Radeon Instinct™ MI8 Accelerator

Scalable accelerator for machine and deep learning inference applications.

Based on the “Fiji” GRAPHICS ARCHITECTURE built to tackle machine and deep learning applications

64 COMPUTE UNITS to accelerate demanding workloads

Up to 8.2 TFLOPS of peak FP32 and FP16 compute performance to speed up compute intensive machine intelligence

47 GFLOPS/watt peak FP16/FP32 performance. Offering amazing performance-per-watt for machine intelligence and deep learning inference applications

State-of-the-art memory technology: 4GB of HBM MEMORY

Passively cooled, 175W TDP board power – designed to fit in most standard server designs

MxGPU for Virtualized Compute Workloads – drive greater utilization and capacity in the data center

ROCm Software Platform provides open source Hyperscale and HPC-class solutions

ROCm logo

ROCm, a New Era in Open GPU Computing

Platform for GPU-enabled HPC and ultrascale computing.

The Ultimate Solution for Your Computing Needs

machine intelligence digital brain abstract image

Inference for Deep Learning

  • ROCm software platform provides open source Hyperscale platform
  • Open source Linux drivers, HCC compiler, tools and libraries for full control from the metal forward
  • Optimized MIOpen Deep Learning framework libraries
  • Large BAR support for mGPU peer to peer
  • MxGPU SR-IOV hardware virtualization for optimized system utilizations
  • Open industry standard support of multiple architectures and industry standard interconnect technologies
HPC

HPC Heterogeneous Compute

  • ROCm software platform provides open source HPC-Class platform
  • Open source Linux drivers, HCC compiler, tools and libraries for full control from the metal forward
  • MxGPU SR-IOV hardware virtualization for optimized system utilizations
  • Open industry standard support of multiple architectures and industry standard interconnect technologies

Instinct™ MI8

GPU Specifications
GPU Architecture
Graphics Core Next (GCN) 3rd Gen
Lithography
28nm
Stream Processors
4096
Peak Half Precision (FP16) Performance
8.19 TFLOPs
Peak Single Precision (FP32) Performance
8.19 TFLOPs
Peak Double Precision (FP64) Performance
512 GFLOPs
GPU Memory
Memory Size
4 GB
Memory Type (GPU)
High Bandwidth Memory (HBM)
Memory Bandwidth
512 GB/s
Memory ECC Support
No
Board Specifications
Form Factor
PCIe Add-in Card
Bus Type
PCIe 3.0 x16
TDP
175W
Cooling
Passive
Board Width
Double Slot
Board Length
6.0" (152 mm)
Board Height
Full Height
External Power Connectors
1x PCIe 8-pin
Additional Features
OpenCL 2.0
Software API Support
DirectX
12.0 (feature level 12_0)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.0
Product Basics
Radeon Instinct™
Radeon Instinct™ MI Series
Platform
Server
Launch Date
June 2017