[Beowulf] "NNSA’s first really big heterogeneous supercomputer"

Prentice Bisbal pbisbal at pppl.gov
Thu Nov 1 09:45:17 PDT 2018


On 11/01/2018 05:10 AM, Chris Samuel wrote:
> On Thursday, 1 November 2018 4:58:30 AM AEDT Prentice Bisbal via Beowulf wrote:
>
>> I read a publication from LANL on it's architecture years ago, and I believe
>> to had to program for all 3 different processors to take advantage of it's
>> architecture. (If soneone knows for sure, please correct me if I'm wrong.)
>> I'd say that's even more heterogeneous than what we are seeing today
>> (CPU + GPU).
> I think you're bang on the money, here's a presentation from LANL
> about Roadrunner which includes programming on slide 25.
>
> https://www.lanl.gov/conferences/salishan/salishan2007/Roadrunner-Salishan-Ken%20Koch.pdf
>
> All the best,
> Chris
Thanks for this. Slides 25 - 31 are all good slides, but I think slide 
31, titled "Programming a Hybrid Computer"  really hammers the point 
home. Fortunately, it's all text, so I can cut-and-paste it's contents 
here:

Decomposition of an application for Cell-acceleration:
1. Opteron code
     - Runs non-accelerated parts of application
     - Participates in usual cluster parallel computations
     - Controls and communicates with Cell PPC code for the accelerated 
portions
2. Cell PPC code
     - Works with Opteron code on accelerated portions of application
     - Allocates Cell common memory
     - Communicates with Opteron code
     - Controls and works with its 8 SPEs
3. Cell SPE code (8-way parallel)
     - Runs on each SPE (SPMD) (MPMD also possible)
     - Shares Cell common memory with PPC code
     - Manages its Local Store (LS), transferring data blocks in/out as 
necessary
     - Performs vector computations from its LS data

It seems like this would be a nightmare to program for. A few years ago 
I worked with faculty member who did some programming for the Roadrunner 
architecture, and he confirmed this.

--
Prentice




More information about the Beowulf mailing list