NVIDIA NVLink High-Speed Interconnect: Maximizes throughput for Superior Application Performance

121 019
62.3
NVIDIA1.78 млн
Следующее
Популярные
32 дня – 284 3723:01
The Next Wave of AI: Physical AI
175 дней – 145 2452:10
NVIDIA—Our Story, Built on Taiwan
Опубликовано 14 ноября 2014, 15:00
Accelerated Computing is driving the next generation of discovery by tapping into the massively parallel processing power of GPUs for a wide range of applications. In today’s servers, GPUs are connected by the PCIe, providing 12 GB/sec of communication bandwidth. With NVIDIA’s new NVLink interconnect, GPUs can communicate directly to each other, at a much higher speed due to 5-12 times more bandwidth. Additionally, NVLink interconnect makes high-speed communication between GPU and CPU possible, allowing both to access system memory at the same speed, further increasing the benefit of accelerated computing. Learn more about it at nvda.ly/EeNQi.
автотехномузыкадетское