mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-14 11:32:34 +00:00
198d8baafb
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
120 lines
3.3 KiB
LLVM
120 lines
3.3 KiB
LLVM
; Test 64-bit floating-point division.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
|
|
|
|
declare double @foo()
|
|
|
|
; Check register division.
|
|
define double @f1(double %f1, double %f2) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: ddbr %f0, %f2
|
|
; CHECK: br %r14
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check the low end of the DDB range.
|
|
define double @f2(double %f1, double *%ptr) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: ddb %f0, 0(%r2)
|
|
; CHECK: br %r14
|
|
%f2 = load double *%ptr
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check the high end of the aligned DDB range.
|
|
define double @f3(double %f1, double *%base) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: ddb %f0, 4088(%r2)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr double, double *%base, i64 511
|
|
%f2 = load double *%ptr
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check the next doubleword up, which needs separate address logic.
|
|
; Other sequences besides this one would be OK.
|
|
define double @f4(double %f1, double *%base) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: aghi %r2, 4096
|
|
; CHECK: ddb %f0, 0(%r2)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr double, double *%base, i64 512
|
|
%f2 = load double *%ptr
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check negative displacements, which also need separate address logic.
|
|
define double @f5(double %f1, double *%base) {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK: aghi %r2, -8
|
|
; CHECK: ddb %f0, 0(%r2)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr double, double *%base, i64 -1
|
|
%f2 = load double *%ptr
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check that DDB allows indices.
|
|
define double @f6(double %f1, double *%base, i64 %index) {
|
|
; CHECK-LABEL: f6:
|
|
; CHECK: sllg %r1, %r3, 3
|
|
; CHECK: ddb %f0, 800(%r1,%r2)
|
|
; CHECK: br %r14
|
|
%ptr1 = getelementptr double, double *%base, i64 %index
|
|
%ptr2 = getelementptr double, double *%ptr1, i64 100
|
|
%f2 = load double *%ptr2
|
|
%res = fdiv double %f1, %f2
|
|
ret double %res
|
|
}
|
|
|
|
; Check that divisions of spilled values can use DDB rather than DDBR.
|
|
define double @f7(double *%ptr0) {
|
|
; CHECK-LABEL: f7:
|
|
; CHECK: brasl %r14, foo@PLT
|
|
; CHECK: ddb %f0, 160(%r15)
|
|
; CHECK: br %r14
|
|
%ptr1 = getelementptr double, double *%ptr0, i64 2
|
|
%ptr2 = getelementptr double, double *%ptr0, i64 4
|
|
%ptr3 = getelementptr double, double *%ptr0, i64 6
|
|
%ptr4 = getelementptr double, double *%ptr0, i64 8
|
|
%ptr5 = getelementptr double, double *%ptr0, i64 10
|
|
%ptr6 = getelementptr double, double *%ptr0, i64 12
|
|
%ptr7 = getelementptr double, double *%ptr0, i64 14
|
|
%ptr8 = getelementptr double, double *%ptr0, i64 16
|
|
%ptr9 = getelementptr double, double *%ptr0, i64 18
|
|
%ptr10 = getelementptr double, double *%ptr0, i64 20
|
|
|
|
%val0 = load double *%ptr0
|
|
%val1 = load double *%ptr1
|
|
%val2 = load double *%ptr2
|
|
%val3 = load double *%ptr3
|
|
%val4 = load double *%ptr4
|
|
%val5 = load double *%ptr5
|
|
%val6 = load double *%ptr6
|
|
%val7 = load double *%ptr7
|
|
%val8 = load double *%ptr8
|
|
%val9 = load double *%ptr9
|
|
%val10 = load double *%ptr10
|
|
|
|
%ret = call double @foo()
|
|
|
|
%div0 = fdiv double %ret, %val0
|
|
%div1 = fdiv double %div0, %val1
|
|
%div2 = fdiv double %div1, %val2
|
|
%div3 = fdiv double %div2, %val3
|
|
%div4 = fdiv double %div3, %val4
|
|
%div5 = fdiv double %div4, %val5
|
|
%div6 = fdiv double %div5, %val6
|
|
%div7 = fdiv double %div6, %val7
|
|
%div8 = fdiv double %div7, %val8
|
|
%div9 = fdiv double %div8, %val9
|
|
%div10 = fdiv double %div9, %val10
|
|
|
|
ret double %div10
|
|
}
|