Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
![]() |
World Community Grid Forums
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
No member browsing this thread |
Thread Status: Active Total posts in this thread: 11
|
![]() |
Author |
|
Jim1348
Veteran Cruncher USA Joined: Jul 13, 2009 Post Count: 1066 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Ouch. Windows is notoriously inefficient on CEP2 I/O but Linux does much better. Does anybody have any ideas? Maybe on older CPUs, but I run CEP2 on WinXP 32-bit and get 98% efficiency on 7 virtual cores of a Haswell i7-4770. The other core supports two GPUs for GPUGrid. (I know, one of the few Haswell machines running XP, but that is for the GPU work). Another machine gets 99% efficiency on 6 cores of an Ivy Bridge i7-3770, with the other two cores supporting GPUs on Folding, but that is with Win7 64-bit. I don't know if the OS makes the difference, but it is small. However, in all cases I don't try to run it directly off of a disk drive, but use a ramdisk or write cache, so I am operating out of main memory. That, along with the good I/O of these chips, makes the difference. [Edit 1 times, last edit by Jim1348 at Mar 27, 2014 2:07:59 PM] |
||
|
|
![]() |