草榴社区

Vehicles are undergoing a period of massive evolution driven by increased levels of autonomy, new in-car experiences, and electrification, driving the automotive supply chain to deliver greater innovation while streamlining the product life cycle. RISC-V is the Open Standard Instruction Set Architecture (ISA) that uniquely scales across every in-vehicle compute application, cost effectively delivering innovation opportunities to meet diverse compute requirements that power future generations of vehicles. This session explores how the RISC-V ISA can be used to simplify development and deployment of extensible, power- and area-efficient hardware and software innovation across vehicle ranges and models. It will discuss how RISC-V implementations and ecosystem can offer efficiencies for the automotive supply chain, and the new possibilities it will open up for in-vehicle compute experiences.

As RISC-V adoption grows, how are EDA tools and IP adapting to address new and evolving design challenges? From architecture exploration to design implementation and software development, SoC designers are looking for ways to take advantage of the RISC-V ecosystem and deliver optimized products with fast time-to-market. ?At 草榴社区, we’re building RISC-V solutions to help customers from the beginning of the project to delivery and deployment, supporting the full RISC-V ISA plus custom instructions while enabling architecting of workload-optimized processors, comprehensive processor verification, and pre-silicon software development. Whether you are building your own RISC-V core, using a partner’s core, or implementing 草榴社区 ARC-V processor IP, 草榴社区 can help you meet your project requirements. ?This presentation will provide an overview of the broad range of 草榴社区 RISC-V solutions that have been proven by our customers taking RISC-V SoCs to silicon.

With the increased usage of RISC-V processors across the whole range of SoC market segments, quality of the RISC-V processor is an increasingly important issue. Historically, processor IP has been purchased from single-source vendors who own the ISA, and this IP was assumed to be of excellent quality. However, in the RISC-V ecosystem with vendor-supplied IP, open source IP and IP developed in-house, such quality cannot be taken for granted. This creates a verification “disconnect” between SoC developers expecting high-quality IP and processor developers that do not have the verification resources of the single source processor IP vendors. This talk will discuss how dynamic and formal methods can be used together for a more thorough and efficient verification process, helping to bridge the verification disconnect. Examples of using this combined methodology on open-source cores from OpenHW Group, specifically the CV32E40 family, CVW and CVA6, will be presented, including functional coverage results. A key feature of the RISC-V ISA is its extensibility, enabling custom instructions and CSRs to be added. The combined approach will also be shown to work well in this common situation.

Reduce the number of vector registers to reduce the area of small processors for DSP applications.

RISC-V allows the freedom to innovate with custom instructions but working out which custom instructions add the most value is key to success and more easily done with simulation and models than RTL. At the same time new applications such as AI/ML are creating ever more complex SoCs with very high core counts. Using models in a digital twin of the design allows fast architectural exploration, accelerates software development and post silicon can help with DevOps flows and diagnosing in-field failures. This talk discusses two custom SoC projects where virtual platforms have been used to successfully develop software for many core systems in advance of silicon being available. This requires fast, accurate golden models of the CPUs in a simulation environment which can scale to hundreds or more cores.

RISC-V allows the freedom to innovate with custom instructions but working out which custom instructions add the most value is key to success and more easily done with simulation and models than RTL. At the same time new applications such as AI/ML are creating ever more complex SoCs with very high core counts. Using models in a digital twin of the design allows fast architectural exploration, accelerates software development and post silicon can help with DevOps flows and diagnosing in-field failures. This talk discusses two custom SoC projects where virtual platforms have been used to successfully develop software for many core systems in advance of silicon being available. This requires fast, accurate golden models of the CPUs in a simulation environment which can scale to hundreds or more cores.