AMD INSTINCT SERIES

AMD Instinct Series accelerators deliver a quantum leap in HPC and AI
performance over competitive data center GPUs. Try them today as part of the
Cirrascale AI Innovation Cloud.

The Era of Exascale is Here

Immense computational power coupled with the fusion of HPC and AI is enabling researchers and scientists to tackle our most pressing challenges from climate change to vaccine research. With the AMD Instinct™ MI250 accelerator and ROCm™ 5.0 software ecosystem, innovators can tap the power of the world’s most powerful HPC and AI data center GPUs to accelerate their time to science and discovery.

Based on the 2nd Gen AMD CDNA™ architecture, AMD Instinct MI250 accelerator delivers a quantum leap in HPC and AI performance over competitive data center GPUs today. With an up to 4x advantage in HPC performance compared to competitive GPUs, the MI250 accelerator is the first data center GPU to deliver 383 teraflops of theoretical mixed precision FP16 performance for deep learning training, offering users a powerful platform to fuel the convergence of HPC and AI.

AMD Instinct Series and the Cirrascale AI Innovation Cloud Advantage

We've partnered with AMD to offer their AMD Instinct MI Series accelerators in the cloud for customers to test, utilize and fully deploy. No matter your application, whether large language models (LLM), natural language processing (NLP), or Object Detection, the Cirrascale AI Innovation Cloud utilizing the AMD Instinct Series is for you.

Our flat rate, no surprises billing model means we can provide you with a price that won't fluctuate so you can count on what we've presented as your final price. We also don't nickel-and-dime you by charging to get your data in to or out of our cloud. Instead, we charge no ingress or egress fees, so you never receive a supplemental bill.

AMD Instinct Server
CDNA Architecture

2nd Generation AMD CDNA™ Architecture

The AMD Instinct™ MI200 series accelerator brings customers the compute engine selected for the first U.S. Exascale supercomputer. Powered by the 2nd Generation AMD CDNA™ architecture, the MI200 series accelerators deliver a quantum leap in HPC and AI performance over competitive data center GPUs today. The AMD Instinct MI200 series GPU delivers industry-leading double precision performance for HPC workloads with up to 47.9TFLOPS peak FP64 performance, enabling scientists and researchers across the globe to process HPC parallel codes more efficiently across several industries.

AMD’s Matrix Core technology delivers a full range of mixed precision operations bringing you the ability to work with large models and enhance memory-bound operation performance for whatever combination of AI and machine learning workloads you need to deploy. The MI200 offers optimized BF16, INT4, INT8, FP16, FP32, and FP32 Matrix capabilities bringing you supercharged compute performance to meet all your AI system requirements. The AMD Instinct MI200 accelerator handles large data efficiently for training and is the first data center GPU to deliver 383 teraflops of peak FP16 performance for deep learning training.

AMD Infinity Fabric™ Link Technology

AMD Instinct MI200 series OAM accelerators with advanced peer- to-peer I/O connectivity through a maximum of eight AMD Infinity Fabric ™ links deliver up to 800 GB/s I/O bandwidth performance.3 With a cache coherency enabled solution using Optimized 3rd Gen AMD EPYC™ CPU and MI250X accelerators, Infinity Fabric unlocks the promise of unified computing, enabling a quick and simple onramp for CPU codes to accelerated platforms.

Ultra-Fast HBM2e Memory

The AMD Instinct™ MI200 accelerators provide up to 128GB Highbandwidth HBM2e memory with ECC support at a clock rate of 1.6 GHz. and deliver an ultra-high 3.2 TB/s of memory bandwidth to help support your largest data sets and eliminate bottlenecks in moving data in and out of memory. Combine this performance with the MI200’s advanced I/O capabilities and you can push workloads closer to their full potential.

AMD Infinity Architecture

AMD Instinct MI250 Instance Pricing

All pricing below is based on Cirrascale's No Surprises billing model. There are no hidden fees and discounts may apply for long-term commitments depending on the service requested. All pricing shown for servers are per server per month.

OAM Processor Specs System RAM Local Storage Network Hourly Equiv. Pricing* Monthly Pricing 6-Month Pricing Annual Pricing
4X AMD Instinct MI250 Dual 64-Core 1TB (1) 960 NVMe
(1) 3.84TB NVMe
25Gb Bonded $4.00*
($1.25/OAM/hr*)
$3,650 $3,285 $2,920

Get Started Today!

Sign-up to access AMD Instinct Series accelerators and experience the exascale era for yourself.