mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-07 14:33:15 +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
89 lines
2.5 KiB
LLVM
89 lines
2.5 KiB
LLVM
; RUN: opt < %s -O2 -force-vector-interleave=2 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; Loop from "rotated"
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; Loop from "nonrotated"
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; No more loops in the module
|
|
; CHECK-NOT: LV: Loop hints: force=
|
|
; In total only 1 loop should be rotated.
|
|
; CHECK: 1 loop-rotate
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; See http://reviews.llvm.org/D3348 for details.
|
|
|
|
;
|
|
; Test #1
|
|
;
|
|
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost prior to LoopVectorize pass.
|
|
; In past LoopRotate was clearing that metadata.
|
|
;
|
|
; The source C code is:
|
|
; void rotated(float *a, int size)
|
|
; {
|
|
; int t = 0;
|
|
; #pragma omp simd
|
|
; for (int i = 0; i < size; ++i) {
|
|
; a[i] = a[i-5] * a[i+2];
|
|
; ++t;
|
|
; }
|
|
;}
|
|
|
|
define void @rotated(float* nocapture %a, i64 %size) {
|
|
entry:
|
|
%cmp1 = icmp sgt i64 %size, 0
|
|
br i1 %cmp1, label %for.header, label %for.end
|
|
|
|
for.header:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%cmp2 = icmp sgt i64 %indvars.iv, %size
|
|
br i1 %cmp2, label %for.end, label %for.body
|
|
|
|
for.body:
|
|
|
|
%0 = add nsw i64 %indvars.iv, -5
|
|
%arrayidx = getelementptr inbounds float, float* %a, i64 %0
|
|
%1 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
|
|
%2 = add nsw i64 %indvars.iv, 2
|
|
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %2
|
|
%3 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
|
|
%mul = fmul float %1, %3
|
|
%arrayidx4 = getelementptr inbounds float, float* %a, i64 %indvars.iv
|
|
store float %mul, float* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !1
|
|
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
br label %for.header, !llvm.loop !1
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|
|
|
|
;
|
|
; Test #2
|
|
;
|
|
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost even
|
|
; if loop was not rotated (see http://reviews.llvm.org/D3348#comment-4).
|
|
;
|
|
define i32 @nonrotated(i32 %a) {
|
|
entry:
|
|
br label %loop_cond
|
|
loop_cond:
|
|
%indx = phi i32 [ 1, %entry ], [ %inc, %loop_inc ]
|
|
%cmp = icmp ne i32 %indx, %a
|
|
br i1 %cmp, label %return, label %loop_inc
|
|
loop_inc:
|
|
%inc = add i32 %indx, 1
|
|
br label %loop_cond, !llvm.loop !3
|
|
return:
|
|
ret i32 0
|
|
}
|
|
|
|
!3 = !{!3, !4}
|
|
!4 = !{!"llvm.loop.vectorize.enable", i1 true}
|