Vega GPU Architecture

The Radeon Pro WX 9100 graphics card is based on AMD’s cutting edge “Vega” GPU architecture, purpose-built to handle big data sets and a diverse range of computational workloads.

Up to 12.29 TFLOPS of peak single-precision floating-point performance

The Radeon Pro WX 9100 offers up to 12.29 TFLOPS peak SPFP. This is tremendous compute power that can be used to speed up professional applications where high performance is paramount, from rendering video effects to visualizing complex simulations.

64 Next-Generation Compute Units (nCUs, 4096 Stream Processors) with support for double-rate 16-bit math

New compute unit design provides super-charged pathways to provide double the processing throughput when using 16-bit data types, accelerating demanding workloads including image/video processing, ray tracing, and artificial intelligence.

OpenCL 2.0 Support

Enables professionals to tap into the parallel computing power of modern GPUs and multi-core CPUs to accelerate compute-intensive tasks in leading CAD/CAM/CAE and Media & Entertainment applications that support OpenCL.

AMD Secure Processor

Radeon Pro WX 9100 workstation graphics takes a holistic approach to security with a dedicated AMD Secure Processor built in. A secure environment is created by carving out a virtual “secure world” in the GPU. IP-sensitive tasks are run on the AMD Secure Processor while other tasks are run in “standard operation.” This helps ensure the secure storage and processing of sensitive data and trusted applications. It also helps protect the integrity and confidentiality of key resources, such as the user interface and service provider assets.

The AMD Secure Processor is designed to facilitate all-day security. As soon as you power on your computer, the onboard AMD Secure Processor performs boot and firmware validation. During use, the AMD Secure Processor works in tandem with Microsoft’s Device Guard to thwart malicious attacks. During shutdown, the AMD Secure Processor continues securing graphics bound IP until device termination.

High Bandwidth Cache Controller (HBCC)

The state of the art memory system found on the “Vega” GPU architecture removes the capacity limitations of traditional GPU memory. Thanks to automatic, fine-grained memory movement controlled by the high bandwidth cache controller, “Vega” GPUs equipped with HBCC enables creators and designers to work with much larger, more detailed models and assets in real time.

16GB High Bandwidth Cache

The Radeon Pro WX 9100 workstation graphics card employs cutting-edge HBM2 memory as an extremely large and ultra-fast hardware managed cache for external memory or storage devices. This allows the cards to efficiently access up to hundreds of terabytes of graphics memory, making it the ideal graphics card for handling massive textures and data sets.

Error Correcting Code (ECC) Memory

Helps ensure the accuracy of your computations by correcting any single or double bit error as a result of naturally occurring background radiation. 1

Efficient Geometry Engine

The new geometry pipe in the “Vega” GPU architecture processes millions of polygons due to its efficient load balancing. The Radeon™ Pro WX 9100 offers up to 2.6x peak geometry throughput per clock 2 to significantly speed up modelling and design workflows in various rendering engines. Modelling applications will be able to render in real-time heavy 3D models and large scenes.

Enhanced Pixel Engine

Updated rasterizer technology to improve cache locality and overdraw, enhancing rendering efficiency and leaving more headroom to crank up quality settings while maintaining smooth 3D rendering.

10-bit Color

Native support for 10-bits per color channel for color-critical tasks. Driving an effective 30-bits per pixel, the Radeon™ Pro WX 9100 is great for any workload requiring that level of detail and color precision.

Comprehensive API Support

The “Vega” GPU architecture supports the latest programming interfaces for graphics and compute tasks, including Vulkan 1.0, OpenGL® 4.5, OpenCL 2.0, and DirectX 12. Coupled with support for API extensions through AMD’s GPUOpen initiative, the Radeon Pro WX 9100 comes ready to handle both current and future applications.

AMD LiquidVR Technology 3

AMD is making VR as comfortable as possible by lowering motion-to-photon latency. Enhance design realism and maintain ultra-immersive VR presence. Enjoy liquid-smooth visual performance and ultra-high frame rates – and cross over to the other side of realistic virtual environments and interaction. 4

Radeon VR Ready Creator 4

Enable extraordinary performance and world-class innovation with Radeon VR Ready Creator products like the Radeon Pro WX 9100. Empower VR content creators and experience designers with amazingly powerful and capable development tools in the AMD LiquidVR SDK.

AMD Eyefinity Technology

Industry-leading multi-display technology enabling highly immersive and unrivaled multi-tasking across multiple displays 3, powered by a single Radeon Pro WX 9100 graphics card.

Ultra-High Definition Display Support

The Radeon Pro WX 9100 workstation graphics cards support the latest display resolutions up to 8K

4K Accelerated Encode/Decode

Multi-stream hardware H.265 HD encode/decode for power-efficient and quick video encoding and playback. 5

TrueAudio Next Technology

High fidelity physically-based audio rendering technology, based on Radeon Rays and utilizing the power of dedicated compute units. This feature is perfect for creating and editing immersive Virtual Reality experiences.

Energy Efficient Design

Radeon Pro WX 9100 workstation graphics cards supports unique power monitoring and management technologies, and has a maximum power consumption of 250 watts TDP board power. AMD PowerTune technology dynamically optimizes GPU power usage and AMD ZeroCore Power technology significantly reduces power consumption at idle. 3