Sophgo Licenses SiFive RISC-V Processor Cores to Drive High-Performance AI Computing Innovation
SiFive’s Multi-Cluster, Multi-Cores P670 and X280 Power the Open Standard Platform for High-Performance AI Applications
Santa Clara, Calif., November 1, 2023 – Today, Sophgo announced that the company has licensed several SiFive RISC-V high performance processor cores, the SiFive Performance P670 and SiFive Intelligence X280 to develop RISC-V AI computing processors. Presented on SG2380 Kick-off Day at the Zhongguancun IC Park in Beijing, the new SiFive cores will be used in the upcoming, Sophgo SG2380.
Ad |
Dual-issue Linux-capable RISC-V core RISC-V high performance CPU Low-power 32-bit RISC-V processor Superscalar Out-of-Order Execution Multicore Cluster |
The new Sophgo SG2380 is a 2.5 GHz 16-core RISC-V processor, utilizing the SiFive Performance P670 with a multi-cluster, multi-core configuration. It boasts high performance and RISC-V vector computation advantages. SG2380 also incorporates SiFive Intelligence X280 and a Vector Cooperative Processor Interface Extension (VCIX), integrating Sophgo's AI/ML hardware design. With complete software toolchain support from RISC-V, this coprocessor is targeting not only AI/ML but various advanced computing needs.
The P670, combined with RISC-V's unique instruction set architecture advantages and advanced microarchitecture design with silicon implementation by the SiFive team, offers high computational density and vector computation capabilities. Sophgo has also utilized the proven X280, paired with VCIX, as an NPU, highlighting the synergies between the two companies in this collaboration.
The SiFive P670 is currently the highest-performance and fully spec-compliant RISC-V commercial-grade processor IP (SpecINT2k6 exceeding 13/GHz) available in the market. SiFive offers multi-cluster, multi-core P670-compliant with RVA22, supporting the latest RISC-V specifications and operating systems, providing optimal performance and the lowest power consumption. The SiFive X280 offers flexibility and scalability in AI applications, supporting multi-core, multi-cluster configurations and numerous successful chip instances. The development tools and software support the latest OpenXLA framework, in line with the market demand and future application trends of AI.
For more information about Sophgo SG2380, please refer to CNX SOFTWARE – EMBEDDED SYSTEMS NEWS: Sophgo SG2380 – A 2.5 GHz 16-core SiFive P670 RISC-V processor with a 20 TOPS AI accelerator.
About SOPHGO
SOPHGO is committed to becoming the world's leading provider of universal computing power, focusing on the development and promotion of computing power products such as AI and RISC-V processors, following the ecological concept of full open source and openness, and working with ecological partners to create a full-scene product matrix covering "cloud, edge and endpoint". Provide computing products and overall solutions for Internet, Urban operations, Intelligent computing centers, General security, Intelligent manufacturing, and AIGC and other application scenarios. Our company has research and development centers in more than 10 cities in China such as Beijing, Shanghai, Shenzhen, Qingdao, Xiamen, as well as in countries such as the United States and Singapore. Since 2016, our brand's SOPHON series products have undergone multiple iterations, achieving significant improvements in energy efficiency compared to their predecessors in each generation.
|
Related News
- SiFive Announces New High-performance RISC-V Datacenter Processor for Demanding AI Workloads
- SiFive Announces Differentiated Solutions for Generative AI and ML Applications Leading RISC-V into a New Era of High-Performance Innovation
- Vidtoo Technology Licenses Codasip's Bk3 RISC-V Processor for High-Performance Computing SoC
- Tenstorrent Selects Arteris IP for AI High-Performance Computing and Datacenter RISC-V Chiplets
- SiFive Partners with Intel to Spark Innovation in High-Performance RISC-V Platforms
Breaking News
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models
Most Popular
E-mail This Article | Printer-Friendly Page |