2013-05-07 00:17:29 +08:00
|
|
|
; Test 64-bit comparison in which the second operand is a zero-extended i32.
|
|
|
|
;
|
|
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
|
|
|
|
|
2013-07-03 18:10:02 +08:00
|
|
|
declare i64 @foo()
|
|
|
|
|
2013-05-07 00:17:29 +08:00
|
|
|
; Check unsigned register comparison.
|
|
|
|
define double @f1(double %a, double %b, i64 %i1, i32 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f1:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; ...and again with a different representation.
|
|
|
|
define double @f2(double %a, double %b, i64 %i1, i64 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f2:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = and i64 %unext, 4294967295
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check signed register comparison, which can't use CLGFR.
|
|
|
|
define double @f3(double %a, double %b, i64 %i1, i32 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f3:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK-NOT: clgfr
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp slt i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; ...and again with a different representation
|
|
|
|
define double @f4(double %a, double %b, i64 %i1, i64 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f4:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK-NOT: clgfr
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = and i64 %unext, 4294967295
|
|
|
|
%cond = icmp slt i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check register equality.
|
|
|
|
define double @f5(double %a, double %b, i64 %i1, i32 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f5:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: je
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp eq i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; ...and again with a different representation
|
|
|
|
define double @f6(double %a, double %b, i64 %i1, i64 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f6:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: je
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = and i64 %unext, 4294967295
|
|
|
|
%cond = icmp eq i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check register inequality.
|
|
|
|
define double @f7(double %a, double %b, i64 %i1, i32 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f7:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jlh
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ne i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; ...and again with a different representation
|
|
|
|
define double @f8(double %a, double %b, i64 %i1, i64 %unext) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f8:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jlh
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = and i64 %unext, 4294967295
|
|
|
|
%cond = icmp ne i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
2013-08-23 19:27:19 +08:00
|
|
|
; Check unsigned comparison with memory.
|
2013-05-07 00:17:29 +08:00
|
|
|
define double @f9(double %a, double %b, i64 %i1, i32 *%ptr) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f9:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check signed comparison with memory.
|
|
|
|
define double @f10(double %a, double %b, i64 %i1, i32 *%ptr) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f10:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK-NOT: clgf
|
|
|
|
; CHECK: br %r14
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp slt i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check memory equality.
|
|
|
|
define double @f11(double %a, double %b, i64 %i1, i32 *%ptr) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f11:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: je
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp eq i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check memory inequality.
|
|
|
|
define double @f12(double %a, double %b, i64 %i1, i32 *%ptr) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f12:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jlh
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ne i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the high end of the aligned CLGF range.
|
|
|
|
define double @f13(double %a, double %b, i64 %i1, i32 *%base) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f13:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, 524284(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr = getelementptr i32, i32 *%base, i64 131071
|
2013-05-07 00:17:29 +08:00
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the next word up, which needs separate address logic.
|
|
|
|
; Other sequences besides this one would be OK.
|
|
|
|
define double @f14(double %a, double %b, i64 %i1, i32 *%base) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f14:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: agfi %r3, 524288
|
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr = getelementptr i32, i32 *%base, i64 131072
|
2013-05-07 00:17:29 +08:00
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the high end of the negative aligned CLGF range.
|
|
|
|
define double @f15(double %a, double %b, i64 %i1, i32 *%base) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f15:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, -4(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr = getelementptr i32, i32 *%base, i64 -1
|
2013-05-07 00:17:29 +08:00
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the low end of the CLGF range.
|
|
|
|
define double @f16(double %a, double %b, i64 %i1, i32 *%base) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f16:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, -524288(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr = getelementptr i32, i32 *%base, i64 -131072
|
2013-05-07 00:17:29 +08:00
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the next word down, which needs separate address logic.
|
|
|
|
; Other sequences besides this one would be OK.
|
|
|
|
define double @f17(double %a, double %b, i64 %i1, i32 *%base) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f17:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: agfi %r3, -524292
|
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr = getelementptr i32, i32 *%base, i64 -131073
|
2013-05-07 00:17:29 +08:00
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check that CLGF allows an index.
|
|
|
|
define double @f18(double %a, double %b, i64 %i1, i64 %base, i64 %index) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f18:
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: clgf %r2, 524284({{%r4,%r3|%r3,%r4}})
|
2013-05-21 16:53:17 +08:00
|
|
|
; CHECK-NEXT: jl
|
2013-05-07 00:17:29 +08:00
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%add1 = add i64 %base, %index
|
|
|
|
%add2 = add i64 %add1, 524284
|
|
|
|
%ptr = inttoptr i64 %add2 to i32 *
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
2013-07-03 18:10:02 +08:00
|
|
|
|
|
|
|
; Check that comparisons of spilled values can use CLGF rather than CLGFR.
|
|
|
|
define i64 @f19(i32 *%ptr0) {
|
2013-07-14 14:24:09 +08:00
|
|
|
; CHECK-LABEL: f19:
|
2013-07-03 18:10:02 +08:00
|
|
|
; CHECK: brasl %r14, foo@PLT
|
|
|
|
; CHECK: clgf {{%r[0-9]+}}, 16{{[04]}}(%r15)
|
|
|
|
; CHECK: br %r14
|
[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
|
|
|
%ptr1 = getelementptr i32, i32 *%ptr0, i64 2
|
|
|
|
%ptr2 = getelementptr i32, i32 *%ptr0, i64 4
|
|
|
|
%ptr3 = getelementptr i32, i32 *%ptr0, i64 6
|
|
|
|
%ptr4 = getelementptr i32, i32 *%ptr0, i64 8
|
|
|
|
%ptr5 = getelementptr i32, i32 *%ptr0, i64 10
|
|
|
|
%ptr6 = getelementptr i32, i32 *%ptr0, i64 12
|
|
|
|
%ptr7 = getelementptr i32, i32 *%ptr0, i64 14
|
|
|
|
%ptr8 = getelementptr i32, i32 *%ptr0, i64 16
|
|
|
|
%ptr9 = getelementptr i32, i32 *%ptr0, i64 18
|
2013-07-03 18:10:02 +08:00
|
|
|
|
|
|
|
%val0 = load i32 *%ptr0
|
|
|
|
%val1 = load i32 *%ptr1
|
|
|
|
%val2 = load i32 *%ptr2
|
|
|
|
%val3 = load i32 *%ptr3
|
|
|
|
%val4 = load i32 *%ptr4
|
|
|
|
%val5 = load i32 *%ptr5
|
|
|
|
%val6 = load i32 *%ptr6
|
|
|
|
%val7 = load i32 *%ptr7
|
|
|
|
%val8 = load i32 *%ptr8
|
|
|
|
%val9 = load i32 *%ptr9
|
|
|
|
|
|
|
|
%frob0 = add i32 %val0, 100
|
|
|
|
%frob1 = add i32 %val1, 100
|
|
|
|
%frob2 = add i32 %val2, 100
|
|
|
|
%frob3 = add i32 %val3, 100
|
|
|
|
%frob4 = add i32 %val4, 100
|
|
|
|
%frob5 = add i32 %val5, 100
|
|
|
|
%frob6 = add i32 %val6, 100
|
|
|
|
%frob7 = add i32 %val7, 100
|
|
|
|
%frob8 = add i32 %val8, 100
|
|
|
|
%frob9 = add i32 %val9, 100
|
|
|
|
|
|
|
|
store i32 %frob0, i32 *%ptr0
|
|
|
|
store i32 %frob1, i32 *%ptr1
|
|
|
|
store i32 %frob2, i32 *%ptr2
|
|
|
|
store i32 %frob3, i32 *%ptr3
|
|
|
|
store i32 %frob4, i32 *%ptr4
|
|
|
|
store i32 %frob5, i32 *%ptr5
|
|
|
|
store i32 %frob6, i32 *%ptr6
|
|
|
|
store i32 %frob7, i32 *%ptr7
|
|
|
|
store i32 %frob8, i32 *%ptr8
|
|
|
|
store i32 %frob9, i32 *%ptr9
|
|
|
|
|
|
|
|
%ret = call i64 @foo()
|
|
|
|
|
|
|
|
%ext0 = zext i32 %frob0 to i64
|
|
|
|
%ext1 = zext i32 %frob1 to i64
|
|
|
|
%ext2 = zext i32 %frob2 to i64
|
|
|
|
%ext3 = zext i32 %frob3 to i64
|
|
|
|
%ext4 = zext i32 %frob4 to i64
|
|
|
|
%ext5 = zext i32 %frob5 to i64
|
|
|
|
%ext6 = zext i32 %frob6 to i64
|
|
|
|
%ext7 = zext i32 %frob7 to i64
|
|
|
|
%ext8 = zext i32 %frob8 to i64
|
|
|
|
%ext9 = zext i32 %frob9 to i64
|
|
|
|
|
|
|
|
%cmp0 = icmp ult i64 %ret, %ext0
|
|
|
|
%cmp1 = icmp ult i64 %ret, %ext1
|
|
|
|
%cmp2 = icmp ult i64 %ret, %ext2
|
|
|
|
%cmp3 = icmp ult i64 %ret, %ext3
|
|
|
|
%cmp4 = icmp ult i64 %ret, %ext4
|
|
|
|
%cmp5 = icmp ult i64 %ret, %ext5
|
|
|
|
%cmp6 = icmp ult i64 %ret, %ext6
|
|
|
|
%cmp7 = icmp ult i64 %ret, %ext7
|
|
|
|
%cmp8 = icmp ult i64 %ret, %ext8
|
|
|
|
%cmp9 = icmp ult i64 %ret, %ext9
|
|
|
|
|
|
|
|
%sel0 = select i1 %cmp0, i64 %ret, i64 0
|
|
|
|
%sel1 = select i1 %cmp1, i64 %sel0, i64 1
|
|
|
|
%sel2 = select i1 %cmp2, i64 %sel1, i64 2
|
|
|
|
%sel3 = select i1 %cmp3, i64 %sel2, i64 3
|
|
|
|
%sel4 = select i1 %cmp4, i64 %sel3, i64 4
|
|
|
|
%sel5 = select i1 %cmp5, i64 %sel4, i64 5
|
|
|
|
%sel6 = select i1 %cmp6, i64 %sel5, i64 6
|
|
|
|
%sel7 = select i1 %cmp7, i64 %sel6, i64 7
|
|
|
|
%sel8 = select i1 %cmp8, i64 %sel7, i64 8
|
|
|
|
%sel9 = select i1 %cmp9, i64 %sel8, i64 9
|
|
|
|
|
|
|
|
ret i64 %sel9
|
|
|
|
}
|
2013-08-23 19:27:19 +08:00
|
|
|
|
2013-12-06 17:56:50 +08:00
|
|
|
; Check the comparison can be reversed if that allows CLGFR to be used.
|
|
|
|
define double @f20(double %a, double %b, i64 %i1, i32 %unext) {
|
2013-08-23 19:27:19 +08:00
|
|
|
; CHECK-LABEL: f20:
|
2013-12-06 17:56:50 +08:00
|
|
|
; CHECK: clgfr %r2, %r3
|
|
|
|
; CHECK-NEXT: jh
|
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i2, %i1
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; ...and again with the AND representation.
|
|
|
|
define double @f21(double %a, double %b, i64 %i1, i64 %unext) {
|
|
|
|
; CHECK-LABEL: f21:
|
|
|
|
; CHECK: clgfr %r2, %r3
|
|
|
|
; CHECK-NEXT: jh
|
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%i2 = and i64 %unext, 4294967295
|
|
|
|
%cond = icmp ult i64 %i2, %i1
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|
|
|
|
|
|
|
|
; Check the comparison can be reversed if that allows CLGF to be used.
|
|
|
|
define double @f22(double %a, double %b, i64 %i2, i32 *%ptr) {
|
|
|
|
; CHECK-LABEL: f22:
|
2013-08-23 19:27:19 +08:00
|
|
|
; CHECK: clgf %r2, 0(%r3)
|
|
|
|
; CHECK-NEXT: jh {{\.L.*}}
|
|
|
|
; CHECK: ldr %f0, %f2
|
|
|
|
; CHECK: br %r14
|
|
|
|
%unext = load i32 *%ptr
|
|
|
|
%i1 = zext i32 %unext to i64
|
|
|
|
%cond = icmp ult i64 %i1, %i2
|
|
|
|
%res = select i1 %cond, double %a, double %b
|
|
|
|
ret double %res
|
|
|
|
}
|