mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 04:02:41 +01:00
0d99339102
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
173 lines
4.6 KiB
LLVM
173 lines
4.6 KiB
LLVM
; Test 32-bit atomic minimum and maximum. Here we match the z10 versions,
|
|
; which can't use LOCR.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 | FileCheck %s
|
|
|
|
; Check signed minium.
|
|
define i32 @f1(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: [[LOOP:\.[^:]*]]:
|
|
; CHECK: lr [[NEW:%r[0-9]+]], %r2
|
|
; CHECK: crjle %r2, %r4, [[KEEP:\..*]]
|
|
; CHECK: lr [[NEW]], %r4
|
|
; CHECK: cs %r2, [[NEW]], 0(%r3)
|
|
; CHECK: jl [[LOOP]]
|
|
; CHECK: br %r14
|
|
%res = atomicrmw min i32 *%src, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check signed maximum.
|
|
define i32 @f2(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: [[LOOP:\.[^:]*]]:
|
|
; CHECK: lr [[NEW:%r[0-9]+]], %r2
|
|
; CHECK: crjhe %r2, %r4, [[KEEP:\..*]]
|
|
; CHECK: lr [[NEW]], %r4
|
|
; CHECK: cs %r2, [[NEW]], 0(%r3)
|
|
; CHECK: jl [[LOOP]]
|
|
; CHECK: br %r14
|
|
%res = atomicrmw max i32 *%src, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check unsigned minimum.
|
|
define i32 @f3(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: [[LOOP:\.[^:]*]]:
|
|
; CHECK: lr [[NEW:%r[0-9]+]], %r2
|
|
; CHECK: clrjle %r2, %r4, [[KEEP:\..*]]
|
|
; CHECK: lr [[NEW]], %r4
|
|
; CHECK: cs %r2, [[NEW]], 0(%r3)
|
|
; CHECK: jl [[LOOP]]
|
|
; CHECK: br %r14
|
|
%res = atomicrmw umin i32 *%src, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check unsigned maximum.
|
|
define i32 @f4(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: [[LOOP:\.[^:]*]]:
|
|
; CHECK: lr [[NEW:%r[0-9]+]], %r2
|
|
; CHECK: clrjhe %r2, %r4, [[KEEP:\..*]]
|
|
; CHECK: lr [[NEW]], %r4
|
|
; CHECK: cs %r2, [[NEW]], 0(%r3)
|
|
; CHECK: jl [[LOOP]]
|
|
; CHECK: br %r14
|
|
%res = atomicrmw umax i32 *%src, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the high end of the aligned CS range.
|
|
define i32 @f5(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK: l %r2, 4092(%r3)
|
|
; CHECK: cs %r2, {{%r[0-9]+}}, 4092(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 1023
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the next word up, which requires CSY.
|
|
define i32 @f6(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f6:
|
|
; CHECK: ly %r2, 4096(%r3)
|
|
; CHECK: csy %r2, {{%r[0-9]+}}, 4096(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 1024
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the high end of the aligned CSY range.
|
|
define i32 @f7(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f7:
|
|
; CHECK: ly %r2, 524284(%r3)
|
|
; CHECK: csy %r2, {{%r[0-9]+}}, 524284(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 131071
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the next word up, which needs separate address logic.
|
|
define i32 @f8(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f8:
|
|
; CHECK: agfi %r3, 524288
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: cs %r2, {{%r[0-9]+}}, 0(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 131072
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the high end of the negative aligned CSY range.
|
|
define i32 @f9(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f9:
|
|
; CHECK: ly %r2, -4(%r3)
|
|
; CHECK: csy %r2, {{%r[0-9]+}}, -4(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 -1
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the low end of the CSY range.
|
|
define i32 @f10(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f10:
|
|
; CHECK: ly %r2, -524288(%r3)
|
|
; CHECK: csy %r2, {{%r[0-9]+}}, -524288(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 -131072
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check the next word down, which needs separate address logic.
|
|
define i32 @f11(i32 %dummy, i32 *%src, i32 %b) {
|
|
; CHECK-LABEL: f11:
|
|
; CHECK: agfi %r3, -524292
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: cs %r2, {{%r[0-9]+}}, 0(%r3)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i32, i32 *%src, i64 -131073
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check that indexed addresses are not allowed.
|
|
define i32 @f12(i32 %dummy, i64 %base, i64 %index, i32 %b) {
|
|
; CHECK-LABEL: f12:
|
|
; CHECK: agr %r3, %r4
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: cs %r2, {{%r[0-9]+}}, 0(%r3)
|
|
; CHECK: br %r14
|
|
%add = add i64 %base, %index
|
|
%ptr = inttoptr i64 %add to i32 *
|
|
%res = atomicrmw min i32 *%ptr, i32 %b seq_cst
|
|
ret i32 %res
|
|
}
|
|
|
|
; Check that constants are handled.
|
|
define i32 @f13(i32 %dummy, i32 *%ptr) {
|
|
; CHECK-LABEL: f13:
|
|
; CHECK: lhi [[LIMIT:%r[0-9]+]], 42
|
|
; CHECK: l %r2, 0(%r3)
|
|
; CHECK: [[LOOP:\.[^:]*]]:
|
|
; CHECK: lr [[NEW:%r[0-9]+]], %r2
|
|
; CHECK: crjle %r2, [[LIMIT]], [[KEEP:\..*]]
|
|
; CHECK: lhi [[NEW]], 42
|
|
; CHECK: cs %r2, [[NEW]], 0(%r3)
|
|
; CHECK: jl [[LOOP]]
|
|
; CHECK: br %r14
|
|
%res = atomicrmw min i32 *%ptr, i32 42 seq_cst
|
|
ret i32 %res
|
|
}
|