Hi folks,
I have a very simple c code as below:
void foo(int* in, int* out)
{
int inArray[4], outArray[4];
int i;
for(i=0; i<4; i++)
{
inArray[i] = in[8*i];
}
outArray[0] = inArray[0] * inArray[1] + inArray[2] + inArray[3] + 0;
outArray[1] = inArray[0] + inArray[1] * inArray[2] + inArray[3] + 1;
outArray[2] = inArray[0] + inArray[1] + inArray[2] * inArray[3] + 2;
outArray[3] = inArray[0] + inArray[1] + inArray[2] + inArray[3] * 3;
for (i=0; i<4; i++)
{
*out++ = outArray[i];
}
}
The llvm IR code with O2 option is generated as:
define void @foo(i32* nocapture readonly %in, i32* nocapture %out) local_unnamed_addr #0 {
entry:
%outArray = alloca [4 x i32], align 16
%0 = bitcast [4 x i32]* %outArray to i8*
call void @llvm.lifetime.start.p0i8(i64 16, i8* nonnull %0) #2
%1 = load i32, i32* %in, align 4, !tbaa !2
%arrayidx.1 = getelementptr inbounds i32, i32* %in, i64 8
%2 = load i32, i32* %arrayidx.1, align 4, !tbaa !2
%arrayidx.2 = getelementptr inbounds i32, i32* %in, i64 16
%3 = load i32, i32* %arrayidx.2, align 4, !tbaa !2
%arrayidx.3 = getelementptr inbounds i32, i32* %in, i64 24
%4 = load i32, i32* %arrayidx.3, align 4, !tbaa !2
%out56 = bitcast i32* %out to i8*
%mul5 = mul nsw i32 %2, %1
%add = add nsw i32 %mul5, %3
%add8 = add nsw i32 %add, %4
%arrayidx10 = getelementptr inbounds [4 x i32], [4 x i32]* %outArray, i64 0, i64 0
store i32 %add8, i32* %arrayidx10, align 16, !tbaa !2
%mul14 = mul nsw i32 %3, %2
%add15 = add i32 %1, 1
%add17 = add i32 %add15, %mul14
%add18 = add i32 %add17, %4
%arrayidx19 = getelementptr inbounds [4 x i32], [4 x i32]* %outArray, i64 0, i64 1
store i32 %add18, i32* %arrayidx19, align 4, !tbaa !2
%add22 = add nsw i32 %2, %1
%mul25 = mul nsw i32 %4, %3
%add26 = add i32 %add22, 2
%add27 = add i32 %add26, %mul25
%arrayidx28 = getelementptr inbounds [4 x i32], [4 x i32]* %outArray, i64 0, i64 2
store i32 %add27, i32* %arrayidx28, align 8, !tbaa !2
%add33 = add nsw i32 %add22, %3
%mul35 = mul nsw i32 %4, 3
%add36 = add nsw i32 %add33, %mul35
%arrayidx37 = getelementptr inbounds [4 x i32], [4 x i32]* %outArray, i64 0, i64 3
store i32 %add36, i32* %arrayidx37, align 4, !tbaa !2
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out56, i8* nonnull %0, i64 16, i32 4, i1 false)
call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull %0) #2
ret void
}
Stack allocation (%outArray = alloca [4 x i32]) is unnecessary and should be optimized for this case. I did some investigation on it and found loop-idiom
pass transformed
for (i=0; i<4; i++)
{
*out++ = outArray[i];
}
to memcpy, which blocked further optimization on local array (outArray).
I am not sure whether it’s a llvm bug. Manually unroll the 2nd loop would bypass this problem, but I prefer to fix it in compiler.
Any suggestion on potential solution to this issue?
Thx,
Wenbo