2013-05-01 01:52:57 +08:00
|
|
|
store float %add8.us.1, float* %arrayidx7.us.1, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%indvars.iv.next.1 = add i64 %indvars.iv.1, %1
|
|
|
|
|
%7 = trunc i64 %indvars.iv.next.1 to i32
|
|
|
|
|
%cmp3.us.1 = icmp slt i32 %7, 32000
|
|
|
|
|
br i1 %cmp3.us.1, label %for.body4.us.1, label %for.body4.lr.ph.us.2
|
|
|
|
|
|
|
|
|
|
for.body4.lr.ph.us.2: ; preds = %for.body4.us.1
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10.us.1 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
br label %for.body4.us.2
|
|
|
|
|
|
|
|
|
|
for.body4.us.2: ; preds = %for.body4.us.2, %for.body4.lr.ph.us.2
|
|
|
|
|
%indvars.iv20.2 = phi i64 [ 0, %for.body4.lr.ph.us.2 ], [ %indvars.iv.next21.2, %for.body4.us.2 ]
|
|
|
|
|
%indvars.iv.2 = phi i64 [ %0, %for.body4.lr.ph.us.2 ], [ %indvars.iv.next.2, %for.body4.us.2 ]
|
|
|
|
|
%indvars.iv.next21.2 = add i64 %indvars.iv20.2, 1
|
|
|
|
|
%sub5.us.2 = sub i64 31999, %indvars.iv20.2
|
|
|
|
|
%sext24 = shl i64 %sub5.us.2, 32
|
|
|
|
|
%idxprom.us.2 = ashr exact i64 %sext24, 32
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx.us.2 = getelementptr inbounds [32000 x float], [32000 x float]* @b, i64 0, i64 %idxprom.us.2
|
2015-02-28 05:17:42 +08:00
|
|
|
%8 = load float, float* %arrayidx.us.2, align 4
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx7.us.2 = getelementptr inbounds [32000 x float], [32000 x float]* @a, i64 0, i64 %indvars.iv.2
|
2015-02-28 05:17:42 +08:00
|
|
|
%9 = load float, float* %arrayidx7.us.2, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%add8.us.2 = fadd float %9, %8
|
2013-05-01 01:52:57 +08:00
|
|
|
store float %add8.us.2, float* %arrayidx7.us.2, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%indvars.iv.next.2 = add i64 %indvars.iv.2, %1
|
|
|
|
|
%10 = trunc i64 %indvars.iv.next.2 to i32
|
|
|
|
|
%cmp3.us.2 = icmp slt i32 %10, 32000
|
|
|
|
|
br i1 %cmp3.us.2, label %for.body4.us.2, label %for.body4.lr.ph.us.3
|
|
|
|
|
|
|
|
|
|
for.body4.lr.ph.us.3: ; preds = %for.body4.us.2
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10.us.2 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
br label %for.body4.us.3
|
|
|
|
|
|
|
|
|
|
for.body4.us.3: ; preds = %for.body4.us.3, %for.body4.lr.ph.us.3
|
|
|
|
|
%indvars.iv20.3 = phi i64 [ 0, %for.body4.lr.ph.us.3 ], [ %indvars.iv.next21.3, %for.body4.us.3 ]
|
|
|
|
|
%indvars.iv.3 = phi i64 [ %0, %for.body4.lr.ph.us.3 ], [ %indvars.iv.next.3, %for.body4.us.3 ]
|
|
|
|
|
%indvars.iv.next21.3 = add i64 %indvars.iv20.3, 1
|
|
|
|
|
%sub5.us.3 = sub i64 31999, %indvars.iv20.3
|
|
|
|
|
%sext25 = shl i64 %sub5.us.3, 32
|
|
|
|
|
%idxprom.us.3 = ashr exact i64 %sext25, 32
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx.us.3 = getelementptr inbounds [32000 x float], [32000 x float]* @b, i64 0, i64 %idxprom.us.3
|
2015-02-28 05:17:42 +08:00
|
|
|
%11 = load float, float* %arrayidx.us.3, align 4
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx7.us.3 = getelementptr inbounds [32000 x float], [32000 x float]* @a, i64 0, i64 %indvars.iv.3
|
2015-02-28 05:17:42 +08:00
|
|
|
%12 = load float, float* %arrayidx7.us.3, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%add8.us.3 = fadd float %12, %11
|
2013-05-01 01:52:57 +08:00
|
|
|
store float %add8.us.3, float* %arrayidx7.us.3, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%indvars.iv.next.3 = add i64 %indvars.iv.3, %1
|
|
|
|
|
%13 = trunc i64 %indvars.iv.next.3 to i32
|
|
|
|
|
%cmp3.us.3 = icmp slt i32 %13, 32000
|
|
|
|
|
br i1 %cmp3.us.3, label %for.body4.us.3, label %for.body4.lr.ph.us.4
|
|
|
|
|
|
|
|
|
|
for.body4.lr.ph.us.4: ; preds = %for.body4.us.3
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10.us.3 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
br label %for.body4.us.4
|
|
|
|
|
|
|
|
|
|
for.body4.us.4: ; preds = %for.body4.us.4, %for.body4.lr.ph.us.4
|
|
|
|
|
%indvars.iv20.4 = phi i64 [ 0, %for.body4.lr.ph.us.4 ], [ %indvars.iv.next21.4, %for.body4.us.4 ]
|
|
|
|
|
%indvars.iv.4 = phi i64 [ %0, %for.body4.lr.ph.us.4 ], [ %indvars.iv.next.4, %for.body4.us.4 ]
|
|
|
|
|
%indvars.iv.next21.4 = add i64 %indvars.iv20.4, 1
|
|
|
|
|
%sub5.us.4 = sub i64 31999, %indvars.iv20.4
|
|
|
|
|
%sext26 = shl i64 %sub5.us.4, 32
|
|
|
|
|
%idxprom.us.4 = ashr exact i64 %sext26, 32
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx.us.4 = getelementptr inbounds [32000 x float], [32000 x float]* @b, i64 0, i64 %idxprom.us.4
|
2015-02-28 05:17:42 +08:00
|
|
|
%14 = load float, float* %arrayidx.us.4, align 4
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx7.us.4 = getelementptr inbounds [32000 x float], [32000 x float]* @a, i64 0, i64 %indvars.iv.4
|
2015-02-28 05:17:42 +08:00
|
|
|
%15 = load float, float* %arrayidx7.us.4, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%add8.us.4 = fadd float %15, %14
|
2013-05-01 01:52:57 +08:00
|
|
|
store float %add8.us.4, float* %arrayidx7.us.4, align 4
|
2011-12-06 01:55:22 +08:00
|
|
|
%indvars.iv.next.4 = add i64 %indvars.iv.4, %1
|
|
|
|
|
%16 = trunc i64 %indvars.iv.next.4 to i32
|
|
|
|
|
%cmp3.us.4 = icmp slt i32 %16, 32000
|
|
|
|
|
br i1 %cmp3.us.4, label %for.body4.us.4, label %for.end.us.4
|
|
|
|
|
|
|
|
|
|
for.end.us.4: ; preds = %for.body4.us.4
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10.us.4 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
%inc.us.4 = add nsw i32 %nl.019.us, 5
|
|
|
|
|
%exitcond.4 = icmp eq i32 %inc.us.4, 200000
|
|
|
|
|
br i1 %exitcond.4, label %for.end12, label %for.body4.lr.ph.us
|
|
|
|
|
|
|
|
|
|
for.end.7: ; preds = %entry, %for.end.7
|
|
|
|
|
%nl.019 = phi i32 [ %inc.7, %for.end.7 ], [ 0, %entry ]
|
2015-03-14 02:20:45 +08:00
|
|
|
%call10 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.1 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.2 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.3 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.4 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.5 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.6 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
|
|
|
|
%call10.7 = tail call i32 @dummy(float* getelementptr inbounds ([32000 x float], [32000 x float]* @a, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @b, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @c, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @d, i64 0, i64 0), float* getelementptr inbounds ([32000 x float], [32000 x float]* @e, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @aa, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @bb, i64 0, i64 0), [256 x float]* getelementptr inbounds ([256 x [256 x float]], [256 x [256 x float]]* @cc, i64 0, i64 0), float 0.000000e+00) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
%inc.7 = add nsw i32 %nl.019, 8
|
|
|
|
|
%exitcond.7 = icmp eq i32 %inc.7, 200000
|
|
|
|
|
br i1 %exitcond.7, label %for.end12, label %for.end.7
|
|
|
|
|
}
|
|
|
|
|
|
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.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
|
2011-12-06 01:55:22 +08:00
|
|
|
|
|
|
|
|
declare i32 @puts(i8* nocapture) nounwind
|
|
|
|
|
|
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
|
|
|
!3 = !{!"branch_weights", i32 64, i32 4}
|