Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
slackito
10 months ago
|
parent
|
context
|
favorite
| on:
LLaMA now goes faster on CPUs
The fact that you're comparing CUDA to using triangles and shaders makes me think you might be confusing OpenCL with OpenGL.
OpenCL is meant for general computation (the C is for "computing") rather than graphics, like CUDA.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
OpenCL is meant for general computation (the C is for "computing") rather than graphics, like CUDA.