On our Tiger Lake notebook, the app exits with an error in the CUDA libraries. For example, if we navigated to C:\Program Files (x86)\Geekbench 5\ in PowerShell and then ran this command: Then just run the wrapper from the command line with the application as an argument. The archive we downloaded includes a "wrapper" for any CUDA-enabled application to run it with the bundled CUDA DLL. We grabbed the latest release from the ZLUDA GitHub page and extracted it into Geekbench. Using ZLUDA on Windows seems easy enough.
No luck for us with ZLUDA yet but we'll keep trying. At the present time, only Geekbench is really running, and prospective users are warned to not rely on it for any production-level software just yet. According to the developers, ZLUDA should achieve near-native performance, but its feature set is limited. The newest release supports both Windows and Linux clients with 6th-generation (or higher) Core processors with integrated graphics. The developers behind ZLUDA describe it as a drop-in replacement for CUDA on systems with Intel GPUs from the Skylake family and later. The latest library on the block, however, promises to run CUDA apps directly on Intel GPUs without any modifications. There have been tools to port CUDA apps to widely-supported languages like OpenCL, but even semi-automated tools like HIPCL require developer intervention. Of course, NVIDIA's proprietary CUDA language and API have been exclusive to the company's GPUs since the beginning. Using a graphics processor or GPU for tasks beyond just rendering 3D graphics is how NVIDIA has made billions in the datacenter space.
0 kommentar(er)
