 Tzanio Kolev
|
e4c2152419
|
Update Copyright to 2010-2025
|
2025-02-03 12:17:26 -08:00 |
|
|
Will Pazner
|
82b0035ba2
|
Add MultTranspose in batched linear algebra
|
2024-10-29 12:36:00 -07:00 |
|
|
Will Pazner
|
dc13eac9e6
|
Remove include of cublas_v2.h from cpp file
|
2024-08-12 10:32:49 -07:00 |
|
|
Will Pazner
|
f734b1bd92
|
Include gpu_blas.hpp from linalg.hpp
Make GPUBlas class work when compiling without CUDA or HIP; in this case, it has
no effect (and the handle is just nullptr).
|
2024-08-09 11:03:33 -07:00 |
|
|
Will Pazner
|
09d03b715e
|
Support single precision with batched BLAS
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
0ff7174de2
|
Add BatchedLinAlg::AddMult and related functionality
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
82ad111db5
|
Implement GPUBlasBatchedLinAlg::Mult
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
f575e45593
|
Doxygen comments for BatchedLinAlg
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
e5c31240d0
|
Support hipBLAS for batched linear algebra
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
31202eb904
|
Initial GPU BLAS implementation
|
2024-07-08 13:17:08 -07:00 |
|
|
Will Pazner
|
bf79ef7f90
|
Initial framework for batched linear aglebra
|
2024-07-08 13:17:08 -07:00 |
|