Introduction | |
---|---|
The Ultimate Solution for Your Computing Needs Machine Intelligence and Deep Learning Neural Network Training - High performance FP16 and FP32 compute - Open software ROCm platform for HPC-class rack scale - Optimized MIOpen deep learning framework libraries - Large BAR support for mGPU peer to peer - Superior compute density and performance per node when combining AMD EPYCT server processor and Radeon InstinctT accelerators HPC Heterogeneous Compute - Outstanding compute density and performance per node - Open software ROCm platform for HPC class rack scale - Open source Linux drivers, HCC compiler, tools and libraries from the metal forward - Open industry standard support of multiple architectures and industry standard interconnect technologies |
|
Processor | |
Graphics processor family | AMD |
Graphics processor | Radeon RX Vega 64 |
Stream processors | 4096 |
Memory | |
Discrete graphics card memory | 16 GB |
Graphics card memory type | High Bandwidth Memory 2 (HBM2) |
Memory bus | 2048 bit |
Bandwidth | 484 GHz |
Ports & interfaces | |
Interface type | PCI Express x16 3.0 |
Performance | |
DirectX version | 12.0 |
OpenGL version | 4.6 |
OpenCL version | 2.0 |
Design | |
Cooling type | Passive |
Product colour | Black |
Power | |
Power consumption (typical) | 300 W |
Supplementary power connectors | 2x 8-pin |
Weight & dimensions | |
Width | 267 mm |
Every effort has been made to ensure the accuracy of all information contained herein. e-nitiative shall not be liable for any changes resulting in wrong product description, tax code and/or price. The shown information (specifications, prices, taxes) should be considered as an indication and can be changed at any moment and without any prior notice.