1/ Accelerating Number Theoretic Transforms is core to making ZK proof generation efficient.
We’re excited to share CycloneNTT: a novel architecture for Accelerating NTTs on FPGA
Check out the paper: https://t.co/91MWONRepI
And the blog post: https://t.co/8AEQqLMfin
🧵👇
1/ We're excited to open-source a library of optimized gadgets for Plonky2:
https://t.co/bDK0EwdfWZ
These include sha256, keccak256, and the underlying binary and biguint arithmetic. We hope these will help speed up your zero-knowledge proofs and tackle more complex ones!
Excited to share some of our work on ZKP!
Open source library of gadgets for Plonky2:
https://t.co/xxf9BLdQYL
Sha256, Keccak256, and the underlying binary & biguint arithmetic.
Heavily optimized: 5x sha2/s on my Mac M1 Pro 🚀
Introducing Firedancer’s latest technical milestone: fd_quic 🔥💃
A high-performance implementation of the QUIC and Solana transaction ingest network protocols.
1/15
Later this week we’ll sit down with a few of the teams attending zkWeek to discuss the state of ZK and more.
We’ll be joined by @ConsenSys, @MinaProtocol, and @lagrangedev.
Set a reminder below!
https://t.co/PEl390D9BS
Join @fd_ripatel, @DanPaul000, and Jump Crypto Research and Development Architect, Philip Taffet to discuss the team’s progress building the Firedancer validator this Friday!
Set a reminder below. 🔥💃
https://t.co/AuwriIYRA4
Jump Crypto Security Engineer @0x0ece recently presented on FPGA Acceleration of Multi-Scalar Multiplication on a live stream hosted by @Scroll_ZKP.
Watch the video below:
https://t.co/v1YTA0RlF9
Hear what @rahulmaganti_ had to say on Manta Network’s OpenZL Talk 10:
CycloneNTT — Improving Twiddle Access for Number Theoretic Transforms. https://t.co/WhVX3wtiJC
And finally, @rahulmaganti_ from @jump_ speaks on Improving “Twiddle Access for Number Theoretic Transforms,” by using a state-of-the-art butterfly network and maps the dataflow to hybrid FIFOs composed of on-chip SRAM and external memory. https://t.co/8iWXRHbQfR
1/ We strive for performance, but our highest priorities are reliability and security.
Learn more about the steps we are taking to help improve the Solana network: https://t.co/LdM0yKJMQT
13/ The code will be open-sourced and available soon! If you want to chat ZK hardware acceleration, reach out to @rahulmaganti_, @0x0ece, and @nickraystalder.
https://t.co/GrK6F6ZqvB
#ePrint CycloneNTT: An NTT/FFT Architecture Using Quasi-Streaming of Large Datasets on DDR- and HBM-based FPGA Platforms: K Aasaraai, E Cesena, R Maganti, N Stalder, J Varela, K Bowers https://t.co/N0IjQ1YBGj
1/ Accelerating Number Theoretic Transforms is core to making ZK proof generation efficient.
We’re excited to share CycloneNTT: a novel architecture for Accelerating NTTs on FPGA
Check out the paper: https://t.co/91MWONRepI
And the blog post: https://t.co/8AEQqLMfin
🧵👇
12/ We explored architectures that process multiple layers at a time. Experiments with 1, 3, and 6-layers showed that the 3-layers approach yields the best latency vs. power tradeoff.