[PATCH] D10950: [SLPVectorizer] Try different vectorization factors and set max vector register size based on target
Sanjay Patel
spatel at rotateright.com
Tue Jul 7 18:01:24 PDT 2015
In http://reviews.llvm.org/D10950#200724, @mzolotukhin wrote:
> I think this patch is good to commit as-is, though I have one question (I'm ok with just adding TODO for now).
Thanks, Michael!
You're right; we need to increase that limit to vectorize more than 16 elements at a time. I'll make that a TODO and then add another cl::opt override, so we can experiment with that setting. This raises another problem: AVX has 256-bit registers, but it can't handle <32 x i8> ops, so creating those here would be useless. Using the data type rather than the register size could get us more optimizations while limiting the compile-time explosion.
http://reviews.llvm.org/D10950
More information about the llvm-commits
mailing list