Tom Lin
|
f2f7f3a3de
|
Fix bad dot group initialiser in HIP and CUDA
|
2023-10-07 11:12:08 +01:00 |
|
Tom Lin
|
e347d2ff6c
|
Aggregate initialise numeric types, resolves #134
|
2023-10-07 09:41:18 +01:00 |
|
Tom Lin
|
369785c96a
|
Add HIP managed memory support, resolves #162
|
2023-09-25 01:41:06 +01:00 |
|
Thomas Gibson
|
696ff6a817
|
Round up dot_num_blocks and remove extra check
|
2023-03-13 10:47:37 -05:00 |
|
Thomas Gibson
|
85d80915f6
|
Simplify/roll back unneeded modifications
|
2022-10-10 21:37:54 -05:00 |
|
Thomas Gibson
|
f44cd6fdd2
|
Roll back modifications for copy, mul, add, and triad
|
2022-10-10 21:32:38 -05:00 |
|
Thomas Gibson
|
de93c06e78
|
Add clarifying comment and further clean-up
|
2022-10-10 21:32:21 -05:00 |
|
Thomas Gibson
|
f98aedf64d
|
Use triple-chevron syntax for hip kernel launching
|
2022-10-10 21:32:21 -05:00 |
|
Thomas Gibson
|
bcf8708f2c
|
Clean up kernels and drop unneeded modifications
|
2022-10-10 21:32:21 -05:00 |
|
Thomas Gibson
|
a075455ad4
|
Add tuned benchmark kernels
Co-authored-by: Nick Curtis <arghdos@users.noreply.github.com>
|
2022-10-10 21:32:21 -05:00 |
|
Tom Deakin
|
e77a34158c
|
fix memory limit check for HIP
|
2022-02-16 14:37:58 +00:00 |
|
Tom Lin
|
f5fe55c204
|
[WIP] Drop CL headers and Makefiles
Update README
Move new models to /src
|
2021-11-30 18:22:55 +00:00 |
|
Tom Lin
|
5318404249
|
Use ./src instead of ./cpp
Create subdir for each cpp-based implementation
|
2021-05-26 17:46:07 +01:00 |
|