vhd2vl is a simple and open-source stand-alone program that converts synthesizable VHDL to Verilog. While it has plenty of limitations, it has proved useful to many developers since its start in 2004. This talk will cover its strengths, weaknesses, and alternatives.

This talk presents the SODA (Software Defined Accelerators) framework, an open-source modular, multi-level, no-human-in-the-loop, hardware compiler that enables end-to-end generation of specialized accelerators from high-level data science frameworks. SODA is composed of SODA-Opt, a high-level frontend developed in MLIR that interfaces with domain-specific programming environments and allows performing system level design, and Bambu, a state-of-the-art high-level synthesis (HLS) engine that can target different device technologies. The framework implements design space exploration as compiler optimization passes. We show how the modular, yet tight, integration of the high-level optimizer and lower-level HLS tools enables the generation of accelerators optimized for the computational patterns of novel "converged" applications. We then discuss some of the research opportunities that such an open-source framework allows.

In this talk, Prof. Guthaus presents the current status of the OpenRAM project including Skywater 130 tape-out results. In addition, Prof. Guthaus will discuss the future roadmap of the OpenRAM project features and support for newer technologies.

Today's EDA algorithms demand large parallel and heterogeneous computing resources for performance. However, writing parallel EDA algorithms is extremely challenging due to highly complex and irregular patterns. This talk will present a novel programming system to help tackle the parallelization challenges of building high-performance EDA algorithms.

This talk explores how hardware projects designed using an open source PDK rely too much on precise data which may not be available, and how problems can be avoided by certain design methodologies such as two-phase clocking, negative-edge clocking, margining, and monte carlo simulation. While open PDK data can be made more reliable by cross validation with multiple tools and, ultimately, measurement, good design practices can achieve working silicon without absolute certainty.

BSV and BH, the Bluespec HLHDLs (High-Level Languages for Hardware Design), emerged from ideas in formal specification (Term Rewriting Systems), functional programming (Haskell), and automatic synthesis of RTL from specifications. BSV has been used in some major commercial ASIC designs and is used widely in FPGA projects. The BSV/BH compiler (written in Haskell) was open-sourced in 2020 (https://github.com/B-Lang-org/bsc) and today's projects are centered around RISC-V design and verification, and on accelerators.

Frans will present Spade, a new open source standalone hardware description language. He will show how Spade's abstractions and tooling, which is inspired by software languages, improves the productivity of an HDL without sacrificing low level control.