Radeon Instinct MI60

Unleash Discovery on the World’s Fastest Double Precision PCIe® Accelerator1

The Radeon Instinct™ MI60 compute card is designed to deliver high levels of performance for deep learning, high performance computing (HPC), cloud computing, and rendering systems. This new accelerator is designed with optimized deep learning operations, class-leading double precision performance1, and hyper-fast HBM2 memory delivering 1 TB/s memory bandwidth speeds.

Scale your datacenter server designs with AMD’s Infinity Fabric™ Link technology by directly connecting up to 2 GPU hives of 4 MI60 GPUs in a single server at up to 6x the speed of PCIe® 3.02.

Quickly achieve reliable and accurate results in large-scale system deployments with the new Radeon Instinct™ MI60 which are equipped with full-chip ECC3 and RAS capabilities4.

Combine this finely balanced and ultra-scalable solution with our ROCm open ecosystem that includes Radeon Instinct optimized MIOpen libraries supporting frameworks like TensorFlow, PyTorch, Caffe 2 and others, and you have a solution ready for the next era of compute and machine intelligence.

Key Features

Based on “Vega 7nm” Technology with 64 supercharged Compute Units (4096 Stream Processors)

Up to 59 TOPS INT8 Performance for Inference Workloads

Up to 29.5 TFLOPS FP16 and 14.7 TFLOPS FP32 Performance for Training Workloads

Up to 7.4 TFLOPS Double Precision for HPC

32 GB Ultra-fast HBM2 ECC Memory with up to 1 TB/s Memory Bandwidth

The World’s First PCIe® Gen 4 x16 Capable GPU5

AMD Infinity Fabric™ Link technology– up to 200 GB/s peer-to-peer GPU communication speeds

ROCm Open Ecosystem

many photos

Optimized for Deep Learning

The Radeon Instinct™ MI60 compute GPU is equipped with optimized deep learning operations to drive the latest workflows in AI and deep learning. The MI60’s superior 29.5 TFLOPS of native half-precision (FP16) and 14.7 TFLOPS single-precision (FP32) peak floating point performance running across 64 Compute Units (4,096 stream processors), combined with its advanced High Bandwidth Cache Controller and 32GB of HBM2 ECC3 memory, brings customers supercharged compute capabilities to meet today’s demanding system requirements of handling large data efficiently for training these complex neural networks used in deep learning.

Blue Server Room

The World’s Fastest Double Precision PCIe® Accelerator1

For High Performance Compute

For High Performance Compute (HPC) workloads, the Radeon Instinct™ MI60 accelerator delivers the world’s fastest double precision performance1, allowing scientists and researches across the globe to more efficiently process HPC parallel codes across several industries including life sciences, energy, finance, automotive and aerospace, academics, government, defense and more. AMD’s next-generation HPC solutions are designed to deliver optimal compute density and performance per node with the efficiency required to handle today’s massively parallel data-intensive codes; as well as, to provide a powerful, flexible solution for general purpose HPC deployments. The ROCm software platform brings a scalable HPC-class solution that provides fully open-source Linux drivers, HCC compilers, tools and libraries to give scientists and researchers system control down to the metal.

ROCm logo

ROCm, a New Era in Open GPU Computing

Platform for GPU-enabled HPC and deep learning.

Radeon Vega 7nm

“Vega 7nm” Graphics Technology

Improved Performance per Watt, Optimized Deep Learning Operations and much more!

Instinct™ MI60

GPU Specifications
GPU Architecture
Vega20
Lithography
TSMC 7nm FinFET
Stream Processors
4096
Compute Units
64
Peak Engine Clock
1800 MHz
Peak Half Precision (FP16) Performance
29.5 TFLOPs
Peak Single Precision (FP32) Performance
14.7 TFLOPs
Peak Double Precision (FP64) Performance
7.4 TFLOPs
Peak INT8 Performance
58.9 TFLOPs
OS Support
Linux x86_64
GPU Memory
Memory Size
32 GB
Memory Type (GPU)
HBM2
Memory Interface
4096-bit
Memory Clock
1 GHz
Memory Bandwidth
1024 GB/s
Memory ECC Support
Yes (Full-Chip)
Board Specifications
Form Factor
PCIe Add-in Card
Bus Type
PCIe 4.0 x16
PCIe 3.0 x16
TDP
300W
Cooling
Passive
Board Width
Double Slot
Board Length
10.5" (267 mm)
Board Height
Full Height
External Power Connectors
1x PCIe 6-pin, 1x PCIe 8-pin
Additional Features
RAS Support
Yes
Software API Support
OpenGL
4.6
OpenCL
2.0
Vulkan
1.0
Product Basics
Product Family
Radeon Instinct™
Product Line
Radeon Instinct™ MI Series
Platform
Server
Launch Date
11/18/2018