arm "neon"

Torbjorn Granlund tg at gmplib.org
Sat Feb 23 18:26:55 CET 2013


Richard Henderson <rth at twiddle.net> writes:

  On 2013-02-23 06:06, Niels Möller wrote:
  > Not sure what the bottlenecks of your loop are though; instruction
  > decoding, load/store, or the recurrency chain (but at least it shouldn't
  > be multiplier throughput, right?).
  
  Yeah, neither am I.  I can't find any info on what latency of neon
  insns should be.
  
I always found experientation to work best for that, using a tiny loop.

-- 
Torbjörn


More information about the gmp-devel mailing list