Episode 267: ZK Hardware Sessions with Zprize Pt. 2

In this two-part series exploring ZK Hardware, Anna Rose interviews various participants from the ZPrize competition, alongside the creator of ZPrize and co-host of this episode Alex Pruden from Aleo. Throughout these interviews, they dig into the different types of hardware, such as GPUs and FPGAs, that can be used to accelerate ZKP computation. They also discuss the underlying mathematical techniques in ZKPs that can be optimized for and the tricks and strategies that ZPrize competitors used to achieve these optimizations.

In Part 2 of the series, Anna and Alex first interview Hamid Salehi and Swati Gupta from Xilinx AMD who contribute insights from the perspective of an FPGA manufacturer. Alex and Anna then interview competitor Niall Emmart, previously from NVIDIA. They discuss his previous work and what went into winning both the MSM for GPUs and MSM for Wasm competitions in ZPrize.


Here is some additional information for this episode:

Hardware/Board options:

  • Varium C1100 board (targeted at accelerating blockchain applications).
    This board has been used to accelerate the following:
  • Poseidon hash (used in the storage sealing process for Filecoin)
  • NTT acceleration at ZPrize
  • Startups are using this to explore NTT and MSM acceleration
  • Other boards
    The U55C in particular has been shown to provide a competitive and more power efficient alternative to GPUs for MSM acceleration in this study by Ingonyama called PipeMSM. There has been interest in U55C for NTT acceleration as well due to the high HBM capacity it provides (16GB).

Research and documents on using FPGAs for ZK related implementation:

Projects using the C1100 board (These can be a good starting point for getting familiar with the hardware and tools):

Documentation on tools and boards:

GitHub Repositories:


Check out the ZK Jobs Board here: ZK Jobs.


Ingonyama’s mission is to improve the performance of Zero-Knowledge Provers by designing hardware optimized for ZK computation. They are proud to introduce their latest project, ICICLE.

For ideas and discussion around the code, visit the ICICLE channel in the Ingonyama discord server, where team members and fellow developers await.


If you like what we do:

Previous Episodes

Episode 321: STIR with Gal Arnon & Giacomo Fenzi

In this week’s episode, Anna and Kobi chat with Gal Arnon, Ph.D student from the Weizmann Institute of Science & Giacomo Fenzi, Ph.D. student in the COMPSEC Lab at EPFL.

Gal and Giacomo are amongst the co-authors of ‘STIR: Reed–Solomon Proximity Testing with Fewer Queries’ and in this conversation, they discuss how their research led them to work on these topics and where the thesis for this particular work sparked from. They set the stage by exploring the history of FRI and discussing some hidden nuances in how FRI works. And then they introduce STIR, a system that can be used in place of FRI, which incorporates various optimisations to improve the performance.

Episode 320: A Deep Dive into Shared Sequencers with Espresso’s Ben Fisch

In this week’s episode, Anna (https://twitter.com/annarrose) and Brendan Farmer (https://twitter.com/_bfarmer) catch up with Ben Fisch (https://twitter.com/benafisch), CEO of Espresso Systems (https://www.espressosys.com/). They explore the inner workings of the current L2 sequencing landscape and then discuss how a shared sequencing marketplace like Espresso works. They touch on how MEV plays a part in the new system, how the role of the sequencer can be separated into subroles, how all these parts will work together in such a system and much more.

Episode 319: The Past & Present of the L2 Landscape with Jordi Baylina

In this week’s episode, Anna catches up with Jordi Baylina, OG Ethereum contributor and Polygon zkEVM Technical Lead. They cover what Jordi has been working on since he was last on the show in 2021. Back then, zkEVMs were still just an idea. Now that many of these systems have launched, they have a chance to look at how these fit into the general L2 landscape.

They cover Jordi’s view on engineering decentralized systems and how these are rolled out, and the recent research from Polygon, including their AggLayer proposal. They wrap up on what inspires him to keep contributing in the space.

Episode 318: Threshold Signature Schemes & FROST with Chelsea Komlo

In this week’s episode, Anna and Nico chat with Chelsea Komlo, Chief Scientist for the Zcash Foundation and member of the Cryptography, Security, and Privacy lab at the University of Waterloo.

They discuss what sparked Chelsea’s interest in cryptography research, starting with her work contributing to Tor, to her move to Zcash and her PhD work on Threshold Signature Schemes. They define some important terms around different signature schemes and discuss possible optimizations that can be used to make these more performant. They then dive into her work on the FROST Threshold Signature Scheme plus some new upcoming work.

Episode 317: Enhancing On-Chain Intelligence with Ritual

This week, Anna and Tarun chat with Niraj Pant and Anish Agnihotri from Ritual. They kick off by revisiting the AIxCrypto intersection before diving into the Ritual product and its goals around developing open access AI infrastructure. They explore the opportunities that open up when you bring ML to smart contracts.

Bonus: zkSummit11 reminder!

Quick reminder about our upcoming zkSummit 11 event. Happening in Athens on April 10th, we once again bring together the top researchers and engineers working in zk to share their latest research and new findings.

Episode 316: Alin Tomescu on Distributed On-chain Randomness and Keyless Accounts

In this week’s episode, Anna and Nico chat with Alin Tomescu, founding team member and Head of Cryptography at Aptos Labs. They discuss Alin’s journey to Aptos and his work on distributed on-chain randomness as well as the new Aptos Keyless project. They cover the Keyless accounts architecture, how the flow works for the user and some of the subtleties in the approach they have taken.

Zk white

Subscribe

Subscribe to Zero Knowledge podcast on these links:

Join the conversation:

Newsletters:

Support: