2010-08-11 08:12:36 +08:00
|
|
|
; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s
|
2009-08-20 07:19:36 +08:00
|
|
|
|
|
|
|
|
; ScalarEvolution should be able to understand the loop and eliminate the casts.
|
2009-05-01 04:47:05 +08:00
|
|
|
|
2015-03-05 02:43:29 +08:00
|
|
|
; CHECK: {%d,+,4}
|
2010-08-11 08:12:36 +08:00
|
|
|
|
2009-05-01 04:47:05 +08:00
|
|
|
define void @foo(i32* nocapture %d, i32 %n) nounwind {
|
|
|
|
|
entry:
|
|
|
|
|
%0 = icmp sgt i32 %n, 0 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %0, label %bb.nph, label %return
|
|
|
|
|
|
|
|
|
|
bb.nph: ; preds = %entry
|
|
|
|
|
br label %bb
|
|
|
|
|
|
|
|
|
|
bb: ; preds = %bb1, %bb.nph
|
|
|
|
|
%i.02 = phi i32 [ %5, %bb1 ], [ 0, %bb.nph ] ; <i32> [#uses=2]
|
|
|
|
|
%p.01 = phi i8 [ %4, %bb1 ], [ -1, %bb.nph ] ; <i8> [#uses=2]
|
|
|
|
|
%1 = sext i8 %p.01 to i32 ; <i32> [#uses=1]
|
|
|
|
|
%2 = sext i32 %i.02 to i64 ; <i64> [#uses=1]
|
[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
|
|
|
%3 = getelementptr i32, i32* %d, i64 %2 ; <i32*> [#uses=1]
|
2009-05-01 04:47:05 +08:00
|
|
|
store i32 %1, i32* %3, align 4
|
|
|
|
|
%4 = add i8 %p.01, 1 ; <i8> [#uses=1]
|
|
|
|
|
%5 = add i32 %i.02, 1 ; <i32> [#uses=2]
|
|
|
|
|
br label %bb1
|
|
|
|
|
|
|
|
|
|
bb1: ; preds = %bb
|
|
|
|
|
%6 = icmp slt i32 %5, %n ; <i1> [#uses=1]
|
|
|
|
|
br i1 %6, label %bb, label %bb1.return_crit_edge
|
|
|
|
|
|
|
|
|
|
bb1.return_crit_edge: ; preds = %bb1
|
|
|
|
|
br label %return
|
|
|
|
|
|
|
|
|
|
return: ; preds = %bb1.return_crit_edge, %entry
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2010-08-11 08:12:36 +08:00
|
|
|
|
|
|
|
|
; ScalarEvolution should be able to find the maximum tripcount
|
|
|
|
|
; of this multiple-exit loop, and if it doesn't know the exact
|
|
|
|
|
; count, it should say so.
|
|
|
|
|
|
|
|
|
|
; PR7845
|
2015-03-05 02:43:29 +08:00
|
|
|
; CHECK: Loop %for.cond: <multiple exits> Unpredictable backedge-taken count.
|
2010-08-11 08:12:36 +08:00
|
|
|
; CHECK: Loop %for.cond: max backedge-taken count is 5
|
|
|
|
|
|
|
|
|
|
@.str = private constant [4 x i8] c"%d\0A\00" ; <[4 x i8]*> [#uses=2]
|
|
|
|
|
|
|
|
|
|
define i32 @main() nounwind {
|
|
|
|
|
entry:
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.cond: ; preds = %for.inc, %entry
|
|
|
|
|
%g_4.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ] ; <i32> [#uses=5]
|
|
|
|
|
%cmp = icmp slt i32 %g_4.0, 5 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.cond
|
|
|
|
|
%conv = trunc i32 %g_4.0 to i16 ; <i16> [#uses=1]
|
|
|
|
|
%tobool.not = icmp eq i16 %conv, 0 ; <i1> [#uses=1]
|
|
|
|
|
%tobool3 = icmp ne i32 %g_4.0, 0 ; <i1> [#uses=1]
|
|
|
|
|
%or.cond = and i1 %tobool.not, %tobool3 ; <i1> [#uses=1]
|
|
|
|
|
br i1 %or.cond, label %for.end, label %for.inc
|
|
|
|
|
|
|
|
|
|
for.inc: ; preds = %for.body
|
|
|
|
|
%add = add nsw i32 %g_4.0, 1 ; <i32> [#uses=1]
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.body, %for.cond
|
[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
|
|
|
%call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i32 %g_4.0) nounwind ; <i32> [#uses=0]
|
2010-08-11 08:12:36 +08:00
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare i32 @printf(i8*, ...)
|
2011-10-03 15:10:45 +08:00
|
|
|
|
|
|
|
|
define void @test(i8* %a, i32 %n) nounwind {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp1 = icmp sgt i32 %n, 0
|
|
|
|
|
br i1 %cmp1, label %for.body.lr.ph, label %for.end
|
|
|
|
|
|
|
|
|
|
for.body.lr.ph: ; preds = %entry
|
|
|
|
|
%tmp = zext i32 %n to i64
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body, %for.body.lr.ph
|
|
|
|
|
%indvar = phi i64 [ %indvar.next, %for.body ], [ 0, %for.body.lr.ph ]
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx = getelementptr i8, i8* %a, i64 %indvar
|
2011-10-03 15:10:45 +08:00
|
|
|
store i8 0, i8* %arrayidx, align 1
|
|
|
|
|
%indvar.next = add i64 %indvar, 1
|
|
|
|
|
%exitcond = icmp ne i64 %indvar.next, %tmp
|
|
|
|
|
br i1 %exitcond, label %for.body, label %for.cond.for.end_crit_edge
|
|
|
|
|
|
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
|
|
|
br label %for.end
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK: Determining loop execution counts for: @test
|
|
|
|
|
; CHECK-NEXT: backedge-taken count is
|
|
|
|
|
; CHECK-NEXT: max backedge-taken count is -1
|
Fix a bug in SCEV's backedge taken count computation from my prior fix in Jan.
This has to do with the trip count computation for loops with multiple
exits, which is quite subtle. Most passes just ask for a single trip
count number, so we must be conservative assuming any exit could be
taken. Normally, we rely on the "exact" trip count, which was
correctly given as "unknown". However, SCEV also gives a "max"
back-edge taken count. The loops max BE taken count is conservatively
a maximum over the max of each exit's non-exiting iterations
count. Note that some exit tests can be skipped so the max loop
back-edge taken count can actually exceed the max non-exiting
iterations for some exits. However, when we know the loop *latch*
cannot be skipped, we can directly use its max taken count
disregarding other exits. I previously took the minimum here without
checking whether the other exit could be skipped. The correct, and
simpler thing to do here is just to directly use the loop latch's max
non-exiting iterations as the loops max back-edge count.
In the problematic test case, the first loop exit had a max of zero
non-exiting iterations, but could be skipped. The loop latch was known
not to be skipped but had max of one non-exiting iteration. We
incorrectly claimed the loop back-edge could be taken zero times, when
it is actually taken one time.
Fixes Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
Loop %for.body.i: max backedge-taken count is 1.
llvm-svn: 209358
2014-05-22 08:37:03 +08:00
|
|
|
|
|
|
|
|
; PR19799: Indvars miscompile due to an incorrect max backedge taken count from SCEV.
|
|
|
|
|
; CHECK-LABEL: @pr19799
|
2015-03-05 02:43:29 +08:00
|
|
|
; CHECK: Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
|
Fix a bug in SCEV's backedge taken count computation from my prior fix in Jan.
This has to do with the trip count computation for loops with multiple
exits, which is quite subtle. Most passes just ask for a single trip
count number, so we must be conservative assuming any exit could be
taken. Normally, we rely on the "exact" trip count, which was
correctly given as "unknown". However, SCEV also gives a "max"
back-edge taken count. The loops max BE taken count is conservatively
a maximum over the max of each exit's non-exiting iterations
count. Note that some exit tests can be skipped so the max loop
back-edge taken count can actually exceed the max non-exiting
iterations for some exits. However, when we know the loop *latch*
cannot be skipped, we can directly use its max taken count
disregarding other exits. I previously took the minimum here without
checking whether the other exit could be skipped. The correct, and
simpler thing to do here is just to directly use the loop latch's max
non-exiting iterations as the loops max back-edge count.
In the problematic test case, the first loop exit had a max of zero
non-exiting iterations, but could be skipped. The loop latch was known
not to be skipped but had max of one non-exiting iteration. We
incorrectly claimed the loop back-edge could be taken zero times, when
it is actually taken one time.
Fixes Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
Loop %for.body.i: max backedge-taken count is 1.
llvm-svn: 209358
2014-05-22 08:37:03 +08:00
|
|
|
; CHECK: Loop %for.body.i: max backedge-taken count is 1
|
|
|
|
|
@a = common global i32 0, align 4
|
|
|
|
|
|
|
|
|
|
define i32 @pr19799() {
|
|
|
|
|
entry:
|
|
|
|
|
store i32 -1, i32* @a, align 4
|
|
|
|
|
br label %for.body.i
|
|
|
|
|
|
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
|
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
|
|
|
%tobool.i = icmp eq i32 %storemerge1.i, 0
|
|
|
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
|
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
|
|
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
|
|
|
store i32 %add.i.i, i32* @a, align 4
|
|
|
|
|
%cmp.i = icmp slt i32 %storemerge1.i, 0
|
|
|
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
|
|
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
2014-05-24 03:47:13 +08:00
|
|
|
|
2014-05-27 14:44:25 +08:00
|
|
|
; PR18886: Indvars miscompile due to an incorrect max backedge taken count from SCEV.
|
|
|
|
|
; CHECK-LABEL: @pr18886
|
2015-03-05 02:43:29 +08:00
|
|
|
; CHECK: Loop %for.body: <multiple exits> Unpredictable backedge-taken count.
|
2014-05-27 14:44:25 +08:00
|
|
|
; CHECK: Loop %for.body: max backedge-taken count is 3
|
|
|
|
|
@aa = global i64 0, align 8
|
|
|
|
|
|
|
|
|
|
define i32 @pr18886() {
|
|
|
|
|
entry:
|
|
|
|
|
store i64 -21, i64* @aa, align 8
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body:
|
|
|
|
|
%storemerge1 = phi i64 [ -21, %entry ], [ %add, %for.cond ]
|
|
|
|
|
%tobool = icmp eq i64 %storemerge1, 0
|
|
|
|
|
%add = add nsw i64 %storemerge1, 8
|
|
|
|
|
br i1 %tobool, label %return, label %for.cond
|
|
|
|
|
|
|
|
|
|
for.cond:
|
|
|
|
|
store i64 %add, i64* @aa, align 8
|
|
|
|
|
%cmp = icmp slt i64 %add, 9
|
|
|
|
|
br i1 %cmp, label %for.body, label %return
|
|
|
|
|
|
|
|
|
|
return:
|
|
|
|
|
%retval.0 = phi i32 [ 1, %for.body ], [ 0, %for.cond ]
|
|
|
|
|
ret i32 %retval.0
|
|
|
|
|
}
|
|
|
|
|
|
2014-05-24 04:46:21 +08:00
|
|
|
; Here we have a must-exit loop latch that is not computable and a
|
2014-05-24 03:47:13 +08:00
|
|
|
; may-exit early exit that can only have one non-exiting iteration
|
|
|
|
|
; before the check is forever skipped.
|
|
|
|
|
;
|
|
|
|
|
; CHECK-LABEL: @cannot_compute_mustexit
|
2015-03-05 02:43:29 +08:00
|
|
|
; CHECK: Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %for.body.i: Unpredictable max backedge-taken count.
|
2014-05-24 03:47:13 +08:00
|
|
|
@b = common global i32 0, align 4
|
|
|
|
|
|
|
|
|
|
define i32 @cannot_compute_mustexit() {
|
|
|
|
|
entry:
|
|
|
|
|
store i32 -1, i32* @a, align 4
|
|
|
|
|
br label %for.body.i
|
|
|
|
|
|
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
|
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
|
|
|
%tobool.i = icmp eq i32 %storemerge1.i, 0
|
|
|
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
|
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
|
|
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
|
|
|
store i32 %add.i.i, i32* @a, align 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%ld = load volatile i32, i32* @b
|
2014-05-24 03:47:13 +08:00
|
|
|
%cmp.i = icmp ne i32 %ld, 0
|
|
|
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
|
|
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
2014-05-24 04:46:21 +08:00
|
|
|
; This loop has two must-exits, both of which dominate the latch. The
|
2014-05-24 03:47:13 +08:00
|
|
|
; MaxBECount should be the minimum of them.
|
|
|
|
|
;
|
|
|
|
|
; CHECK-LABEL: @two_mustexit
|
2018-03-27 15:30:38 +08:00
|
|
|
; CHECK: Loop %for.body.i: <multiple exits> backedge-taken count is 1
|
2014-05-24 03:47:13 +08:00
|
|
|
; CHECK: Loop %for.body.i: max backedge-taken count is 1
|
|
|
|
|
define i32 @two_mustexit() {
|
|
|
|
|
entry:
|
|
|
|
|
store i32 -1, i32* @a, align 4
|
|
|
|
|
br label %for.body.i
|
|
|
|
|
|
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
|
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
|
|
|
%tobool.i = icmp sgt i32 %storemerge1.i, 0
|
|
|
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
|
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
|
|
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
|
|
|
store i32 %add.i.i, i32* @a, align 4
|
|
|
|
|
%cmp.i = icmp slt i32 %storemerge1.i, 3
|
|
|
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
|
|
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
2017-01-12 04:55:48 +08:00
|
|
|
|
|
|
|
|
; CHECK-LABEL: @ne_max_trip_count_1
|
|
|
|
|
; CHECK: Loop %for.body: max backedge-taken count is 7
|
|
|
|
|
define i32 @ne_max_trip_count_1(i32 %n) {
|
|
|
|
|
entry:
|
|
|
|
|
%masked = and i32 %n, 7
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body:
|
|
|
|
|
%i = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
|
%add = add nsw i32 %i, 1
|
|
|
|
|
%cmp = icmp ne i32 %i, %masked
|
|
|
|
|
br i1 %cmp, label %for.body, label %bar.exit
|
|
|
|
|
|
|
|
|
|
bar.exit:
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @ne_max_trip_count_2
|
|
|
|
|
; CHECK: Loop %for.body: max backedge-taken count is -1
|
|
|
|
|
define i32 @ne_max_trip_count_2(i32 %n) {
|
|
|
|
|
entry:
|
|
|
|
|
%masked = and i32 %n, 7
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body:
|
|
|
|
|
%i = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
|
%add = add nsw i32 %i, 1
|
|
|
|
|
%cmp = icmp ne i32 %add, %masked
|
|
|
|
|
br i1 %cmp, label %for.body, label %bar.exit
|
|
|
|
|
|
|
|
|
|
bar.exit:
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @ne_max_trip_count_3
|
2017-01-12 05:07:15 +08:00
|
|
|
; CHECK: Loop %for.body: max backedge-taken count is 6
|
2017-01-12 04:55:48 +08:00
|
|
|
define i32 @ne_max_trip_count_3(i32 %n) {
|
|
|
|
|
entry:
|
|
|
|
|
%masked = and i32 %n, 7
|
|
|
|
|
%guard = icmp eq i32 %masked, 0
|
|
|
|
|
br i1 %guard, label %exit, label %for.preheader
|
|
|
|
|
|
|
|
|
|
for.preheader:
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body:
|
|
|
|
|
%i = phi i32 [ 0, %for.preheader ], [ %add, %for.body ]
|
|
|
|
|
%add = add nsw i32 %i, 1
|
|
|
|
|
%cmp = icmp ne i32 %add, %masked
|
|
|
|
|
br i1 %cmp, label %for.body, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
br label %exit
|
|
|
|
|
|
|
|
|
|
exit:
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: @ne_max_trip_count_4
|
2017-01-12 05:07:15 +08:00
|
|
|
; CHECK: Loop %for.body: max backedge-taken count is -2
|
2017-01-12 04:55:48 +08:00
|
|
|
define i32 @ne_max_trip_count_4(i32 %n) {
|
|
|
|
|
entry:
|
|
|
|
|
%guard = icmp eq i32 %n, 0
|
|
|
|
|
br i1 %guard, label %exit, label %for.preheader
|
|
|
|
|
|
|
|
|
|
for.preheader:
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body:
|
|
|
|
|
%i = phi i32 [ 0, %for.preheader ], [ %add, %for.body ]
|
|
|
|
|
%add = add nsw i32 %i, 1
|
|
|
|
|
%cmp = icmp ne i32 %add, %n
|
|
|
|
|
br i1 %cmp, label %for.body, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
br label %exit
|
|
|
|
|
|
|
|
|
|
exit:
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
2017-10-13 22:30:43 +08:00
|
|
|
|
|
|
|
|
; The end bound of the loop can change between iterations, so the exact trip
|
|
|
|
|
; count is unknown, but SCEV can calculate the max trip count.
|
|
|
|
|
define void @changing_end_bound(i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: max backedge-taken count is 2147483646
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add nsw i32 %iv, 1
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Similar test as above, but unknown start value.
|
|
|
|
|
; Also, there's no nsw on the iv.next, but SCEV knows
|
|
|
|
|
; the termination condition is LT, so the IV cannot wrap.
|
|
|
|
|
define void @changing_end_bound2(i32 %start, i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound2
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: max backedge-taken count is -1
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ %start, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add i32 %iv, 1
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; changing end bound and greater than one stride
|
|
|
|
|
define void @changing_end_bound3(i32 %start, i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound3
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: max backedge-taken count is 1073741823
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ %start, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add nsw i32 %iv, 4
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; same as above test, but the IV can wrap around.
|
|
|
|
|
; so the max backedge taken count is unpredictable.
|
|
|
|
|
define void @changing_end_bound4(i32 %start, i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound4
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable max backedge-taken count.
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ %start, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add i32 %iv, 4
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; unknown stride. Since it's not knownPositive, we do not estimate the max
|
|
|
|
|
; backedge taken count.
|
|
|
|
|
define void @changing_end_bound5(i32 %stride, i32 %start, i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound5
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable max backedge-taken count.
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ %start, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add nsw i32 %iv, %stride
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; negative stride value
|
|
|
|
|
define void @changing_end_bound6(i32 %start, i32* %n_addr, i32* %addr) {
|
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @changing_end_bound6
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable backedge-taken count.
|
|
|
|
|
; CHECK: Loop %loop: Unpredictable max backedge-taken count.
|
|
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%iv = phi i32 [ %start, %entry ], [ %iv.next, %loop ]
|
|
|
|
|
%acc = phi i32 [ 0, %entry ], [ %acc.next, %loop ]
|
|
|
|
|
%val = load atomic i32, i32* %addr unordered, align 4
|
|
|
|
|
fence acquire
|
|
|
|
|
%acc.next = add i32 %acc, %val
|
|
|
|
|
%iv.next = add nsw i32 %iv, -1
|
|
|
|
|
%n = load atomic i32, i32* %n_addr unordered, align 4
|
|
|
|
|
%cmp = icmp slt i32 %iv.next, %n
|
|
|
|
|
br i1 %cmp, label %loop, label %loop.exit
|
|
|
|
|
|
|
|
|
|
loop.exit:
|
|
|
|
|
ret void
|
|
|
|
|
}
|