Applied-Software/ZLUDA
5
0
Fork 0
mirror of https://github.com/vosen/ZLUDA.git synced 2025-04-20 00:19:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update README

Browse Source
This commit is contained in:
Andrzej Janik
2024-12-23 17:19:38 +01:00
parent f533cfe03f
commit e43eb99902
3 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
GeekBench_5_2_3.svg
View File

File diff suppressed because one or more lines are too long
Side by Side

Before

Width:  |  Height:  |  Size: 259 KiB

17
README.md
View File

@ -4,6 +4,8 @@
ZLUDA is a drop-in replacement for CUDA on non-NVIDIA GPU. ZLUDA allows to run unmodified CUDA applications using non-NVIDIA GPUs with near-native performance. ZLUDA is a drop-in replacement for CUDA on non-NVIDIA GPU. ZLUDA allows to run unmodified CUDA applications using non-NVIDIA GPUs with near-native performance.
![GeekBench 5.5.1 chart](geekbench.svg)
ZLUDA is work in progress. Follow development here and say hi on [Discord](https://discord.gg/sg6BNzXuc7). For more details see the announcement: https://vosen.github.io/ZLUDA/blog/zludas-third-life/ ZLUDA is work in progress. Follow development here and say hi on [Discord](https://discord.gg/sg6BNzXuc7). For more details see the announcement: https://vosen.github.io/ZLUDA/blog/zludas-third-life/
## Usage ## Usage
@ -12,8 +14,8 @@ ZLUDA is work in progress. Follow development here and say hi on [Discord](https
### Windows ### Windows
You should have recent AMD GPU driver ("AMD Software: Adrenalin Edition") installed.\ You should have recent AMD GPU driver ("AMD Software: Adrenalin Edition") installed.\
To run your application you should etiher: To run your application you should etiher:
* (Recommended approach) Copy ZLUDA-provided `nvcuda.dll` and `nvml.dll` into a path which your application uses to load CUDA. Paths vary application to application, but usually it's the directory where the .exe file is located * (Recommended approach) Copy ZLUDA-provided `nvcuda.dll` and `nvml.dll` from `target\release` (if built from sources) or `zluda` (if downloaded a zip package) into a path which your application uses to load CUDA. Paths vary application to application, but usually it's the directory where the .exe file is located
* Use ZLUDA launcher like below. ZLUDA launcher is known to be buggy and unfinished * Use ZLUDA launcher like below. ZLUDA launcher is known to be buggy and incomplete:
``` ```
<ZLUDA_DIRECTORY>\zluda_with.exe -- <APPLICATION> <APPLICATIONS_ARGUMENTS> <ZLUDA_DIRECTORY>\zluda_with.exe -- <APPLICATION> <APPLICATIONS_ARGUMENTS>
``` ```
@ -25,7 +27,7 @@ Run your application like this:
LD_LIBRARY_PATH=<ZLUDA_DIRECTORY> <APPLICATION> <APPLICATIONS_ARGUMENTS> LD_LIBRARY_PATH=<ZLUDA_DIRECTORY> <APPLICATION> <APPLICATIONS_ARGUMENTS>
``` ```
where `<ZLUDA_DIRECTORY>` is the directory which contains ZLUDA-provided `libcuda.so`: `target\release` if you built from sources or `zluda` if you downloaded prebuilt package. where `<ZLUDA_DIRECTORY>` is the directory which contains ZLUDA-provided `libcuda.so`: `target/release` if you built from sources or `zluda` if you downloaded prebuilt package.
### MacOS ### MacOS
@ -54,9 +56,10 @@ Not supported
If you are building on Linux you must also symlink the ZLUDA output binaries after ZLUDA build finishes: If you are building on Linux you must also symlink the ZLUDA output binaries after ZLUDA build finishes:
``` ```
cd target/release cd target/release
ln -s libnvcuda.so target/release/libcuda.so ln -s libnvcuda.so libcuda.so
ln -s libnvcuda.so target/release/libcuda.so.1 ln -s libnvcuda.so libcuda.so.1
ln -s libnvml.so target/release/libnvidia-ml.so ln -s libnvml.so libnvidia-ml.so
ln -s libnvml.so libnvidia-ml.so.1
``` ```
## Contributing ## Contributing
@ -70,7 +73,7 @@ If you want to contribute a code fix or documentation update feel free to open a
There's no architecture document (yet). Two most important crates in ZLUDA are `ptx` (PTX compiler) and `zluda` (AMD GPU runtime). A good starting point to tinkering the project is to run one of the `ptx` unit tests under a debugger and understand what it is doing. `cargo test -p ptx -- ::add_hip` is a simple test that adds two numbers. There's no architecture document (yet). Two most important crates in ZLUDA are `ptx` (PTX compiler) and `zluda` (AMD GPU runtime). A good starting point to tinkering the project is to run one of the `ptx` unit tests under a debugger and understand what it is doing. `cargo test -p ptx -- ::add_hip` is a simple test that adds two numbers.
Github issues tagged with ["help wanted"](https://github.com/vosen/ZLUDA/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22) are tasks that are self-containted. Their level of difficulty varies, they are not always great starting points, but they have a relatively clear definition of "done". Github issues tagged with ["help wanted"](https://github.com/vosen/ZLUDA/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22) are tasks that are self-containted. Their level of difficulty varies, they are not always good beginner tasks, but they defined unambiguously.
If you have questions feel free to ask on [#devtalk channel on Discord](https://discord.com/channels/1273316903783497778/1303329281409159270). If you have questions feel free to ask on [#devtalk channel on Discord](https://discord.com/channels/1273316903783497778/1303329281409159270).

1
geekbench.svg Normal file
View File

File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 287 KiB