Re:Nyuzi: open-source processor designed for highly parallel...
by trsohmers on Tuesday January 26, 2016 @09:08PM
(#10977750)
The Knights Corner (2012-2015) Xeon Phi was based on a modified and scaled down version of the Intel P54C core... the same one used in the original 1995 Pentium. On top of that, each core only runs at 1.053 to 1.1GHz. Why would you think that single threaded performance would be any good for an in order superscalar core that is 20 years old?
Re:Nyuzi: open-source processor designed for highly parallel...
by rbanffy on Tuesday January 26, 2016 @10:03PM
(#10977927)
IIRC, it's actually a bit worse: each core could run two threads, but they'd run alternating clock cycles, like the Cell PPUs - unless you have two threads running, each core has half that speed. A normal optimization trick of spreading across as many cores as possible backfires here.
But that was integer performance. Each core also had a beefy SIMD unit, twice as wide as the one in then current Xeons.
I wanted to treat the Xeon Phi like a regular Xeon with just many more cores. So I ran my benchmark mostly unchanged. I was surprised however that the single threaded performance was roughly 20x lower than a normal Xeon. Using all 240 threads I was still doing no better than with 12 cores on a normal Xeon. It seems that the Xeon Phi memory subsystem is not really optimized for multithreaded random access.
The provider of that system suggested that I ought to perform computation and memory access (including prefetching) on the SIMD units (VPUs), but I haven't gotten around to studying the use of VPUs yet...