Attila Afra
|
6431f3e7c6
|
added Heap, Arena and ArenaPlanner, removed MetalGraph, refactoring
|
2023-11-11 23:38:04 +02:00 |
|
Attila Afra
|
73deab0e7a
|
updated copyright year
|
2023-05-15 20:09:34 +03:00 |
|
Attila Afra
|
497d5b9131
|
added support for arbitrary channel padding
|
2023-03-06 22:42:10 +02:00 |
|
Attila Afra
|
b4fea90f3d
|
avoid symbol collision when using OIDN_API_NAMESPACE
|
2023-02-13 15:35:16 +02:00 |
|
Attila Afra
|
9983abdcd8
|
replaced cuDNN with CUTLASS
|
2022-05-05 16:34:33 +03:00 |
|
Attila Afra
|
3c0850f420
|
improved scratch memory management, cleanups, bumped version to 2.0
|
2022-03-12 15:30:05 +02:00 |
|
Attila Afra
|
b4e4b59c45
|
major refactoring
|
2022-01-06 23:11:27 +02:00 |
|
Attila Afra
|
f4010b10dd
|
tensor and image accessor improvements and cleanups
|
2021-12-12 01:23:27 +02:00 |
|
Attila Afra
|
068594ab38
|
minor TensorAccessor refactoring
|
2021-12-10 02:10:38 +02:00 |
|
Attila Afra
|
b8d83938f4
|
TensorAccessor cleanup
|
2021-12-09 02:45:45 +02:00 |
|
Attila Afra
|
09e5170d83
|
renamed OIDN_DEVICE_GPU to OIDN_DEVICE_SYCL
|
2021-11-26 03:22:01 +02:00 |
|
Attila Afra
|
8ec06a997b
|
optimized SYCL upsample and pool kernels
|
2021-08-02 14:42:12 +03:00 |
|
Attila Afra
|
c1b52b4bc4
|
experimental SYCL upsample kernel optimization
|
2021-08-02 01:38:12 +03:00 |
|
Attila Afra
|
0a83695547
|
much faster SYCL upsample kernel
|
2021-08-02 01:06:41 +03:00 |
|
Attila Afra
|
cd6984ca93
|
optimized SYCL upsample kernel
|
2021-07-28 00:56:42 +03:00 |
|
Attila Afra
|
8b41a0c88d
|
added support for FP16 image formats
|
2021-07-26 21:14:57 +03:00 |
|
Attila Afra
|
86d5d9bedb
|
use FP16 for most of the GPU computations
|
2021-07-15 02:07:27 +03:00 |
|
Attila Afra
|
aabd89737c
|
added name for nodes, other minor updates
|
2021-07-12 15:01:21 +03:00 |
|
Attila Afra
|
2ccc9f448b
|
initial SYCL kernels
|
2021-07-09 20:30:15 +03:00 |
|
Attila Afra
|
7a324f1a70
|
added placeholder SYCL nodes
|
2021-07-08 19:00:52 +03:00 |
|