Topic: [REMOVED] (Read 1060 times)
There's no reason to force a choice between CPU and GPU and opencl is likely the best choice for scheduling and partitioning the work. A couple CPU cores could be used to pre-initialize the initial work state before being queued for hashing in a GPU command queue. If it's a CPU-only kernel, you can still make use of calls to inline-assembly in the host program for the opencl kernel(s) if you want (and can do better than SSEx optimization). Have fun with it.
Good luck trying to beat cpuminer when you are hindered by an extra abstraction layer and can't use assembly instructions directly 
I agree. Also a GPU will always be faster, unless you have something like a Xeon Phi.
Good luck trying to beat cpuminer when you are hindered by an extra abstraction layer and can't use assembly instructions directly
If I understand Intel correctly it does appear that you can run OpenCL on Intel® Core™ Processors. It might be an interesting project but I wouldn't bet on it beating a GPU, that is unless you had a server farm and a wad of cash for power.
Intel® SDK for OpenCL* Applications 2013
http://software.intel.com/en-us/vcsource/tools/opencl-sdk
Intel® SDK for OpenCL* Applications 2013
http://software.intel.com/en-us/vcsource/tools/opencl-sdk
if i am correct, openCL is extension that only works on gpu, .
cpu dont need that extension because it nativly supports all operations.
if you want gpu to make calculations, then you will eed openCL
so cpu and openCL ? wtf ... nooo
cpu dont need that extension because it nativly supports all operations.
if you want gpu to make calculations, then you will eed openCL
so cpu and openCL ? wtf ... nooo
[REMOVED]
Jump to: