2011-12-09 07:19:40 +01:00
|
|
|
; RUN: opt < %s -S -loop-unroll -unroll-runtime=true | FileCheck %s
|
|
|
|
|
|
2015-04-14 05:20:38 +02:00
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
|
|
2011-12-09 07:19:40 +01:00
|
|
|
; Tests for unrolling loops with run-time trip counts
|
|
|
|
|
|
2014-06-21 15:46:25 +02:00
|
|
|
; CHECK: %xtraiter = and i32 %n
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
; CHECK: %lcmp.mod = icmp ne i32 %xtraiter, 0
|
2015-02-18 20:32:25 +01:00
|
|
|
; CHECK: br i1 %lcmp.mod, label %for.body.prol, label %for.body.preheader.split
|
2014-06-21 15:46:25 +02:00
|
|
|
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
; CHECK: for.body.prol:
|
|
|
|
|
; CHECK: %indvars.iv.prol = phi i64 [ %indvars.iv.next.prol, %for.body.prol ], [ 0, %for.body.preheader ]
|
|
|
|
|
; CHECK: %prol.iter.sub = sub i32 %prol.iter, 1
|
|
|
|
|
; CHECK: %prol.iter.cmp = icmp ne i32 %prol.iter.sub, 0
|
|
|
|
|
; CHECK: br i1 %prol.iter.cmp, label %for.body.prol, label %for.body.preheader.split, !llvm.loop !0
|
2011-12-09 07:19:40 +01:00
|
|
|
|
|
|
|
|
define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp1 = icmp eq i32 %n, 0
|
|
|
|
|
br i1 %cmp1, label %for.end, label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
|
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
|
|
|
%sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-27 20:29:02 +01:00
|
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
2015-02-27 22:17:42 +01:00
|
|
|
%0 = load i32, i32* %arrayidx, align 4
|
2011-12-09 07:19:40 +01:00
|
|
|
%add = add nsw i32 %0, %sum.02
|
|
|
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
|
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
|
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %n
|
|
|
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
|
|
|
%sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
|
ret i32 %sum.0.lcssa
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; Still try to completely unroll loops with compile-time trip counts
|
|
|
|
|
; even if the -unroll-runtime is specified
|
|
|
|
|
|
|
|
|
|
; CHECK: for.body:
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
; CHECK-NOT: for.body.prol:
|
2011-12-09 07:19:40 +01:00
|
|
|
|
|
|
|
|
define i32 @test1(i32* nocapture %a) nounwind uwtable readonly {
|
|
|
|
|
entry:
|
|
|
|
|
br label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
|
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
|
|
|
%sum.01 = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
[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
2015-02-27 20:29:02 +01:00
|
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
2015-02-27 22:17:42 +01:00
|
|
|
%0 = load i32, i32* %arrayidx, align 4
|
2011-12-09 07:19:40 +01:00
|
|
|
%add = add nsw i32 %0, %sum.01
|
|
|
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
|
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
|
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 5
|
|
|
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.body
|
|
|
|
|
ret i32 %add
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; This is test 2007-05-09-UnknownTripCount.ll which can be unrolled now
|
|
|
|
|
; if the -unroll-runtime option is turned on
|
|
|
|
|
|
|
|
|
|
; CHECK: bb72.2:
|
|
|
|
|
|
|
|
|
|
define void @foo(i32 %trips) {
|
|
|
|
|
entry:
|
|
|
|
|
br label %cond_true.outer
|
|
|
|
|
|
|
|
|
|
cond_true.outer:
|
|
|
|
|
%indvar1.ph = phi i32 [ 0, %entry ], [ %indvar.next2, %bb72 ]
|
|
|
|
|
br label %bb72
|
|
|
|
|
|
|
|
|
|
bb72:
|
|
|
|
|
%indvar.next2 = add i32 %indvar1.ph, 1
|
|
|
|
|
%exitcond3 = icmp eq i32 %indvar.next2, %trips
|
|
|
|
|
br i1 %exitcond3, label %cond_true138, label %cond_true.outer
|
|
|
|
|
|
|
|
|
|
cond_true138:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; Test run-time unrolling for a loop that counts down by -2.
|
|
|
|
|
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
; CHECK: for.body.prol:
|
|
|
|
|
; CHECK: br i1 %prol.iter.cmp, label %for.body.prol, label %for.body.preheader.split
|
2011-12-09 07:19:40 +01:00
|
|
|
|
|
|
|
|
define zeroext i16 @down(i16* nocapture %p, i32 %len) nounwind uwtable readonly {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp2 = icmp eq i32 %len, 0
|
|
|
|
|
br i1 %cmp2, label %for.end, label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
|
|
|
%p.addr.05 = phi i16* [ %incdec.ptr, %for.body ], [ %p, %entry ]
|
|
|
|
|
%len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
|
|
|
|
|
%res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-27 20:29:02 +01:00
|
|
|
%incdec.ptr = getelementptr inbounds i16, i16* %p.addr.05, i64 1
|
2015-02-27 22:17:42 +01:00
|
|
|
%0 = load i16, i16* %p.addr.05, align 2
|
2011-12-09 07:19:40 +01:00
|
|
|
%conv = zext i16 %0 to i32
|
|
|
|
|
%add = add i32 %conv, %res.03
|
|
|
|
|
%sub = add nsw i32 %len.addr.04, -2
|
|
|
|
|
%cmp = icmp eq i32 %sub, 0
|
|
|
|
|
br i1 %cmp, label %for.cond.for.end_crit_edge, label %for.body
|
|
|
|
|
|
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
|
|
|
%phitmp = trunc i32 %add to i16
|
|
|
|
|
br label %for.end
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
|
|
|
|
|
%res.0.lcssa = phi i16 [ %phitmp, %for.cond.for.end_crit_edge ], [ 0, %entry ]
|
|
|
|
|
ret i16 %res.0.lcssa
|
|
|
|
|
}
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
|
2015-03-09 07:14:18 +01:00
|
|
|
; Test run-time unrolling disable metadata.
|
|
|
|
|
; CHECK: for.body:
|
|
|
|
|
; CHECK-NOT: for.body.prol:
|
|
|
|
|
|
|
|
|
|
define zeroext i16 @test2(i16* nocapture %p, i32 %len) nounwind uwtable readonly {
|
|
|
|
|
entry:
|
|
|
|
|
%cmp2 = icmp eq i32 %len, 0
|
|
|
|
|
br i1 %cmp2, label %for.end, label %for.body
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
|
|
|
%p.addr.05 = phi i16* [ %incdec.ptr, %for.body ], [ %p, %entry ]
|
|
|
|
|
%len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
|
|
|
|
|
%res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
|
|
|
|
|
%incdec.ptr = getelementptr inbounds i16, i16* %p.addr.05, i64 1
|
|
|
|
|
%0 = load i16, i16* %p.addr.05, align 2
|
|
|
|
|
%conv = zext i16 %0 to i32
|
|
|
|
|
%add = add i32 %conv, %res.03
|
|
|
|
|
%sub = add nsw i32 %len.addr.04, -2
|
|
|
|
|
%cmp = icmp eq i32 %sub, 0
|
|
|
|
|
br i1 %cmp, label %for.cond.for.end_crit_edge, label %for.body, !llvm.loop !0
|
|
|
|
|
|
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
|
|
|
%phitmp = trunc i32 %add to i16
|
|
|
|
|
br label %for.end
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
|
|
|
|
|
%res.0.lcssa = phi i16 [ %phitmp, %for.cond.for.end_crit_edge ], [ 0, %entry ]
|
|
|
|
|
ret i16 %res.0.lcssa
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
!0 = distinct !{!0, !1}
|
|
|
|
|
!1 = !{!"llvm.loop.unroll.runtime.disable"}
|
|
|
|
|
|
2015-01-08 23:38:29 +01:00
|
|
|
; CHECK: !0 = distinct !{!0, !1}
|
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
2014-12-15 20:07:53 +01:00
|
|
|
; CHECK: !1 = !{!"llvm.loop.unroll.disable"}
|
Use a loop to simplify the runtime unrolling prologue.
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
2014-09-29 13:15:00 +02:00
|
|
|
|
