[Beowulf] Power calculations , double precision, ECC and power of APU's

Mark Hahn hahn at mcmaster.ca
Fri Mar 22 09:14:58 PDT 2013


> No ECC might be an issue.

Phi definitely has a mode to enable ECC for onboard dram,
similar to how Nvidia and AMD do it (somewhat reduced 
performance and capacity, since the interface is a power
of two bits wide.)  it says here:
http://software.intel.com/en-us/articles/case-study-achieving-superior-performance-on-black-scholes-valuation-computing-using
that Phi has ECC on L2 as well.  (afaik it's fairly common
to do only parity on L1, especially for inclusive caches, 
since corrupted lines can be refetched from the L+1 cache.)

> Public information states approximately 2 SP
> ops per DP op. Sounds like the SIMD registers can do both, like a normal
> x86 chip.

Phi implements standard x86 integer, x87 (!), and the Phi-specific
512b-wide mode.  (I wish they'd just call it MMX512 or something, 
rather than inventing a new, inconsistent name.  MMX, SSE, SSE2, SSE3,
but then SSSE3, then back to SSE4, then AVX and now IMICPHIAVX++ ;)

although I'm excited to get my hands on a Phi, I can't help thinking
about how it seems a little rushed.  not supporting any of the *SSE*
levels, for instance.  I think the big question is whether Intel is 
going to put some impetus behind the product (piplineing multiple 
design teams, doing 2.5d integration, etc).  oddly, the only rumors
I hear about Phi futures are about sticking IB/etc on the board,
which seems like an unimportant detour to me unless it somehow manages
to produce unique levels of performance...

>> A dutch saying is: "whose bread you eat his word you speak"

your bread needs a pinch of salt.  or barrel.

regards, mark hahn.


More information about the Beowulf mailing list