Linked by Thom Holwerda on Fri 19th Mar 2010 13:00 UTC, submitted by Jim Lynch
Thread beginning with comment 414244
To read all comments associated with this story, please click here.
To read all comments associated with this story, please click here.
GPUs are specialized for doing parallel arithmetic operations. Specifically, a GPU can perform a vector sum in one cycle, whereas the CPU would require more cycles. The problem with your suggestion is that the kernel doesn't spend most of its time doing vector sums, but instead things like interrupt handling and context switching.
RE[2]: Comment by twitterfire
by twitterfire on Fri 19th Mar 2010 23:36
in reply to "RE: Comment by twitterfire"





Member since:
2008-09-11
I would like OS kernels to make use of GPU computation power. Modern GPUs are providing high parallel computation power and all that computation power is unused beside 3d applications.