[Libre-soc-dev] IIT Roorkee 2021 OpenPOWER Workshop,

[Lauri Kasanen]

On Mon, 19 Jul 2021 17:40:16 -0600
Richard Wilbur <richard.wilbur at gmail.com> wrote:

> > Businesswise a custom memory standard will not fly. Even if you're only
> > making 800Mhz 180nm RAM, it's going to be expensive as hell, limited
> > volume, and made only by you. The market will say "lol no".
>
> I think you are correct.  Since the market will laugh at anyone until they dominate the current leader, my goal is to provide an alternative with equal or superior capability and the freedom of libre licenses.  In that I believe my goals align with those of the libre-soc project.
>
> Regarding cost, is there any reason to believe we would need to use a different process or foundry for the RAM chip?  If the same geometry will suffice, we could very likely make a RAM chip for less than the processor because the package should be cheaper—far fewer pins since we’d be using a serial interface.
>
> The same criticism could be leveled against the processor we are working on but our target audience is not initially the general market.  We are courting first the folks who care about freedom and are willing to pay a premium for what they care about.

The current players use different processes for RAM and logic.

You're not taking size into account. Look at a DDR1 era RAM stick, the
size of the chips. Just one of them is much larger than our processor,
and they had 4-8-16 of them per stick.

I don't understand how libre RAM is any argument; they don't exactly
have firmware. Whatever link training is done is on the cpu's side. How
are you going to sell libre RAM to the audience? "I mean yes it costs
80x what the market sticks do per megabyte, and we're backordered and
you can get some next year, but .."

"It allows the cpu to have 40% faster RAM and be 2% smaller" is not
much use when the baseline RAM speed is low, and the cpu is already
tiny. Requiring expensive RAM would just cause the Rambus fate.

- Lauri