mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-27 02:31:09 +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
210 lines
7.2 KiB
LLVM
210 lines
7.2 KiB
LLVM
; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s
|
|
|
|
; ScalarEvolution should be able to understand the loop and eliminate the casts.
|
|
|
|
; CHECK: {%d,+,sizeof(i32)}
|
|
|
|
define void @foo(i32* nocapture %d, i32 %n) nounwind {
|
|
entry:
|
|
%0 = icmp sgt i32 %n, 0 ; <i1> [#uses=1]
|
|
br i1 %0, label %bb.nph, label %return
|
|
|
|
bb.nph: ; preds = %entry
|
|
br label %bb
|
|
|
|
bb: ; preds = %bb1, %bb.nph
|
|
%i.02 = phi i32 [ %5, %bb1 ], [ 0, %bb.nph ] ; <i32> [#uses=2]
|
|
%p.01 = phi i8 [ %4, %bb1 ], [ -1, %bb.nph ] ; <i8> [#uses=2]
|
|
%1 = sext i8 %p.01 to i32 ; <i32> [#uses=1]
|
|
%2 = sext i32 %i.02 to i64 ; <i64> [#uses=1]
|
|
%3 = getelementptr i32, i32* %d, i64 %2 ; <i32*> [#uses=1]
|
|
store i32 %1, i32* %3, align 4
|
|
%4 = add i8 %p.01, 1 ; <i8> [#uses=1]
|
|
%5 = add i32 %i.02, 1 ; <i32> [#uses=2]
|
|
br label %bb1
|
|
|
|
bb1: ; preds = %bb
|
|
%6 = icmp slt i32 %5, %n ; <i1> [#uses=1]
|
|
br i1 %6, label %bb, label %bb1.return_crit_edge
|
|
|
|
bb1.return_crit_edge: ; preds = %bb1
|
|
br label %return
|
|
|
|
return: ; preds = %bb1.return_crit_edge, %entry
|
|
ret void
|
|
}
|
|
|
|
; ScalarEvolution should be able to find the maximum tripcount
|
|
; of this multiple-exit loop, and if it doesn't know the exact
|
|
; count, it should say so.
|
|
|
|
; PR7845
|
|
; CHECK: Loop %for.cond: <multiple exits> Unpredictable backedge-taken count.
|
|
; CHECK: Loop %for.cond: max backedge-taken count is 5
|
|
|
|
@.str = private constant [4 x i8] c"%d\0A\00" ; <[4 x i8]*> [#uses=2]
|
|
|
|
define i32 @main() nounwind {
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.inc, %entry
|
|
%g_4.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ] ; <i32> [#uses=5]
|
|
%cmp = icmp slt i32 %g_4.0, 5 ; <i1> [#uses=1]
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%conv = trunc i32 %g_4.0 to i16 ; <i16> [#uses=1]
|
|
%tobool.not = icmp eq i16 %conv, 0 ; <i1> [#uses=1]
|
|
%tobool3 = icmp ne i32 %g_4.0, 0 ; <i1> [#uses=1]
|
|
%or.cond = and i1 %tobool.not, %tobool3 ; <i1> [#uses=1]
|
|
br i1 %or.cond, label %for.end, label %for.inc
|
|
|
|
for.inc: ; preds = %for.body
|
|
%add = add nsw i32 %g_4.0, 1 ; <i32> [#uses=1]
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.body, %for.cond
|
|
%call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 x i8]* @.str, i64 0, i64 0), i32 %g_4.0) nounwind ; <i32> [#uses=0]
|
|
ret i32 0
|
|
}
|
|
|
|
declare i32 @printf(i8*, ...)
|
|
|
|
define void @test(i8* %a, i32 %n) nounwind {
|
|
entry:
|
|
%cmp1 = icmp sgt i32 %n, 0
|
|
br i1 %cmp1, label %for.body.lr.ph, label %for.end
|
|
|
|
for.body.lr.ph: ; preds = %entry
|
|
%tmp = zext i32 %n to i64
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %for.body.lr.ph
|
|
%indvar = phi i64 [ %indvar.next, %for.body ], [ 0, %for.body.lr.ph ]
|
|
%arrayidx = getelementptr i8, i8* %a, i64 %indvar
|
|
store i8 0, i8* %arrayidx, align 1
|
|
%indvar.next = add i64 %indvar, 1
|
|
%exitcond = icmp ne i64 %indvar.next, %tmp
|
|
br i1 %exitcond, label %for.body, label %for.cond.for.end_crit_edge
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
br label %for.end
|
|
|
|
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
|
|
ret void
|
|
}
|
|
|
|
; CHECK: Determining loop execution counts for: @test
|
|
; CHECK-NEXT: backedge-taken count is
|
|
; CHECK-NEXT: max backedge-taken count is -1
|
|
|
|
; PR19799: Indvars miscompile due to an incorrect max backedge taken count from SCEV.
|
|
; CHECK-LABEL: @pr19799
|
|
; CHECK: Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
|
|
; CHECK: Loop %for.body.i: max backedge-taken count is 1
|
|
@a = common global i32 0, align 4
|
|
|
|
define i32 @pr19799() {
|
|
entry:
|
|
store i32 -1, i32* @a, align 4
|
|
br label %for.body.i
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
%tobool.i = icmp eq i32 %storemerge1.i, 0
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
store i32 %add.i.i, i32* @a, align 4
|
|
%cmp.i = icmp slt i32 %storemerge1.i, 0
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
ret i32 0
|
|
}
|
|
|
|
; PR18886: Indvars miscompile due to an incorrect max backedge taken count from SCEV.
|
|
; CHECK-LABEL: @pr18886
|
|
; CHECK: Loop %for.body: <multiple exits> Unpredictable backedge-taken count.
|
|
; CHECK: Loop %for.body: max backedge-taken count is 3
|
|
@aa = global i64 0, align 8
|
|
|
|
define i32 @pr18886() {
|
|
entry:
|
|
store i64 -21, i64* @aa, align 8
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%storemerge1 = phi i64 [ -21, %entry ], [ %add, %for.cond ]
|
|
%tobool = icmp eq i64 %storemerge1, 0
|
|
%add = add nsw i64 %storemerge1, 8
|
|
br i1 %tobool, label %return, label %for.cond
|
|
|
|
for.cond:
|
|
store i64 %add, i64* @aa, align 8
|
|
%cmp = icmp slt i64 %add, 9
|
|
br i1 %cmp, label %for.body, label %return
|
|
|
|
return:
|
|
%retval.0 = phi i32 [ 1, %for.body ], [ 0, %for.cond ]
|
|
ret i32 %retval.0
|
|
}
|
|
|
|
; Here we have a must-exit loop latch that is not computable and a
|
|
; may-exit early exit that can only have one non-exiting iteration
|
|
; before the check is forever skipped.
|
|
;
|
|
; CHECK-LABEL: @cannot_compute_mustexit
|
|
; CHECK: Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
|
|
; CHECK: Loop %for.body.i: Unpredictable max backedge-taken count.
|
|
@b = common global i32 0, align 4
|
|
|
|
define i32 @cannot_compute_mustexit() {
|
|
entry:
|
|
store i32 -1, i32* @a, align 4
|
|
br label %for.body.i
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
%tobool.i = icmp eq i32 %storemerge1.i, 0
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
store i32 %add.i.i, i32* @a, align 4
|
|
%ld = load volatile i32* @b
|
|
%cmp.i = icmp ne i32 %ld, 0
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
ret i32 0
|
|
}
|
|
|
|
; This loop has two must-exits, both of which dominate the latch. The
|
|
; MaxBECount should be the minimum of them.
|
|
;
|
|
; CHECK-LABEL: @two_mustexit
|
|
; CHECK: Loop %for.body.i: <multiple exits> Unpredictable backedge-taken count.
|
|
; CHECK: Loop %for.body.i: max backedge-taken count is 1
|
|
define i32 @two_mustexit() {
|
|
entry:
|
|
store i32 -1, i32* @a, align 4
|
|
br label %for.body.i
|
|
|
|
for.body.i: ; preds = %for.cond.i, %entry
|
|
%storemerge1.i = phi i32 [ -1, %entry ], [ %add.i.i, %for.cond.i ]
|
|
%tobool.i = icmp sgt i32 %storemerge1.i, 0
|
|
%add.i.i = add nsw i32 %storemerge1.i, 2
|
|
br i1 %tobool.i, label %bar.exit, label %for.cond.i
|
|
|
|
for.cond.i: ; preds = %for.body.i
|
|
store i32 %add.i.i, i32* @a, align 4
|
|
%cmp.i = icmp slt i32 %storemerge1.i, 3
|
|
br i1 %cmp.i, label %for.body.i, label %bar.exit
|
|
|
|
bar.exit: ; preds = %for.cond.i, %for.body.i
|
|
ret i32 0
|
|
}
|