From: terje.mathisen@nospicedham.tmsw.no   
      
   James Harris wrote:   
   > On 07/04/2019 07:24, Rod Pemberton wrote:   
   >> On Thu, 4 Apr 2019 22:35:12 +0100   
   >> James Harris  wrote:   
   >>   
   >>> Anyone know how portably to test an x86 PC's memory?   
   >>   
   >> What do you mean by "portably" here?  Reliable methods?  Multiple   
   >> generations of processors?  Universal software sequence?   
   >> All-of-the-above?   
   >   
   > Certainly they would need to be reliable methods which covered multiple   
   > generations of processors and took account of various types of installed   
   > cache memory.   
   >   
   > As for a 'universal software sequence', depending on what you mean, a   
   > single approach would be ideal but it may be necessary to have the code   
   > select different paths for different hardware. I say that because any   
   > one method may not work on all machines.   
   >   
   > For example, Terje suggested writing four times as much RAM as there is   
   > cache. The problems I have with that are   
   >   
   > * Why 'four' times?   
      
   I wanted to suggest 8 times, since the highest associativity of any   
   cache I have seen was 8, but this is almost certainly not needed as long   
   as you are accessing a memory block which is many times larger than the   
   last level cache.   
      
   > * How to tell how much cache there is on such machines   
      
   CPUID if an x86, and this is after all c.l.a.x86   
   :-)   
      
   Terje   
      
      
   --   
   -    
   "almost all programming can be viewed as an exercise in caching"   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)