Imperas is honored for its support of Andes customers with Fast Processor Models of the Andes RISC-V processor IP
Oxford, United Kingdom, December 11, 2023 — Imperas Software Ltd., the leader in RISC-V simulation solutions, today announced that Andes Technology Corporation, a leading supplier of high efficiency, low-power 32/64-bit RISC-V processor cores and Founding Premier member of RISC-V International, has selected Imperas as the Andes Partner of the Year for 2023. Imperas has worked with Andes since 2017 to provide fast, instruction accurate models for the complete range of Andes RISC-V processor IP, with Andes certifying Imperas models as reference models of the Andes cores.
Virtual platforms (software simulation) are now a mainstream technology used to shift-left software development, and are also used after silicon is available for comprehensive, automated software testing. The key requirement for the successful deployment of virtual platforms is quality models, especially of the processors. In addition, the models need to be compatible with a range of industry standard tools and design flows, including SystemC and hardware emulators. Imperas Fast Processor Models (ImperasFPMs) of the Andes processor IP satisfy these requirements.
Andes provides a wide range of RISC-V CPUs, ranging from small microprocessors to multi-core applications processors with multi-issue out-of-order pipelines, including supporting the RISC-V DSP, FPU and vector extensions. Andes was also the first company to develop a fully ISO 26262 compliant processor for automotive SoCs, including certification to the ASIL-B functional safety standard. Andes processors are also used to meet high performance AI/ML requirements.
Joint successes include a hyperscaler customer with a complex many-core AI accelerator. This customer used Imperas technology initially in their project for architecture exploration. They then demonstrated their full software stack running within a week of receiving silicon, having developed the software in advance on Imperas virtual platforms with ImperasFPMs of the Andes processors.
“Imperas provides high quality, fast simulation models, which enable our customers to develop highly complex software stacks ahead of silicon availability, improving their time to market and reducing risk,” said Dr. Emerson Hsiao, President, Andes Technology USA. “This award recognizes the strength of the partnership between Andes and Imperas.”
“As a founding member of RISC-V International, Andes has been driving the RISC-V instruction set architecture specification from the beginning, and their IP has set a very high standard for the community,” said Simon Davidmann, CEO at Imperas Software Ltd. “We have been supporting Andes customers with our models for nearly seven years, and feel honored to receive this Partner of the Year award as it recognizes the hard work and dedication of our entire team.”
Availability
The Imperas models of the Andes processor IP portfolio are available now via www.OVPworld.org. Imperas RISC-V reference models are also available via approved EDA distribution partners. To explore this option in more detail, please contact Imperas or your preferred EDA supplier.
About OVPworld.org
The Imperas simulation and modeling technology supports over 12 ISAs and over 300 processor models. OVPworld (Open Virtual Platforms) is dedicated to making software virtual platforms an easy and ubiquitous element of embedded software development. As the hardware has gotten more complex, the embedded software has also become more complex, and requires new tools. Software virtual prototypes, enabling embedded software simulation, verification and debug, are the key technology to effective embedded software development going forward.
OVP models are typically published under the Apache 2.0 open-source license and include reference platforms, examples and other collaborative projects from the community of OVP users. OVPworld was established over 10 years ago and has supported thousands of users, both commercial and academic. Registration is free, as is academic and non-commercial use, commercial users are supported for a 90-day evaluation period.
