mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 04:29:57 +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
82 lines
2.8 KiB
LLVM
82 lines
2.8 KiB
LLVM
; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc32 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=PPC32
|
|
; FIXME: -verify-machineinstrs currently fail on ppc64 (mismatched register/instruction).
|
|
; This is already checked for in Atomics-64.ll
|
|
; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc64 | FileCheck %s --check-prefix=CHECK --check-prefix=PPC64
|
|
|
|
; In this file, we check that atomic load/store can make use of the indexed
|
|
; versions of the instructions.
|
|
|
|
; Indexed version of loads
|
|
define i8 @load_x_i8_seq_cst([100000 x i8]* %mem) {
|
|
; CHECK-LABEL: load_x_i8_seq_cst
|
|
; CHECK: sync 0
|
|
; CHECK: lbzx
|
|
; CHECK: sync 1
|
|
%ptr = getelementptr inbounds [100000 x i8], [100000 x i8]* %mem, i64 0, i64 90000
|
|
%val = load atomic i8* %ptr seq_cst, align 1
|
|
ret i8 %val
|
|
}
|
|
define i16 @load_x_i16_acquire([100000 x i16]* %mem) {
|
|
; CHECK-LABEL: load_x_i16_acquire
|
|
; CHECK: lhzx
|
|
; CHECK: sync 1
|
|
%ptr = getelementptr inbounds [100000 x i16], [100000 x i16]* %mem, i64 0, i64 90000
|
|
%val = load atomic i16* %ptr acquire, align 2
|
|
ret i16 %val
|
|
}
|
|
define i32 @load_x_i32_monotonic([100000 x i32]* %mem) {
|
|
; CHECK-LABEL: load_x_i32_monotonic
|
|
; CHECK: lwzx
|
|
; CHECK-NOT: sync
|
|
%ptr = getelementptr inbounds [100000 x i32], [100000 x i32]* %mem, i64 0, i64 90000
|
|
%val = load atomic i32* %ptr monotonic, align 4
|
|
ret i32 %val
|
|
}
|
|
define i64 @load_x_i64_unordered([100000 x i64]* %mem) {
|
|
; CHECK-LABEL: load_x_i64_unordered
|
|
; PPC32: __sync_
|
|
; PPC64-NOT: __sync_
|
|
; PPC64: ldx
|
|
; CHECK-NOT: sync
|
|
%ptr = getelementptr inbounds [100000 x i64], [100000 x i64]* %mem, i64 0, i64 90000
|
|
%val = load atomic i64* %ptr unordered, align 8
|
|
ret i64 %val
|
|
}
|
|
|
|
; Indexed version of stores
|
|
define void @store_x_i8_seq_cst([100000 x i8]* %mem) {
|
|
; CHECK-LABEL: store_x_i8_seq_cst
|
|
; CHECK: sync 0
|
|
; CHECK: stbx
|
|
%ptr = getelementptr inbounds [100000 x i8], [100000 x i8]* %mem, i64 0, i64 90000
|
|
store atomic i8 42, i8* %ptr seq_cst, align 1
|
|
ret void
|
|
}
|
|
define void @store_x_i16_release([100000 x i16]* %mem) {
|
|
; CHECK-LABEL: store_x_i16_release
|
|
; CHECK: sync 1
|
|
; CHECK: sthx
|
|
%ptr = getelementptr inbounds [100000 x i16], [100000 x i16]* %mem, i64 0, i64 90000
|
|
store atomic i16 42, i16* %ptr release, align 2
|
|
ret void
|
|
}
|
|
define void @store_x_i32_monotonic([100000 x i32]* %mem) {
|
|
; CHECK-LABEL: store_x_i32_monotonic
|
|
; CHECK-NOT: sync
|
|
; CHECK: stwx
|
|
%ptr = getelementptr inbounds [100000 x i32], [100000 x i32]* %mem, i64 0, i64 90000
|
|
store atomic i32 42, i32* %ptr monotonic, align 4
|
|
ret void
|
|
}
|
|
define void @store_x_i64_unordered([100000 x i64]* %mem) {
|
|
; CHECK-LABEL: store_x_i64_unordered
|
|
; CHECK-NOT: sync 0
|
|
; CHECK-NOT: sync 1
|
|
; PPC32: __sync_
|
|
; PPC64-NOT: __sync_
|
|
; PPC64: stdx
|
|
%ptr = getelementptr inbounds [100000 x i64], [100000 x i64]* %mem, i64 0, i64 90000
|
|
store atomic i64 42, i64* %ptr unordered, align 8
|
|
ret void
|
|
}
|