Think Silicon NEOX RISC-V GPU offers 3D graphics or AI acceleration
The Think Silicon NEOX family of GPUs with models optimized for graphics (NEOX|G) or artificial intelligence (NEOX|A) are based on the RISC-V RV64C ISA instruction set with adaptive NoC and offer up to 64 cores delivering up to 409.6 GFLOPS at 800 MHz with support for FP16, FP32 and optionally FP64 and SIMD instructions.
NEOX GPUs can be integrated into even more powerful microcontrollers, cross-processors and application processors, and target AI, IoT/Edge and media processing in consumer and industrial devices.
Each GPU shader is a programmable 64-bit RISC-V (RV64GC) core running a real-time operating system (RTOS) and the GPU is supported by lightweight graphics and machine learning frameworks. The multi-threaded GPU system can be customized for graphics, machine learning, video/vision processing, and general purpose computing (GPGPU) workloads.
The solution is intended to be integrated into 32-bit SoCs designed for smartwatches, augmented reality (AR) glasses, video surveillance and smart display terminals running Linux, Wear OS or real-time operating systems. . Think Silicon says NEOX IP pre-evaluation systems based on Xilinx SoC FPGA are available for customer testing with System Verilog RTL, configuration tools, NEOX SDK, LLVM, and GCC toolchains, and libraries with OpenCL 1.2 EP and OpenGL ES 2.x API support, among other deliverables.

This “news” may not be so new since it looks a lot like the announcement of the NEOX GPU | V RISC-V from December 2019, except now there are two models optimized for 3D graphics or AI. I haven’t found any NEOX GPU-based SoCs so far, but perhaps progress has been made and the company will showcase both 3D/2D graphics and machine learning applications at Embedded World 2022. Further details can be found at the product sheet and recent announcement.

Jean-Luc started CNX Software in 2010 on a part-time basis, before stepping down as Director of Software Engineering and starting writing daily news and reviews full-time later in 2011.
Support CNX software! Make a donation through PayPal Where cryptocurrencies, become a patron on Patreon, or buy exam samples
Comments are closed.