search for: den0018a

Viswanath Puttagunta wrote: > I responded to your feedback before I started on RFCv3.. and took your > silence as approval :).. I guess that email got lost in your inbox sea > some where.. so re-posting the responses. Sorry, I did see it but I guess I read it rather more quickly than I thought. Apologies for that. > guidance. I wouldn't know where else to put this. Without

...ault) -O2 is identical. However, if > someone actually wants to make an unoptimized build for some reason > (e.g., testing or debugging), you've broken that. Thanks. After re-referring to the NEON Programmer's guide carefully http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.den0018a/index.html the appropriate flag should have been "-ftree-vectorize". I can also confirm that -O2 and -O3 produces almost same output. What I was comparing when I meant "painful" is when I don't use any optimization level.. which I tried during unit testing. But it looks lik...

Viswanath Puttagunta wrote: > + SUMM = vdupq_n_f32(0); It kills me that there's no intrinsic for VMOV.F32 d0, #0 (or at least I couldn't find one), so this takes two instructions instead of one. > + /* Consume 4 elements in x vector and 8 elements in y > + * vector. However, the 8'th element in y never really gets > + * touched in this loop. So, if len == 4,