RISC-V AI Chips Will Be Everywhere (2022)
RISC-V AI chips, exemplified by Esperanto's ET-SoC-1 chip with over 1,000 cores, are set to revolutionize AI processing. Industry forecasts predict substantial growth, challenging traditional architectures and promoting innovation.
Read original article
RISC-V AI chips are gaining momentum, driven by the demand for AI and machine learning applications. Esperanto Technologies has developed the ET-SoC-1 chip, featuring over 1,000 RISC-V cores consuming only 20 watts. The industry is projected to witness a significant increase in RISC-V technology adoption, with an estimated 25 billion AI chips generating $291 billion in revenue by 2027. This shift signifies a notable advancement in AI processing capabilities, challenging traditional architectures like x86 and Arm.
Esperanto's innovative approach aims to compete with powerful GPUs in AI recommendation systems by leveraging RISC-V's streamlined instruction set. The ET-SoC-1 chip, with 1,088 ET-Minion cores and four ET-Maxions, offers high performance at low power consumption, outperforming conventional AI accelerators. Intel's strategic investment in RISC-V further validates the architecture's potential, fostering collaboration with key players like Andes Technology, SiFive, and Ventana Microsystems to drive innovation and adoption.
Overall, the surge in RISC-V AI chips marks a significant shift in the semiconductor industry, emphasizing the importance of open-source architectures and customized solutions to meet the evolving demands of AI and machine learning technologies.
Related
Sohu: The First Transformer ASIC
Etched secures $120 million to develop Sohu, a transformer ASIC enhancing AI model performance. Sohu enables real-time voice agents, rapid text processing, and trillion-parameter models, revolutionizing AI processing with advanced features.
Sohu AI chip claimed to run models 20x faster and cheaper than Nvidia H100 GPUs
Etched startup introduces Sohu AI chip, specialized for transformer models, outperforming Nvidia's H100 GPUs in AI LLM inference. Sohu aims to revolutionize AI processing efficiency, potentially reshaping the industry.
Supercomputer-on-a-chip goes live: single PCIe card packs more than 6k cores
InspireSemi introduces Thunderbird I Accelerated Computing chip with 1,536 custom RISC-V CPU cores for scientific and data processing. Energy-efficient, scalable to 360,000 cores, suitable for high-performance computing tasks. CEO praises team's work.
Milk-V Reveals Technical Specs of Milk-V Jupiter RISC-V Mini-ITX PC
Milk-V unveils Milk-V Jupiter RISC-V Mini-ITX PC with SpacemiT K1/M1 SoC, octa-core X60 processor, 2.0 TOPS AI power, RAM options, GPU support, multimedia features, storage choices, connectivity options, and OS compatibility. Available on Taobao.
Extreme Measures Needed to Scale Chips
The July 2024 IEEE Spectrum issue discusses scaling compute power for AI, exploring solutions like EUV lithography, linear accelerators, and chip stacking. Industry innovates to overcome challenges and inspire talent.
6 commentsPart of the strategy of commoditizing your complement: https://gwern.net/complement
Similar thing going on right now with the rampant open sourcing of LLMs
Eventually RISC-V may have CPU cores fast enough to compete with high end ARM and x86 cores but it will take a while and incentive from the chip companies to design those high performance RISC-V cores. Some of that incentive may come from ARM raising license fees.
Short term we won't see it "everywhere". Without a powerhouse to push it, I find it hard to see/say if it'll be able to catch up or what that'll look like (see Linux example).
Related
Sohu: The First Transformer ASIC
Etched secures $120 million to develop Sohu, a transformer ASIC enhancing AI model performance. Sohu enables real-time voice agents, rapid text processing, and trillion-parameter models, revolutionizing AI processing with advanced features.
Sohu AI chip claimed to run models 20x faster and cheaper than Nvidia H100 GPUs
Etched startup introduces Sohu AI chip, specialized for transformer models, outperforming Nvidia's H100 GPUs in AI LLM inference. Sohu aims to revolutionize AI processing efficiency, potentially reshaping the industry.
Supercomputer-on-a-chip goes live: single PCIe card packs more than 6k cores
InspireSemi introduces Thunderbird I Accelerated Computing chip with 1,536 custom RISC-V CPU cores for scientific and data processing. Energy-efficient, scalable to 360,000 cores, suitable for high-performance computing tasks. CEO praises team's work.
Milk-V Reveals Technical Specs of Milk-V Jupiter RISC-V Mini-ITX PC
Milk-V unveils Milk-V Jupiter RISC-V Mini-ITX PC with SpacemiT K1/M1 SoC, octa-core X60 processor, 2.0 TOPS AI power, RAM options, GPU support, multimedia features, storage choices, connectivity options, and OS compatibility. Available on Taobao.
Extreme Measures Needed to Scale Chips
The July 2024 IEEE Spectrum issue discusses scaling compute power for AI, exploring solutions like EUV lithography, linear accelerators, and chip stacking. Industry innovates to overcome challenges and inspire talent.