Today, AMD introduced its high-end graphics card, the Radeon Pro VII, for the workstations build on the 7nm process. Radeon Pro VII is the top-range GPU of the company for professional work burden.
The Radeon Pro VII is packed with 16GB HBM2 GPU memory with full EEC support and delivers a memory bandwidth of 1TB/s.
It likewise features assistance for innovations such as Infinity Fabric Link, which enables 2 GPUs to link to each other and share the memory with a low-latency connection, and PCIe 4.0, assuring double the bandwidth of PCIe 3.0.
Radeon Pro VII Specifications
|GPU Specifications||GPU Architecture: Vega20|
Lithography: TSMC 7nm FinFET
Stream Processors: 3840
Compute Units: 60
Peak Single Precision (FP32) Performance: 13.1 TFLOPs
Peak Double Precision (FP64) Performance: 6.5 TFLOPs
|GPU Memory||Memory Size: 16 GB|
Memory Type (GPU): HBM2
Memory Interface: 4096-bit
Memory Bandwidth: 1024 GB/s
Memory ECC Support: Yes
|Board Specifications||Form Factor: PCIe® Add-in Card|
Bus Type: PCIe® 4.0 x16
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
|Display Outputs||DisplayPort: 6x DisplayPort 1.4|
|Additional Features||Supported Technologies|
AMD Remote Workstation
Radeon Media Engine
Radeon Pro Software
Radeon VR Ready Creator
AMD Eyefinity Technology (Professionals)
|Software API Support||DirectX: 12.0 (feature level 12_1)|
The performance comparison in various software are as follows:
The high-end GPU will be available in the mid of June, and it will cost $1899 (separate buy). The new GPU with the workstations will be available in the H2 of 2020.