[Halld-offline] computing model, alpha release

[Heyes Graham]

This is a good start but we should avoid converting requirements into hardware, such as tape drives or CPUs at this level. The idea is to be implementation neutral and leave that to Chip's group. We (Physics) provide requirements in terms of, for example,  input and output data streams at various data and/or event rates coupled with the CPU seconds per event for whatever processing happens between input and output. Using these rates and times we (Chip's group and I) can calculate the number of CPUs or tape drives depending on the details of implementation. 

	Graham


On Feb 15, 2011, at 2:29 pm, Mark M. Ito wrote:

> On 02/15/2011 02:24 PM, Mark M. Ito wrote:
>> Find attached a spreadsheet that estimates our computing needs.
> 
> One important formatting point I forgot to mention:
> 
> There are only a few input parameters in spreadsheet. They appear in the 
> light blue cells. All other cells are derived from these. The attempt 
> was to be able to change numerical values in one and only one place.
> 
> _______________________________________________
> Halld-offline mailing list
> Halld-offline at jlab.org
> https://mailman.jlab.org/mailman/listinfo/halld-offline