This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
cluster:91 [2010/12/28 18:50] hmeij |
cluster:91 [2011/01/07 20:49] (current) hmeij |
||
---|---|---|---|
Line 142: | Line 142: | ||
* NB: start with 64, then 128, try 192 ... | * NB: start with 64, then 128, try 192 ... | ||
* PxQ: perfect square of 10x16=160, the number of cores we have | * PxQ: perfect square of 10x16=160, the number of cores we have | ||
- | * | + | |
+ | < | ||
+ | ============================================================================ | ||
+ | T/V N NB | ||
+ | ---------------------------------------------------------------------------- | ||
+ | WR00L2L2 | ||
+ | ---------------------------------------------------------------------------- | ||
+ | ||Ax-b||_oo / ( eps * ||A||_1 | ||
+ | ||Ax-b||_oo / ( eps * ||A||_1 | ||
+ | ||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) = 0.0020883 ...... PASSED | ||
+ | ============================================================================ | ||
+ | </ | ||
+ | |||
* INFINIBAND | * INFINIBAND | ||
* N calculation: | * N calculation: | ||
* NB: start with 64, then 128, try 192 ... | * NB: start with 64, then 128, try 192 ... | ||
* PxQ: perfect square of 10x16=160, the number of cores we have | * PxQ: perfect square of 10x16=160, the number of cores we have | ||
+ | |||
+ | < | ||
+ | ============================================================================ | ||
+ | T/V N NB | ||
+ | ---------------------------------------------------------------------------- | ||
+ | WR00L2L2 | ||
+ | ---------------------------------------------------------------------------- | ||
+ | ||Ax-b||_oo / ( eps * ||A||_1 | ||
+ | ||Ax-b||_oo / ( eps * ||A||_1 | ||
+ | ||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) = 0.0024480 ...... PASSED | ||
+ | ============================================================================ | ||
+ | </ | ||
+ | |||
+ | So a total of 2.455e+02 + 3.264e+0 or about 572 Gflops, 0.5 teraflops. | ||
Line 157: | Line 184: | ||
* NB: start with 64, then 128, try 192 ... | * NB: start with 64, then 128, try 192 ... | ||
* PxQ: perfect square of 9x10=92, close to the number of cores we have. | * PxQ: perfect square of 9x10=92, close to the number of cores we have. | ||
+ | |||
+ | |||
+ | Hmm, unable to make this work across all the nodes at the same time. Not sure why. My estimates are that with 92 cores and 1,126 gb of memory this cluster should be able to do 500-700 Gflops. | ||