An Interest In:
Web News this Week
- March 28, 2024
- March 27, 2024
- March 26, 2024
- March 25, 2024
- March 24, 2024
- March 23, 2024
- March 22, 2024
September 14, 2022 11:32 pm GMT
Computational requirements for AI have been growing at an exponential rate. New innovation is required across hardware and software to deliver computational throughput needed to advance AI. One of the promising areas of research to address this growing compute gap is to reduce the numeric precision requirements for deep learning to improve memory and computational efficiencies. Reduced-precision methods exploit the inherent noise-resilient properties of deep neural networks to improve compute efficiency.
Original Link: https://www.techpowerup.com/298881/intel-arm-and-nvidia-propose-a-new-8-bit-fp-format-to-accelerate-ai
(PR) Intel, Arm, and NVIDIA Propose a new 8-bit FP Format to Accelerate AI
Arm, Intel and NVIDIA have jointly authored a paper describing an 8-bit floating point (FP8) specification and its two variants E5M2 and E4M3 to provide a common interchangeable format that works for both artificial intelligence (AI) training and inference. This cross-industry specification alignment will allow AI models to operate and perform consistently across hardware platforms, accelerating AI software development.Computational requirements for AI have been growing at an exponential rate. New innovation is required across hardware and software to deliver computational throughput needed to advance AI. One of the promising areas of research to address this growing compute gap is to reduce the numeric precision requirements for deep learning to improve memory and computational efficiencies. Reduced-precision methods exploit the inherent noise-resilient properties of deep neural networks to improve compute efficiency.
Original Link: https://www.techpowerup.com/298881/intel-arm-and-nvidia-propose-a-new-8-bit-fp-format-to-accelerate-ai
Share this article:
Tweet
View Full Article