Seunghoon Lee
|
86cdab3b14
|
Follow-up changes of #27 (#32)
* Update README.
* Drop dead codes.
* Use addr_of.
* Update Dockerfiles.
* Disable warnings for nvrtc.
* nvrtc.
|
2024-07-14 16:37:39 +09:00 |
|
|
Seunghoon Lee
|
d7714d84c0
|
Add support of ROCm 6. (#27)
* Add support of ROCm 6.1.2 for Windows.
* Fix CI.
* Use llvm.sqrt.f64.
|
2024-07-13 13:47:35 +09:00 |
|
|
Seunghoon Lee
|
d23b3f4636
|
Drop cudart.
|
2024-07-11 14:52:36 +09:00 |
|
|
Seunghoon Lee
|
53b51ddd55
|
Revert "Fix CI."
This reverts commit 0e558cc0ae.
|
2024-07-11 11:08:38 +09:00 |
|
|
Seunghoon Lee
|
0e558cc0ae
|
Fix CI.
|
2024-07-11 11:07:13 +09:00 |
|
|
Seunghoon Lee
|
4d5838ecec
|
Merge remote-tracking branch 'upstream/master'
|
2024-07-10 17:14:47 +09:00 |
|
Andrzej Janik
|
9e56862ebb
|
Update README with CGBN information (#237)
|
2024-05-23 13:28:17 +02:00 |
|
|
Seunghoon Lee
|
2ad9ad6851
|
[Fix] Clean up Runtime API.
|
2024-05-21 10:49:19 +09:00 |
|
|
Seunghoon Lee
|
11cc584451
|
Implement cuda runtime api. (cudart) (#17)
* [WIP] Implement cudart.
* wip
* wip
* Implement cudart.
* wip
* Ready to merge.
|
2024-05-17 13:15:16 +09:00 |
|
|
Seunghoon Lee
|
95f881004f
|
[CI] Rename CI jobs.
|
2024-05-17 13:08:52 +09:00 |
|
|
Seunghoon Lee
|
4f12e8cfe9
|
Merge remote-tracking branch 'upstream/master'
|
2024-05-17 12:44:07 +09:00 |
|
|
Seunghoon Lee
|
6fe6b7f843
|
[CI] Add CI for PR.
|
2024-05-17 12:34:31 +09:00 |
|
|
Andrzej Janik
|
2d8c47f147
|
Support Meshroom (#153)
|
2024-05-17 00:35:38 +02:00 |
|
NyanCatTW1
|
fcd7a57888
|
Fix + improve vprintf implementation (#211)
|
2024-05-16 00:38:52 +02:00 |
|
|
Andrzej Janik
|
f0c905db15
|
Fix trap instruction codegen, don't fail build with older Rust versions (#229)
|
2024-05-08 15:19:59 +02:00 |
|
|
Andrzej Janik
|
27c0e13677
|
Minor codegen improvements (#225)
|
2024-05-06 00:28:49 +02:00 |
|
|
Seunghoon Lee
|
7538ae61c6
|
Remove zluda_dnn remains.
|
2024-04-29 22:56:19 +09:00 |
|
|
Seunghoon Lee
|
2804604c29
|
Merge remote-tracking branch 'upstream/master'
|
2024-04-29 22:32:59 +09:00 |
|
|
Andrzej Janik
|
bdc652f9eb
|
Correctly report emulated wave32 CUDA device (#216)
|
2024-04-29 15:09:14 +02:00 |
|
|
Seunghoon Lee
|
cb5fb0e633
|
[CI] Revise Windows HIP SDK dependency.
|
2024-04-28 14:39:42 +09:00 |
|
|
Seunghoon Lee
|
17af40c848
|
[CI] Add needs.
|
2024-04-28 13:53:26 +09:00 |
|
|
Seunghoon Lee
|
c2710a88f1
|
Merge remote-tracking branch 'upstream/master'
|
2024-04-28 13:00:19 +09:00 |
|
|
Andrzej Janik
|
995bc95174
|
Build improvements (#206)
* Allow to create .zip package on Windows
* Allow to create .tar.gz package on Linux
* Add configuration for post-build Github CI
|
2024-04-28 01:22:43 +02:00 |
|
|
Seunghoon Lee
|
b9e932b9c8
|
Rewrite nvrtcVersion.
|
2024-04-21 00:32:58 +09:00 |
|
|
Seunghoon Lee
|
cf262c6889
|
Implement nvmlDeviceGetCudaComputeCapability.
|
2024-04-21 00:31:57 +09:00 |
|
|
Seunghoon Lee
|
12c2da499f
|
Merge remote-tracking branch 'upstream/master'
|
2024-04-21 00:08:33 +09:00 |
|
|
Andrzej Janik
|
5d5f7cca75
|
Rewrite surface implementation to more accurately support unofficial CUDA semantics (#203)
This fixes black screen in some CompuBench tests (TV-L1 Optical Flow) and other apps that use CUDA surfaces incorrectly
|
2024-04-14 02:39:34 +02:00 |
|
|
Seunghoon Lee
|
4baac34d4e
|
Implement cublasDotEx.
|
2024-04-10 15:20:58 +09:00 |
|
|
Seunghoon Lee
|
9e97c717c3
|
Disable DNN build on Windows.
|
2024-04-06 13:51:46 +09:00 |
|
|
Seunghoon Lee
|
fcf2654050
|
Merge remote-tracking branch 'upstream/master'
|
2024-04-06 13:40:31 +09:00 |
|
|
Andrzej Janik
|
774f4bcb37
|
Implement sad instruction (#198)
|
2024-04-06 01:23:53 +02:00 |
|
|
Andrzej Janik
|
0d9ace2475
|
Fix buggy carry flags when mixing subc/sub.cc with addc/add.cc (#197)
|
2024-04-05 23:26:08 +02:00 |
|
|
NyanCatTW1
|
76bae5f91b
|
Implement mad.hi.cc (#196)
|
2024-04-05 19:12:59 +02:00 |
|
|
Andrzej Janik
|
b695f44c18
|
Support old PTX compression scheme (#188)
|
2024-03-29 02:03:23 +01:00 |
|
|
Andrzej Janik
|
7d4147c8b2
|
Add Blender 4.2 support (#184)
Redo primary context and fix various long-standing bugs around this API
|
2024-03-28 17:12:10 +01:00 |
|
|
Seunghoon Lee
|
0f191c2354
|
Fix type errors.
|
2024-03-25 14:09:02 +09:00 |
|
|
Seunghoon Lee
|
1122cc0e83
|
Implement cublasSdot.
|
2024-03-25 11:30:23 +09:00 |
|
|
Seunghoon Lee
|
7c3891e6b3
|
Fix cusparseDnMatGet.
|
2024-03-21 22:07:36 +09:00 |
|
|
Seunghoon Lee
|
ff1bc6d9b6
|
Fix nvrtcGetErrorString.
|
2024-03-21 22:06:42 +09:00 |
|
|
Seunghoon Lee
|
87d2e3e163
|
Add match order fallback.
|
2024-03-20 14:59:10 +09:00 |
|
|
Seunghoon Lee
|
2b52d0a040
|
Fix typo.
|
2024-03-20 14:38:49 +09:00 |
|
|
Seunghoon Lee
|
6b2488395d
|
Implement cusparseCreateDnMat, cusparseDestroyDnMat, cusparseDnMat*.
|
2024-03-20 14:12:00 +09:00 |
|
|
Seunghoon Lee
|
2812b1db44
|
Include zluda.exe in Windows release.
|
2024-03-20 11:22:57 +09:00 |
|
|
Seunghoon Lee
|
4fe7c2b1d4
|
Merge remote-tracking branch 'upstream/master'
|
2024-03-20 11:21:42 +09:00 |
|
|
Seunghoon Lee
|
4fab2af0f4
|
Implement cusparseXcoo2csr.
|
2024-03-20 10:30:31 +09:00 |
|
|
Seunghoon Lee
|
f52edbd132
|
Implement cusparseXcoo2csr.
|
2024-03-20 10:29:09 +09:00 |
|
|
Seunghoon Lee
|
cd1e0a3d50
|
Implement cublasDgetrsBatched.
|
2024-03-18 22:38:57 +09:00 |
|
|
Andrzej Janik
|
1ede61c696
|
Disable even more optional LLVM components (#179)
|
2024-03-17 14:53:15 +01:00 |
|
|
Seunghoon Lee
|
605254b38e
|
fix upload_url
|
2024-03-17 18:39:24 +09:00 |
|
|
Seunghoon Lee
|
65dbb30d2e
|
job deps
|
2024-03-17 18:09:08 +09:00 |
|