Date: | Sun, 22 Oct 2006 15:45:10 -0500 |
---|---|
From: | "Mike Marty" <mikem@xxxxxxxxxxx> |
Subject: | Re: [Gems-users] Changing processors per chip |
> > But in RubyConfig.h the number of L1 Cache per chip returned by using > following function calls. Isn't it the reverse what you are saying? Am I > missing something? > > static int L1CachePerChipBits() { return procsPerChipBits() ; } // L1s > != processors not currently supported > static int numberOfL1CachePerChip() { return numberOfProcsPerChip(); } > // L1s != processors not currently supported > Yes, that assumes the # of L1s == # of processors. This implies that the # of L1s/chip == # procs/chip. |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | [Gems-users] LogTM and L1 cache simulation, Kevin Moore |
---|---|
Next by Date: | Re: [Gems-users] Changing processors per chip, Philip Garcia |
Previous by Thread: | Re: [Gems-users] Changing processors per chip, Hemayet Hossain |
Next by Thread: | [Gems-users] CPU accesses to L2 cache, Daniele Bordes |
Indexes: | [Date] [Thread] |