'how Create program using binary in CUDA?
I had code in OpenCL where I use clCreateProgramWithBinary() to create the program from binary. I am porting this application to CUDA and I don't find any similar function.
Can someone help me with how I can create the program from binary or equivalent of clCreateProgramWithBinary in CUDA?
Solution 1:[1]
AFAIK, the CUDA equivalent of clCreateProgramWithBinary() will be cuModuleLoad (). Please check cuModuleLoad () for precompiled binary. It loads a compute module.
For further reference please check module management in CUDA Driver API API Reference Manual.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | BZKN |