Just need to invoke clMapxx function before you access the host ptr from CPU side, and invoke clUnmapxx function after the CPU access. There is no extra copy inside clMap/Unmapxx if all the conditions are satisfied. You can refer to the code in runtime_use_host_ptr_buffer.cpp under beignet/utests.
From: spring_wind [mailto:[email protected]] Sent: Wednesday, December 03, 2014 10:02 AM To: Guo, Yejun Cc: [email protected] Subject: Re:RE: [Beignet] CL_MEM_USE_HOST_PTR involve extra copy? You mean if I use CL_MEM_USE_HOST_PTR and host ptr is page aligned, I change the data pointed by host ptr from CPU side, I don't have to do any flush opertaion or I should still call clMapxx function? 在 2014-12-03 08:37:15，"Guo, Yejun" <[email protected]<mailto:[email protected]>> 写道： Hi, please check the latest code of beignet, there is no copy needed between CPU and GPU if the host_ptr provided by application is page aligned, and the page align limitation is expected to be removed some days later. You can also try CL_MEM_ALLOC_HOST_PTR to avoid the extra copy without align limitation. Btw, this zero-copy is supported starting from linux kernel 3.16 and libdrm 2.4.58. From: Beignet [mailto:[email protected]<mailto:[email protected]>] On Behalf Of spring_wind Sent: Tuesday, December 02, 2014 8:38 PM To: [email protected]<mailto:[email protected]> Subject: [Beignet] CL_MEM_USE_HOST_PTR involve extra copy? Hi: Intel opencl optimization guide said using CL_MEM_USE_HOST_PTR can avoid extra copy between CPU and GPU, but I noticed that in beignet's implementation source it was not like that: /* Copy the data if required */ if (flags & CL_MEM_COPY_HOST_PTR || flags & CL_MEM_USE_HOST_PTR) cl_buffer_subdata(mem->bo, 0, sz, data); Could someone give me an answer?
_______________________________________________ Beignet mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/beignet
