I’m investigating a miscompilation bug ( http://llvm.org/bugs/show_bug.cgi?id=19823 ), but I’ve run into a problem: the output of the program is different when I compile the IR with clang compared to opt | llc | clang. Any clues on how to resolve this difference?
$ ./opt -O1 19823.ll | ./llc | ./clang -x assembler - -o a.out ; ./a.out ; echo $?
1
$ ./opt -O2 19823.ll | ./llc | ./clang -x assembler - -o a.out ; ./a.out ; echo $?
1
$ ./clang -O1 19823.ll ; ./a.out ; echo $?
1
$ ./clang -O2 19823.ll ; ./a.out ; echo $?
0 <— that’s bad!
The IR is pretty simple:
@a = common global i16 0, align 2
@c = global i16* @a, align 8
@d = global i8 0, align 1
@b = common global i16 0, align 2
; Function Attrs: nounwind ssp uwtable
define i32 @main() #0 {
entry:
%0 = load i16** @c, align 8, !tbaa !1
%d.promoted = load i8* @d, align 1, !tbaa !5
br label %lbl
lbl: ; preds = %lbl, %entry
%1 = phi i8 [ %dec, %lbl ], [ %d.promoted, %entry ]
%dec = add i8 %1, -1
%conv = sext i8 %1 to i16
store i16 %conv, i16* @b, align 2, !tbaa !6
store i16 1, i16* %0, align 2, !tbaa !6
%tobool = icmp eq i8 %dec, 0
br i1 %tobool, label %if.end, label %lbl
if.end: ; preds = %lbl
store i8 0, i8* @d, align 1, !tbaa !5
%2 = load i16* @a, align 2, !tbaa !6
%conv1 = sext i16 %2 to i32
ret i32 %conv1
}
-- The x86_64 processor models (for Haswell, Sandy Bridge, etc.) do set LoopMicroOpBufferSize and will runtime unroll small loops.