Comparison With CUDA
| The neutrality of this section is disputed. Please do not remove this message until the dispute is resolved. |
Two comparisons have been drawn between CUDA and OpenCL since its inception, and both arrived at the same conclusion: if the OpenCL implementation is correctly tweaked to suit the target architecture, it performs no worse than CUDA. Because the key feature of OpenCL is portability (via its abstracted memory and execution model), the programmer is not able to directly use GPU-specific technologies (such as inline PTX) unless they are willing to give up direct portability. CUDA is more directly connected to the platform upon which it will be executing because it is limited to Nvidia hardware. Compiler technology for both standards supported by Nvidia's toolkit is based upon LLVM and compiles to Nvidia's PTX instruction set abstraction.
Read more about this topic: Open CL
Famous quotes containing the words comparison with and/or comparison:
“I have travelled a good deal in Concord; and everywhere, in shops, and offices, and fields, the inhabitants have appeared to me to be doing penance in a thousand remarkable ways.... The twelve labors of Hercules were trifling in comparison with those which my neighbors have undertaken; for they were only twelve, and had an end; but I could never see that these men slew or captured any monster or finished any labor.”
—Henry David Thoreau (1817–1862)
“It is very important not to become hard. The artist must always have one skin too few in comparison to other people, so you feel the slightest wind.”
—Shusha Guppy (b. 1938)