Changes between Version 9 and Version 10 of Fastest_GEMM_implementation_On_Cypress
- Timestamp:
- Oct 11, 2010 8:11:14 AM (14 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Fastest_GEMM_implementation_On_Cypress
v9 v10 8 8 == abstract == 9 9 We present benchmark results of optimized dense matrix multiplication 10 kernels for Cypress GPU. We write general matrix multiply (GEMM) kernels10 kernels for a Cypress GPU. We write general matrix multiply (GEMM) kernels 11 11 for single (SP), double (DP) and double-double (DDP) precision. 12 12 Our SGEMM and DGEMM kernels show 73% and 87% of … … 33 33 34 34 http://github.com/dadeba/cypress_dgemm/ 35