This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
wg:geodynamo:performance_results [2014/10/27 17:04] hrmatsui |
— (current) | ||
---|---|---|---|
Line 1: | Line 1: | ||
- | These pages show the results of performance tests for different dynamo codes on the [[https://www.tacc.utexas.edu/user-services/user-guides/stampede-user-guide|TACC XSEDE Stampede system]]. | ||
- | To clarify terminology, here are some definitions of terms used in the measurements: | ||
- | * Node: On Stampede, each node contains //2 Xeon E5-2680// processors, each with 8 cores, for a total of 16 cores per node. Each node also has //32GB 8x4G 4 channels DDR3-1600MHz// of memory, | ||
- | * Core: A single core in a processor. | ||
- | * MPI processes: | ||
- | * Thread: An OpenMP thread. Unless otherwise specified processor thread affinity is not enabled. | ||
- | * SU: Service unit, a unit of usage accounting equal to //#cores x #hours//. Usage is billed by the node, so using 8 of 16 cores in a node for 1 hour will be recorded as 16 SUs rather than 8 SUs. | ||
- | |||
- | All timings are measured in terms of wall time unless otherwise specified. They are measured using ''MPI_Wtime()'' (If program does not use MPI, ''system_clock(itime, irate, imax)'' is used). The time for one step is determined by taking the mean of the elapsed time for 100 time steps. | ||
- | |||
- | [[wg:geodynamo:Performance_results:Calypso|Calypso Ver.1.1]] \\ | ||
- | Status: Three cases should be tested again \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:Calypso_Latest|Calypso latest Ver.]] \\ | ||
- | Status: Two cases are missing and three cases should be tested again \\ | ||
- | |||
- | |||
- | [[wg:geodynamo:Performance_results:GeoFEM|GeoFEM-MHD]] \\ | ||
- | Status: Done \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:ETH|ETH code (not finished)]] \\ | ||
- | Status: Having a problem generating initial field. Request is pending to authors. \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:Dennou|SPmodel(GFD-dennou code) (not finished)]] \\ | ||
- | Status: Strong scaling is done. Discussing with authors \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:Goddard|Goddard code]] \\ | ||
- | Status: Routine has been written to generate initial field of multiple resolutions. | ||
- | Tests are underway. | ||
- | Request pending for how to deal with $dt$ adjustment. | ||
- | |||
- | [[wg:geodynamo:Performance_results:H2000|H2000]] \\ | ||
- | Status: Done \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:IPGP|Parody(IPGP JHU code)]] \\ | ||
- | Status: Done \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:LSD|LSD (Leeds code)]] \\ | ||
- | Status: Done \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:MagIC|MagIC (by J. Wicht)]] \\ | ||
- | Status: Done \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:MagIC5|MagIC5 (by J. Wicht)]] \\ | ||
- | Status: Code received, compiled. | ||
- | |||
- | [[wg:geodynamo:Performance_results:SFEMANS|SFEMANS (not finished)]] \\ | ||
- | Status: Strong scaling is done. Discussing with authors for warnings and changing resolutions \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:Busse|simitev-busse-drs]] \\ | ||
- | Status: Strong scaling is done with $l_{max} = 128$. Simulations fail more than $l_{max} = 192$. | ||
- | |||
- | [[wg:geodynamo:Performance_results:Gary|UCSC-Glatzmaier code]] \\ | ||
- | Status: Strong scaling is done. | ||
- | |||
- | [[wg:geodynamo:Performance_results:Gary_Latest|UCSC-Glatzmaier code (New Version)]] \\ | ||
- | Status: Code received. | ||
- | |||
- | [[wg:geodynamo:Performance_results:xshells|xshells]] \\ | ||
- | Status: Done, need to communicate with authors. \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:TITECH|TITECH code (not started)]] \\ | ||
- | |||
- | [[wg:geodynamo:Performance_results:Comp|Comparison among codes]] \\ |