Florian Zaruba
@be4web
Followers
340
Following
1K
Media
11
Statuses
132
@ ETH Zurich. Zurich based Austrian expat. He/him.
Zurich, Switzerland
Joined March 2009
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
195
290
3K
🌟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
1
7
19
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: https://t.co/GMps7YYIcB
1
27
90
Cool @AxeleraAI booth at #ew23 looks great. #AI made in Europe And they use #RISCV in some chips Greetings to the #RISCVambassador @be4web
0
4
9
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! https://t.co/5PGK6KfUjj
#deeptech #ai #ml #edgeai
0
10
16
Wow, congratulations to the entire team, this is such an incredible achievement!
Here is Occamy: 216 Snitch cores, an HBM controller in GF12LPP, designed as a chiplet. Enough said 😇🦉. This work wouldn't be possible without the generous support of @GlobalFoundries and @rambusinc. https://t.co/mdsCEhAD8y
0
0
8
Obviously proud!
Found another chip that is manufactured in Intel 4. This is a 8-core RISC-V (RV64GC) CPU with compute near LLC called Vela. - 64 kB SRAM for each core - 512 kB shared LLC - the silicon is just 1,92 mm² (1,939 x 0,991 mm)
1
0
6
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
2
4
36
This is great! That's what I am talking about when I push for open hardware!! Avalanche effect 🚀😎
@LucaBeniniZhFe @pulp_platform Thanks @LucaBeniniZhFe ! We are also open-sourcing the code following the same principles as the @pulp_platform and the @openhwgroup here:
0
4
11
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". https://t.co/izTkTBG5M1
1
8
32
Thank you very much - it was a blast!
Today Florian @be4web nailed it! Congratulations on earning a doctorate degree for his work on "Energy-Efficient High-Performance Computing." Here is him getting ready for the defense and some celebration pictures from the good old days. 😊🍾
2
0
13
Happy to share Snitch with the world!
We are delighted to announce that Florian @be4web and Fabian @fabianschuiki (AKA Flabians 😇) have just open-sourced Snitch. You can find its source code here https://t.co/eJJLEE54ZQ and the documentation under https://t.co/tfNBUyQYn5 Wishing you all successful snitching 🤣.
0
0
10
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.🤣😼 https://t.co/9WK0WRcsBT
1
10
57
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 cool talk from FlorianxFabian of ETH on their Manticore chip. Cool to see what a PhD in other fields can be like. Taping out a chip ain't bad and what a logo too ;) @be4web @fabianschuiki #HotChips2020
1
2
14
Really looking forward to our presentation about Manticore later today #HotChips2020!! Feel free to get in touch anytime via DM or Slack.
In HC32, researchers have presented Manticore, a 22FDX general-purpose ultra-efficient #RISCV chiplet-based architecture for data-parallel floating-point workloads. https://t.co/rFdANlxxEq
1
1
15
#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
0
2
22
Me, during #HotChips2020 quantum computing session. Still lot to learn. But love the figures 😍
1
0
8
Excellent start of #HotChips2020 #hc32!! Perks of virtual: No heads in line of sight 😋 @pulp_platform @ETH_en
1
1
20
Looking forward to presenting together with @fabianschuiki on Tue and to a super interesting HotChips in general!
HotChips 2020 is almost here! Florian will be representing our team on August 18, 2020 with his 4096-core Manticore. https://t.co/Og2jeTlqtP
1
3
13