[FOSSi Dial-Up] Tim Ansell - Skywater PDK: Fully open source manufacturable PDK for a 130nm process

Google wants to create an open, innovative ecosystem for silicon so it will be easier for them to build accelerators for their workloads to meet the growing demand for compute. TPU is only one example of the kind of accelerators they want to build. Tim directly addresses this in the talk: [VIDEO] .

Google, FOSSi and eFabless are working on a 100% open source chip design workflow that would allow you to use only open source tools to create a chip, and thanks to other efforts open source chips and ISA exist already: See: [VIDEO]

It was talked about all over the place. E.g. see [VIDEO] from June around the one hour mark. As I said, I'm very far from an insider.

> It was talked about all over the place. Really? Where can we read about it? > E.g. see [VIDEO] from June around the one hour mark. What are you referring to, where exactly in there? I poked "around the one hour mark" and didn't stumble across it, but am not gonna watch the whole thing. It's over an hour of somebody talking at a camera. Does an offhand comment buried in the middle of a 90-minute youtube ramble really strike you as appropriate notification of such an important requirement? Especially when this requirement doesn't appear anyplace where it can be read ?

Google has done a lot of effort in that direction. The first ever chips have already been produced that are fully open source from the tools used to make to the complete tool chain need to manufacture them. There is a huge amount of great stuff going on this this area. Tim Ansell - Skywater PDK: Fully open source manufacturable PDK for a 130nm process [VIDEO]

> The architecture doesn't offer anything actually new to the industry. There is more to live then technical specification. The change in the license and the development pattern and the business model does actually matter. I suggest you watch some talks by Krste Asanovic who created the RISC-V project, he explained exactly this point. > Open source software is unreasonably effective because of that trivial marginal cost of reproduction. Its open hardware isn't as good as open software. Yes we know. Sadly we don't have a universal 3d printer. But that doesn't mean its worthless. > Unlike the Linux kernel you can't compile a CPU core and reboot and get some performance gain. Have you never used an modern FPGA? > It just doesn't solve any of the very real problems of producing hardware. If you have a narrow point of you of only considering manufacturing but if you broaden your point of view and look at the whole value chain, it absolutely does. And you know who agrees with me, tons of companies who have invested in RISC-V and the ecosystem. If you don't believe me, I suggest you watch this video from Google where they explain why they are doing what they are doing: [VIDEO] You can find videos like that from other companies, including hardware companies. > It doesn't obviate the challenges or costs of developing new process nodes or chemistries. I didn't know that producing hardware was the same as developing knew nodes. In your mind, the only thing that matters is the cost of ne