Comments on: Intel readies massive multicore processors
Researchers work to mask intricate functionality of up-to-80-core chips, so hardware and software makers can more easily adapt to them. ![]()
Researchers work to mask intricate functionality of up-to-80-core chips, so hardware and software makers can more easily adapt to them. ![]()
January 5, 2010 7:48 PM PST
January 5, 2010 6:00 PM PST
January 5, 2010 5:27 PM PST
Add headlines from CNET News to your homepage or feedreader.
More feeds available in our RSS feed index.
Related quotes
Pro towers and blades?
home use? This is overkill.
Hamlet to Horatio.
Sure Office (today) doesn't need 16 cores, how about video editing, compression, and transcoding, interactive photo editing, voice recognition, photo realistic rendering, synthetic vision (interesting home applications like photo-3D model, or home security)
Everytime the processing power rachets up, we find ways to use it. When it goes up by factors of 100, we find entirely new usage models (c.f. the overused "paradigm" word)
one to partition core usage to be user defined. It
is not far-fetched to imagine uses of Supercomputing to come to normal day-to-day usage.
I see the requirement to pop-up within 3-5 years.
Intel's R&D has done the job but I don't expect
them to imagine the applications.
huge amounts of memory
error correcting memory
memory access that can keep up with the CPU
really huge amounts of data storage (e.g., hard drive)
fast access to that data storage
operating system that can control all this
software that can make use of all this
Here's an e-Book on multicore programming. Covers programming approaches including OpenMP, Intel's TBB, Pthreads, Cilk++, MPI.
http://www.cilk.com/multicore-e-book
- by ilya_cilk August 18, 2008 12:33 PM PDT
- With the arrival of these CPUs, multicore programming will be a competitive imperative for software developers within 12-18 months.
- Like this Reply to this comment
-
(13 Comments)Here's an e-Book on multicore programming. Covers programming approaches including OpenMP, Intel's TBB, Pthreads, Cilk++, MPI.
http://www.cilk.com/multicore-e-book