Commit Graph

23 Commits (448533effb31094165464d9a1d3b8a00af1f8743)

Author SHA1 Message Date
gabrielequatrana c08431d71e Merge remote-tracking branch 'origin/cuda-multivect' into psblas-bgmres 10 months ago
gabrielequatrana 4ff0f112a9 SpMM HDIAG working 10 months ago
gabrielequatrana bdd04a6911 Adding support to HDIAG SpMM 10 months ago
gabrielequatrana 0490dd77db ELG SpMM now working 10 months ago
gabrielequatrana dc6e5bb942 ELG SpMM (compiling but not working) 11 months ago
gabrielequatrana 6b8199f84b ELG SpMM (not compiling) 11 months ago
gabrielequatrana 9daa04c3dc Updated HLG SpMM (s,d,c,z) 11 months ago
Salvatore Filippone ccb4f73dca Choose version of HLG-multivect kernel 11 months ago
sfilippone 148a5e5e14 Check for shmemsize 11 months ago
Salvatore Filippone 378c126055 Use MMBSZ=8, prepare to check shmem size 11 months ago
Salvatore Filippone 897cfb4028 Multicolumn HLG product 11 months ago
gabrielequatrana cf315660e1 Updated tests 11 months ago
sfilippone 48455190ec Add GPU version of XYZW 1 year ago
sfilippone a11f328e62 Added CUDA version of XYZW 1 year ago
sfilippone 0e269ed641 typo in Cabgdxyz 1 year ago
Salvatore Filippone 2d3773df98 CUDA kernels for ABGDXYZ 1 year ago
sfilippone 0568a83734 Fix ifdef and old code 1 year ago
Salvatore Filippone 35d68aa4e3 Reuse calls to getDeviceProperties done at init time 1 year ago
Salvatore Filippone 1ba8dfc7b7 Switch FOR and IF in AXPBY 1 year ago
Salvatore Filippone 4681767ef8 New implementation for ABGDXYZ in CUDA 1 year ago
Salvatore Filippone 864872ecac Intermediate implementation of abgdxyz on cuda 1 year ago
Salvatore Filippone a41b209144 Better AXPBY implementation in CUDA. 1 year ago
sfilippone 6aa7987d52 Rename GPU into cuda, and merge SPGPU code. 1 year ago