This is the mail archive of the gcc-help@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: Matrix multiplication: performance drop

From: John Fine <johnsfine at verizon dot net>
To: Yury Serdyuk <Yury at serdyuk dot botik dot ru>
Cc: gcc-help at gcc dot gnu dot org
Date: Tue, 03 Mar 2009 11:44:52 -0500
Subject: Re: Matrix multiplication: performance drop
References: <49AD55E6.50602@serdyuk.botik.ru>

L2 cache is associative. The exact design of that associativity creates a power of two, such that stepping through memory with a step size of that power of two (or a nearby power of two) will cause far more cache misses than a non power of two step size.

Yury Serdyuk wrote:


why an unoptimized code works fine, say, for N = 2100 ,
but doesn't work for N = 2048, or, in general, for N multiply of 512?
What is a magic number ?

References:
- Matrix multiplication: performance drop
  - From: Yury Serdyuk

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]