SPHYNX Benchmark List
By Dong-hyeon Park on
16 February 2014
Last Update: 2/18/2014 9:00PM
This blog post will keep a table of all the benchmarks & machine configurations that have been simulated and saved on Charlab machine. Update this table once the benchmark is run & the appropriate output files are moved into the results directory.
The output file of the benchmark will be saved in /data/charlab/gpgpu-sim/RESULTS/ directory.
| Machine | BFS | CP | LIB | LPS | NN | NQU | RAY | STO |
|---|---|---|---|---|---|---|---|---|
| GTX 480 default [4:64:4] | X | X | X | X | X | X | X | X |
| Quadro FX5600 default | X | X | X | X | Error | X | X | X |
| Quadro FX5800 default | ||||||||
| Tesla C2050 default | ||||||||
| _____________________________ | _______ | _______ | _______ | _______ | _______ | _______ | _______ | _______ |
| GTX480 Unified Cluster | X | |||||||
| GTX480 Unified Core [4:64:4] | X | X | X | X | Error | X | X | X |
| GTX480 Unified Core [60:64:4] | X | X | X | X | Error | X | X | X |
| GTX480 Unified Core [32:64:4] | X | X | X | X | Error | X | X | X |
| GTX480 Unified Core [16:64:4] | X | X | X | X | Error | X | X | X |
| GTX480 Unified Core [8:64:4] | X | X | X | X | Error | X | X | X |
| GTX480 Unified Core [2:64:4] | X | X | X | X | Error | X | X | X |
--
The [#:#:#] following each GPU is the per-core L1 Instruction cache configuration. The tag goes as: [ NumSet : BlockSize : Associativity ]
Notes
-
GTX 480 defaultandQuadro FX5600 defaultwere not run with the modified L1 cache print. -
GTX480 Unified Clusteris GTX480 with all the cores moved to a single cluster. -
GTX480 Unified Coreis single-core configuration of GTX480. Its cache size was not changed reflect the increased execution width.
Runtime observations: LIB seems to take an extremely long time to finish (~1hour or more). On the other hand, NQU is very short (~6 second simulation time).