Supercharging AI and HPC to propel new discoveries
From single-server solutions up to the world’s largest, Exascale-class supercomputers¹, AMD Instinct™ accelerators are uniquely well-suited to power even the most demanding AI and HPC workloads in your data centers.
Get more done, more efficiently, with exceptional compute performance, large memory density, high bandwidth memory, and support for specialized data formats.
UNDER THE HOOD
AMD Instinct™ accelerators are built on AMD CDNA™ architecture, which offers Matrix Core Technologies and support for a broad range of precision capabilities – from the highly efficient INT8 and FP8 (including sparsity support for AI with AMD CDNA™ 3), to the most demanding FP64 for HPC.
MI300 SERIES
AMD INSTINCT™ MI300X ACCELERATOR
Designed to deliver leadership memory capacity and bandwidth, AMD Instinct™ MI300X accelerators are ideal for Generative AI and HPC applications. They deliver nearly 40% more compute units², 1.5x more memory capacity, 1.7x more peak theoretical memory bandwidth³ compared to previous generation AMD Instinct™ MI250X accelerators.
AMD INSTINCT™ MI300A APU
The world’s first data center accelerated processing units (APUs) for HPC and AI, leverage 3D packaging and the 4th Gen AMD Infinity Architecture to deliver leadership performance on critical workloads sitting at the convergence of HPC and AI. They combine the power of AMD Instinct™ accelerators and AMD EPYC™ processors with shared memory to enable enhanced efficiency, flexibility, and programmability.
AMD INSTINCT™ MI300X PLATFORM
This leadership generative AI platform integrates 8 fully connected MI300X GPU OAM modules onto an industry-standard OCP design via 4th-Gen AMD Infinity Fabric™ links, delivering up to 1.5TB HBM3 capacity for low-latency AI processing. It's ready-to-deploy, and designed to accelerate time-to-market and reduce development costs when adding AMD Instinct™ MI300X accelerators into existing AI rack and server infrastructure.
MI200 SERIES
AMD INSTINCT™ MI250 AND MI250X ACCELERATOR
Delivers outstanding performance to power some of the world’s top supercomputers for HPC and AI
View specsAMD INSTINCT™ MI210 ACCELERATOR
Powers enterprise, research, and academic HPC and AI workloads for single-server solutions and more
View specsAMD ROCm™ Software
This open software stack includes a broad set of programming models, tools, compilers, libraries, and runtimes for AI and HPC solution development – targeting AMD Instinct™ accelerators.
Download our White Paper to find out how the AMD CDNA™ 3 Architecture powers the AMD Instinct™ MI300 accelerators to deliver the highest performance, efficiency, and programmability.
KT Cloud
Korean cloud computing company KT Cloud is unleashing the possibilities of AI with AMD Instinct™ MI250 accelerators to build a cost-effective and scalable AI cloud service.
Read case study
LUMI Supercomputer
Learn how AMD Instinct™ MI250 accelerators are powering LUMI to advance groundbreaking research in climate change modeling, early cancer detection, and more.
Watch video
Oak Ridge National Laboratory - CHOLLA
Step into an alternate universe! Using AMD Instinct™ accelerators, the Cholla CAAR team is simulating the entire Milky Way.
Read case study
Oak Ridge National Laboratory - PIConGPU
Leveraging the ROCm platform, ORNL’s PIConGPU taps the immense compute capacity of AMD Instinct™ MI200 accelerators to advance radiation therapy, high-energy physics, and photon science.
Read case study