There is an alternate reality where Cray took their vector supercomputers, ditched FP64 calculations, and went with one FP32 pipe and a BF16 tensor core pipe. The same instruction set, memory architecture, and vector registers would have made a sweet deep learning machine, in many ways nicer than SIMT CUDA programming on GPUs. A Y-MP class machine like that could have delivered the AlexNet and DQN moments two decades earlier. Even doing everything in FP64 with no architectural changes, a Cray-1 would have been the best machine in the world for neural networks. If @geoffreyhinton had access to one for early research, the case could have been made for the architectural modifications to 10x the performance.

🌟We have had an amazing time at #RISCVSummitEurope so far! Watch #RISCV Ambassador @FlorianWoh's #recap video, highlighting a few of the incredible Summit announcements, sessions, and activities. We can't wait to see everyone for another packed day tomorrow! #RISCVeverywhere

In order to put to rest incorrect information that recently appeared on social media and several more prominent websites, we have published a summary of our project Occamy: pulp-platform.org/occamy/

Cool @AxeleraAI booth at #ew23 looks great. #AI made in Europe And they use #RISCV in some chips Greetings to the #RISCVambassador @be4web

We’re thrilled to share that we have closed our $27million Series A and are ready to launch our AI acceleration platform in early 2023! axelera.ai/european-ai-start… #deeptech #ai #ml #edgeai

Wow, congratulations to the entire team, this is such an incredible achievement!

Obviously proud!

Hello (ex) @pulp_platform's Ariane/@openhwgroup's CVA6! Thanks to Massimiliano.G's LiteX port, it's possible to regain some freedom: - No longer restricted to Xilinx/Genesys2/MIG. - New peripherals to play with :) - 100% open-source SoC! - ... Try it: litex_sim --cpu-type=cva6

This is great! That's what I am talking about when I push for open hardware!! Avalanche effect 🚀😎

We are delighted to see our Ariane helping researchers at Google 😇. Learn more in the article "Google Deploys AI to Build Better AI Hardware Accelerators". extremetech.com/extreme/3236…

This is the single best pull request I’ve ever got! Thanks @OlofKindgren

Thank you very much - it was a blast!

Happy to share Snitch with the world!

Can you design a chip in GF22 with 10 RISC-V cores in 5 weeks @fabianschuiki @be4web? Challenge accepted, hold our beers for a while. We present Thestral, PULP chip Nr. 38 taped out. But be careful - only people that have seen death can see a Thestral.🤣😼 asic.ethz.ch/2020/Thestral.h…

Thank you!! It was a blast and an honor presenting at #hotchips2020 We'll for sure post updates about Manticore's next steps😃@pulp_platform

Really looking forward to our presentation about Manticore later today #HotChips2020!! Feel free to get in touch anytime via DM or Slack.

#POWER10, what a beast! Designed with energy efficiency as one of the main design goals. An additional plus: the ISA is open source @OpenPOWERorg #HotChips2020

Me, during #HotChips2020 quantum computing session. Still lot to learn. But love the figures 😍

Excellent start of #HotChips2020 #hc32!! Perks of virtual: No heads in line of sight 😋 @pulp_platform @ETH_en

Looking forward to presenting together with @fabianschuiki on Tue and to a super interesting HotChips in general!