From: "Bobby D. Bryant" <bdbryant@mail.utexas.edu>
Subject: SIMD w/ MMX or 3dnow!
Date: Thu, 29 May 2003 22:55:17 -0600
Date: 2003-05-29T22:55:17-06:00 [thread overview]
Message-ID: <pan.2003.05.30.04.55.14.186980@mail.utexas.edu> (raw)
Has anyone tried speeding up fp multiplication by calling MMX or 3dnow!
instructions from within an Ada program?
I work with artificial neural networks and much of the signal propagation
can be reduced to instances of multiplying a single fp number times all
the fp numbers in an array and adding the result of each individual
multiplication to a different accumulator variable for each number in the
array. (I.e., an input value is multiplied against a slice of the weight
matrix and the results are added to the values in the hidden layer.)
Any benchmark results and/or example code would be appreciated. Thanks.
--
Bobby Bryant
Austin, Texas
next reply other threads:[~2003-05-30 4:55 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-05-30 4:55 Bobby D. Bryant [this message]
2003-05-30 10:54 ` SIMD w/ MMX or 3dnow! Jeffrey Creem
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox