Re: IBM "Cell" processor
Dave Leimbach wrote:
> I think this "cell" technology is somewhat related to PCA project:
>
> http://www.morphware.org. Being able to dynamically reconfigure the "cpu"
> for different applications. I think this means you need to think of the
> processing unit in a new light and that cell is directly related to this.
>
> Also the performance numbers you probably see from it are most likely
> highly dependent on locality of reference which means "streaming" applications.
>
Is it true that this form of interprocessor communication is, in some
ways, similar to Java's RMI? We will have a long time to read the
morphware papers because according to the URL below, workstations are at
least one year, maybe 18 months, away.
http://www.theregister.co.uk/2004/11/29/ps3_to_ship_2006
This chip will be in the IBM Power Architecture family so, if someone
were determined to get a head-start on porting DF to the Cell, they
could probably make significant inroads by simply porting to a current
64 bit PowerPC platform. There has been a lot of Intel-groaning on the
commit list in the last few months.
討論串 (同標題文章)
完整討論串 (本文為第 6 之 6 篇)：