Vectorization is crucial for getting performance out of Phi.
Intel SPMD Program Compiler runs on Phi http://ispc.github.com/
but it's probably not an officially supported product.
On 28 February 2013 03:30, "C. Bergström" wrote:
> Unless I missed something I only see this being wrapped around som
Intel Introduces Cache Acceleration Software
http://newsroom.intel.com/community/intel_newsroom/blog/2013/02/12/introducing-intel-cache-acceleration-software-for-use-with-intel-ssd-data-center-family
It would be interesting to know if anyone had a success with it
especially in the context of para
You nailed it! And not just the code, new codes appear all the time.
bowtie, bwa, soap2, soap3, bowtie2, snap ..
On 9 November 2012 05:32, James Lowey wrote:
> Bingo, the code changes so fast that parallelism is best left to the
> scheduler, for now...
>
>
> James Lowey
> Director, NCS
> TGen
__
help the winner win
http://www.kickstarter.com/projects/adapteva/parallella-a-supercomputer-for-everyone
On 4 October 2012 21:05, Eugen Leitl wrote:
>
> http://www.streamcomputing.eu/blog/2012-08-27/processors-that-can-do-20-gflops-watt/
>
> Processors that can do 20+ GFLOPS/Watt
>
> by Vincent H
Hi Ellis,
if we are to believe the video on the page John pointed to then the
membrane indeed processes both DNA strands. You will probably want to
have a second read anyway in order to improve reliability. We can only
guess what's their signal to noise ratio is.
Igor
> I do wonder however if the
"this thing" does only ~ 1/20 of the genome. you have to pay quite a
bit more for your full genome which makes it comparable (price-wise)
with other technologies. hopefully in a few years time it'll get
cheaper.
stored as characters (1 byte per char) the genome is ~ 3 GB. you could
use two bits to
It is not so much about parallel programming experience but about
scientific software development career path. Quite often parallel
skills are needed anyway. A former colleague and a good friend of mine
explains it quite nicely here:
http://software.ac.uk/blog/2012-04-23-work-scientific-software-e
if memory bandwidth is your concern then there are models which boost
it quite significantly. e.g.
http://ark.intel.com/products/64584/Intel-Xeon-Processor-E5-2660-20M-Cache-2_20-GHz-8_00-GTs-Intel-QPI
probably very few codes are going to benefit from AVX without extra
efforts but BW is a clear win
Gnodal was probably the first to announce a 1U 72 port switch
http://www.gnodal.com/docs/Gnodal%20GS7200%20datasheet.pdf
Other vendors either have announced or will be probably announcing
dense packaging too.
On 12 October 2011 15:52, Chris Dagdigian wrote:
>
> First time I'm seriously pondering
>
http://www.hpcwire.com/blogs/New-China-GPGPU-Super-Outruns-Jaguar-105987389.html
I have been wondering what use if any Tianhe-1 made of Radeon HD 4870 X2. I
had a card like that and it died three times during one year warranty.
Needless to add it perished shortly after the warranty run out. Perh
Hello everyone,
I'm quite curios about the bandwidth to GPUs people are getting especially
with NVIDIA C1060 or Fermi on Intel hosts with two 5520 chipsets. Using
bandwidthTest from CUDA SDK and averaging the results over all cores and
GPUs (we have S1070) I'm getting with memory=pageable 3672 MB
> Not only CUDA and OpenCL, but also DirectX, DirectCompute, C++, and
> Fortran. From a programmer's point of view, it could be a major
> improvement, and the only thing which still kept people from using
> GPUs to run their code.
all of the above but C++ can be used on the current hardware.
CUDA
Dear All,
As you probably already know there will be three extremely interesting
seminars held on the 7th July at Daresbury
- Jack Dongarra, U of Tennessee "Multicore and Hybrid Computing for
Dense Linear Algebra Computations"
- Benoit Raoult, CAPS "HMPP: Leverage Computing Power Simply by Directiv
an answer to my own question on Arista 7148SX latency. or rather an upper
estimate.
there is a mellanox white paper
http://www.mellanox.com/pdf/whitepapers/wp_mellanox_en_Arista.pdf
which reports the "TCP latency using standard test suite" (netperf?) as 7.36
us
(Mellanox ConnectX EN -> Arista 7124S
Hello everyone,
we are embarking on evaluation of 10 GbE for HPC and I was wondering if
someone has already had experience with Arista 7148SX 48 port switch or/and
Netxen cards. General pros and cons would be greatly appreciated and in
particular
- Switch latency (btw, the data sheet says x86 insi
are the slides of this presentation available?
2009/2/9 Dow Hurst DPHURST
> Has anyone tested scaling of NAMD/CUDA over QLogic or ConnectX QDR
> interconnects for a large number of IB cards and GPUs? I've listened to
> John Stone's presentation on VMD and NAMD CUDA acceleration. The consensus
2009/2/4 Eloi Gaudry
> Kilian CAVALOTTI wrote:
>
>> Hi John,
>>
>> On Tuesday 03 February 2009 18:25:04 John Hearns wrote:
>>
>>
>>> http://www.theregister.co.uk/2009/02/03/llnl_buys_ibm_supers/
>>>
>>> I make this 400 cores per 1U rack unit. How is the counting being done
>>> here?
>>>
>>>
>>
>>
the presentation is now available on-line at
http://www.cse.scitech.ac.uk/disco/presentations/BriceGoglin.shtml
> * * CSE SEMINAR * *
>
> You are invited to attend a CSED Seminar taking place on Tuesday 13 January
> 2009 in CR1, A Block at 2pm. The Seminar will be given by Brice Goglan from
> IN
I do not know how big the UK audience of this list is but hopefully a few of
you may find it very interesting.
* * CSE SEMINAR * *
You are invited to attend a CSED Seminar taking place on Tuesday 13 January
2009 in CR1, A Block at 2pm. The Seminar will be given by Brice Goglan from
INRIA, France.
23.55 Mflops/W according to green500 estimates (#488 in thier list)
2008/12/12 Vincent Diepeveen
>
> On Dec 12, 2008, at 8:56 AM, Eugen Leitl wrote:
>
>
>> http://www.goodgearguide.com.au/article/270416/inside_tsubame_-
>> _nvidia_gpu_supercomputer?fp=&fpid=&pf=1
>>
>> Inside Tsubame - the Nvidi
>
> Did you really hold the Nehalem Xeon chips in your hands? They probably
> require new motherboards with a new chipset.
>
absolutely
> It would be nice to hear from you some numbers concerning Harpertown vs
> Nehalem performance
>
those who know will not be able tell you because of the NDA.
i
lol the guy surely is very ambitious - 4 PFLOPS for $0.9M
http://helmer3.sfe.se/
2008/10/5 Eugen Leitl <[EMAIL PROTECTED]>
>
> A Linux cluster built in a Helmer IKEA cabinet:
>
> http://helmer.sfe.se/
>
___
Beowulf mailing list, Beowulf@beowulf.org
T
22 matches
Mail list logo
