AMD Instinct MI200 Series Accelerator GPU Unveiled, Has 58-Billion Transistors to Power Exascale Systems
AMD is officially the first semiconductor company to use 6nm multi-chip module (MCM) technology with their Instinct MI200 Series. These accelerators are all based on AMD CDNA 2 architecture, providing up to 4.9X better performance than its competitors for double precision (FP64) HPC applications, as it surpasses 380 teraflops of peak theoretical half-precision (FP16) for AI workloads to enable disruptive approaches in further accelerating data-driven research. Read more for a video and additional information.
When you combine AMD’s Instinct MI200 series accelerators with their third-generation EPYC CPUs and the ROCm 5.0 open software platform, research teams will be able be able to make new discoveries for the exascale era, whether it be for climate change or vaccine research. For those who don’t know about the ROCm platform, it’s essentially built on the foundation of open portability, thus offering support to environments across multiple accelerator vendors and architectures.
AMD Instinct MI200 accelerators deliver leadership HPC and AI performance, helping scientists make generational leaps in research that can dramatically shorten the time between initial hypothesis and discovery. With key innovations in architecture, packaging and system design, the AMD Instinct MI200 series accelerators are the most advanced data center GPUs ever, providing exceptional performance for supercomputers and data centers to solve the world’s most complex problems,” said Forrest Norrod, senior vice president and general manager, Data Center and Embedded Solutions Business Group, AMD.