AMD
GPUWorkstationReleased May 13, 2020

AMD Radeon Pro VII

16 GB HBM2 · 4096-bit · 3,840 cores

The Radeon Pro VII is AMD's workstation graphics card based on the 7 nm Vega 20 GPU, launched on May 13, 2020 at $1,899 for broadcast, engineering simulation and HPC workloads. It enables 60 compute units and 16 GB of ECC-capable HBM2 with 1 TB/s of bandwidth, and its half-rate double-precision support delivers up to 6.5 TFLOPS FP64 alongside 13.1 TFLOPS FP32. Two cards can be linked with AMD Infinity Fabric Link for faster GPU-to-GPU communication.

General

Manufacturer
AMD
Model
Radeon Pro VII
Segment
Workstation
GPU chip
Vega 20
Architecture
GCN 5 (Vega)
Release date
May 13, 2020
Price

Memory

Memory size
16 GB
Memory type
HBM2
Bus width
4096-bit
Bandwidth
1,024 GB/s
Memory clock
1,000 MHz

Clocks & silicon

GPU clock
1,400 MHz
Boost clock
1,700 MHz
Shader units
3,840 Stream Processors (60 CU)
Tensor / AI cores
—
RT cores
—
Transistors
13.23 billion
Technology (nm)
7 nm
TSMC 7 nm
TDP / TBP
250 W

Interface & APIs

Bus interface
PCIe 4.0 x16
SLI / multi-GPU
—
DirectX
12 (12_1)
OpenGL
4.6
Vulkan
1.3
Other APIs
OpenCL 2.0

AI support

Precisions
FP8FP16BF16INT8INT4TF32FP64
AI accelerator
—
Peak AI TOPS
—
Notes
Vega 20 has no dedicated matrix or AI units. It runs packed FP16 math at twice the FP32 rate and FP64 at half the FP32 rate, which AMD rates at 6.5 TFLOPS.
All AMD GPUs →

Workstation gpus from AMD announced around the same time as the AMD Radeon Pro VII. Add any of them to your compare list to see the specs side by side.