2011-04-12 05:09:18 +08:00
|
|
|
; RUN: llc < %s -mtriple=thumbv7-apple-darwin -mcpu=cortex-a8 | FileCheck %s
|
|
|
|
|
|
|
|
|
|
; Overly aggressive LICM simply adds copies of constants
|
|
|
|
|
; rdar://9266679
|
|
|
|
|
|
|
|
|
|
define zeroext i1 @t(i32* nocapture %A, i32 %size, i32 %value) nounwind readonly ssp {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: t:
|
2011-04-12 05:09:18 +08:00
|
|
|
entry:
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.cond:
|
|
|
|
|
%0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
|
|
|
|
|
%cmp = icmp ult i32 %0, %size
|
|
|
|
|
br i1 %cmp, label %for.body, label %return
|
|
|
|
|
|
|
|
|
|
for.body:
|
2011-05-04 06:31:21 +08:00
|
|
|
; CHECK: %for.
|
MachineSink: Fix and tweak critical-edge breaking heuristic.
Per original comment, the intention of this loop
is to go ahead and break the critical edge
(in order to sink this instruction) if there's
reason to believe doing so might "unblock" the
sinking of additional instructions that define
registers used by this one. The idea is that if
we have a few instructions to sink "together"
breaking the edge might be worthwhile.
This commit makes a few small changes
to help better realize this goal:
First, modify the loop to ignore registers
defined by this instruction. We don't
sink definitions of physical registers,
and sinking an SSA definition isn't
going to unblock an upstream instruction.
Second, ignore uses of physical registers.
Instructions that define physical registers are
rejected for sinking, and so moving this one
won't enable moving any defining instructions.
As an added bonus, while virtual register
use-def chains are generally small due
to SSA goodness, iteration over the uses
and definitions (used by hasOneNonDBGUse)
for physical registers like EFLAGS
can be rather expensive in practice.
(This is the original reason for looking at this)
Finally, to keep things simple continue
to only consider this trick for registers that
have a single use (via hasOneNonDBGUse),
but to avoid spuriously breaking critical edges
only do so if the definition resides
in the same MBB and therefore this one directly
blocks it from being sunk as well.
If sinking them together is meant to be,
let the iterative nature of this pass
sink the definition into this block first.
Update tests to accomodate this change,
add new testcase where sinking avoids pipeline stalls.
llvm-svn: 192608
2013-10-15 00:57:17 +08:00
|
|
|
; CHECK: mov{{.*}} r{{[0-9]+}}, #{{[01]}}
|
|
|
|
|
; CHECK: mov{{.*}} r{{[0-9]+}}, #{{[01]}}
|
|
|
|
|
; CHECK-NOT: mov r{{[0-9]+}}, #{{[01]}}
|
[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 i32, i32* %A, i32 %0
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp4 = load i32, i32* %arrayidx, align 4
|
2011-04-12 05:09:18 +08:00
|
|
|
%cmp6 = icmp eq i32 %tmp4, %value
|
|
|
|
|
br i1 %cmp6, label %return, label %for.inc
|
|
|
|
|
|
|
|
|
|
for.inc:
|
|
|
|
|
%inc = add i32 %0, 1
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
return:
|
|
|
|
|
%retval.0 = phi i1 [ true, %for.body ], [ false, %for.cond ]
|
|
|
|
|
ret i1 %retval.0
|
|
|
|
|
}
|