Snark ChocolateICICLE
Resources
Company

Tony Wu

Tony is a hardware engineer and FPGA architect at Ingonyama.

He specializes in building datacenter-class FPGA accelerators and loves to work at the intersection between software and hardware. Tony holds a Masters degree in Computer Science from the University of New South Wales. He is always on the lookout for interesting computer architectures and tools to help push the performance frontier of cryptography.

Blogs by 

Tony Wu

Product Announcement: ZK-Containers

Ingonyama is the developer of ICICLE, which is the equivalent of PyTorch for AI, but for ZK proof generation. We are offering a new set of tools alongside ICICLE. Let us introduce the ZKDC framework, a set of secure and optimized ZK Containers for ICICLE applications and a set of scripts for deploying basic ZK datacenters.

Down the Rabbit Hole: Optimizing AWS F1 Direct Memory Access (DMA)

When implementing a system involving both software and hardware components, unforeseen issues always seem to occur at the interfaces.

AMD XDNA: Meet 2023 ZK Acceleration King

As the computational demand for AI inference increases at the edge and in the data-center, manufacturers are integrating power-efficient AI engines into their devices. AMD’s new AI-Engine architecture, called XDNA is one such example, and are currently available in select Versal FPGAs and laptop CPUs. What’s interesting for us, in the context of ZK acceleration, is their excellent integer multiply performance.

Deep dive into the Latest MSM Hardware Implementation

The 2023 ZPrize competition (Prize 1A) challenged participants to accelerate MSMs on either NVIDIA GPUs or AMD FPGAs. The work described in this blog post was a collaboration between ZPrize 2022 winner Niall Emmart of Yrrid Software and Ingonyama’s Tony Wu. Niall was the architect of the project and Tony was in charge of the implementation.