clCreateBuffer() with CL_MEM_USE_HOST_PTR, visible to gpu and cpu, but implicitly copying data from host to device, reducing performance.
clCreateBuffer() + CL_MEM_ALLOC_HOST_PTR. This allocates memory that both CPU and GPU can use without a copy. visible to both cpu and gpu
For more info, check this thread, http://malideveloper.arm.com/downloads/deved/tutorial/SDK/opencl/memory_buffers_tutorial.html.
About zero-copy examples, check this.
https://software.intel.com/en-us/articles/getting-the-most-from-opencl-12-how-to-increase-performance-by-minimizing-buffer-copies-on-intel-processor-graphics
About zero-copy examples, check this.
https://software.intel.com/en-us/articles/getting-the-most-from-opencl-12-how-to-increase-performance-by-minimizing-buffer-copies-on-intel-processor-graphics
No comments:
Post a Comment