You may never have heard of SiFive before -and that's perfectly understandable. The startup has just been brought from the ground-up following a round of funding, which netted it some $50.6 million dollars in the old, pre-ICO-preferred ways for funding: venture capital. The objective: to offer other startup companies a way to bring their idealized silicon into actual, custom silicon based on the RISC-V architecture, and then work with them towards achieving actual large-scale production.

The company will have available for customers options of IP and pre-baked designs which they can mix and match according to their needs, alongside small-scale production capability for companies to have their actual product - and test it in real-world conditions - before entering large-scale production. This move by SiFive aims to enable a larger variety of task-specific processor designs, ushering in a new, more liberal area of chip design and production.

"The way we view it, is that we think we should not depend on people learning special languages and things of that nature to be able to modify the architecture and enhance the architecture," Naveed Sherwani with SiFive, told TechCrunch. "What we believe is there could be a high-level interface, which is what we're building, which will allow people to take existing cores, bring them into their design space, and then apply a configuration. Moving those configurations, you can modify the core, and then you can get the new modified core. That's the approach we take, we don't have to learn a special language or be an expert, it's the way we present the core. We'd like to start with cores that are verified, and each of these modifications does not cause to become non-verifiable."

The small-scale, block-minded production will allow the company to charge less and less for companies that want to use their design tools, since instead of having to acquire expensive equipment and having to carry the entire cost burden of development until they have actual working silicon (and that can take an inordinate, unmanageable amount of time), SiFive will instead capitalize on having a web-based, easy-access system. "Our vision is that we deliver the entire chip experience to that platform and people can be able to log in. They don't need a team, any tools, they don't need FPGAs because all those will be available on the web. As a result the cost goes down because it's a shared economy, they're sharing tools, and that is how we think dramatically you can do chips at much lower cost."

The market is surely ready for some more ambitious, forward-thinking custom designs, ushering in a whole new slew of workloads and ways of addressing them. The idea of the monolithic, competent-at-many-things chip is getting a bit long in the tooth as computational demands and more specific applications appear; the idea now is to be able to deliver a myriad of specific chips that can be more specialized, filling niches that the giant manufacturing, chip-design behemoths can't.