|
Parallel computing and heterogeneous systems — with mixed types of computational units — are able to break through SMP scaling limits and achieve increased performance with reduced power consumption. However, they also come with their own challenges, and making parallel computing easy to use has been described as “a problem as hard as any that computer science has faced.” With these challenges in mind the Parallella project has set out to help close the knowledge gap by developing an affordable, high performance and truly open parallel computing platform. From Kickstarter to Colossus.
|
|
|
|
|
Pretty cool!
But.... only 1 GB RAM? I'm sure this is more than enough for testing and prototyping, but most tasks I have heard of that could utilise such an immense amount of processing power also tend to need a LOT more than 1 GB to run.
=====
\ | /
\|/
|
|-----|
| |
|_ |
_) | /
_) __/_
_) ____
| /|
| / |
| |
|-----|
|
=====
===
=
|
|
|
|
|
Perhaps in the intended use case, 1 GB *per node* is enough. Just a guess.
Director of Content Development, The Code Project
|
|
|
|
|
But but but... 640K... ? Bill said 640K ...
|
|
|
|
|
16000 Cores on one 10mm chip in 2022?
We already know the answer is 42...
.
|
|
|
|