NVIDIA Quadro GV100
Unmatched Power. Unmatched Creative Freedom.
AI, photo realistic rendering, simulation, and VR are transforming professional workflows. Engineers can now create groundbreaking products faster. Architects can design buildings that could only have existed in their imaginations. And artists can render complex photorealistic scenes in seconds instead of hours. As applications continue to be enhanced with these technologies, professional computing tools need to keep pace.
The NVIDIA® Quadro® GV100 is reinventing the workstation to meet the demands of these next-generation workflows. It’s powered by NVDIA Quadro Volta, delivering the extreme memory capacity, scalability, and performance that designers, architects, and scientists need to create, build, and solve the impossible.
Based on a state-of-the-art 12nm FFN (FinFET NVIDIA) high-performance manufacturing process customized for NVIDIA to incorporate 5120 CUDA cores, the NVIDIA Quadro GV100 GPU is the most powerful computing platform for HPC, AI, VR and graphics workloads on professional desktops. Able to deliver more than 7.4 TFLOPS of double-precision (FP64), 14.8 TFLOPS of single-precision (FP32), 29.6 TFLOPS of half-precision (FP16), 59.3 TOPS of integer-precision (INT8), and 118.5 TFLOPs of tensor operation capability, it supports a wide range of compute-intensive workloads flawlessly.
New mixed-precision Tensor Cores purpose-built for deep learning matrix arithmetic, deliver an 8x boost in TFLOPS performance for training, compared to the previous generation. NVIDIA Quadro GV100 utilizes 640 Tensor Cores; each Tensor Core performs 64 floating point fused multiply-add (FMA) operations per clock, and each SM performs a total of 1024 individual floating point operations per clock.
NVIDIA Quadro GV100 Features
Full-Scene Antialiasing (FSAA)
Dramatically reduce visual aliasing artifacts or “jaggies” with up to 64x FSAA (128x with SLI HB or NV Link) for unparalleled image quality and highly realistic scenes.
32K Texture and Render Processing
Texture from and render to 32K x 32K surfaces to support applications that demand the highest resolution and quality image processing.
NVIDIA Quadro MOSAIC Technology
Transparently scale the desktop and applications across up to 8 GPUs and 32 displays from a single workstation while delivering full performance and image quality.
DisplayPort 1.4
Support up to four 5K monitors at 60Hz, or dual 8K displays at 60Hz per card. NVIDIA Quadro GV100 supports HDR color for 4K at 60Hz, 10/12b HEVC decode and up to 4K at 60Hz for 10b HVEC encode. Each DisplayPort connector is capable or driving ultra-high resolutions of 4096 x 2160 at 120 Hz with 30-bit color.
NVIDIA Quadro View
NVIDIA Quadro View desktop management software helps you organize single- or multi-monitor workspaces with ease. Divide your workspace into regions to snap applications into place. Save profiles with pre-set configurations for your workflows. And set up hotkeys to quickly access common functions. Quadro View delivers the tools you need to take charge of your desktop.
NVIDIA Quadro Experience
NVIDIA Quadro Experience delivers productivity tools that simplify time-consuming tasks so you can get things done faster. Keep your Quadro driver up to date with automatic alerts so your system is always optimized for performance. Capture content in 4K and upload to your favorite third-party sites, broadcast live, or stream to your NVIDIA Shield for effortless collaboration. Get a suite of display management tools with NVIDIA Quadro View software. Even enjoy great gaming with just one click. NVIDIA Quadro Experience is the ultimate productivity companion to your Quadro graphics card.
NVIDIA Quadro Sync II
Synchronize the display and image output of up to 32 displays from 8 GPUs (connected through two NVIDIA Quadro Sync II boards) in a single system, reducing the number of systems needed to create an advanced video visualization environment.
GPU Memory : | 32 GB HBM2 |
Memory Interface : | 4096-bit |
Memory Bandwidth : | Up to 870 GB/s |
ECC : | Yes |
NVIDIA CUDA Cores : | 5120 |
NVIDIA Tensor Cores : | 640 |
Double-Precision Performance : | 7.4 TFLOPS |
Single-Precision Performance : | 14.8 TFLOPS |
Tensor Performance : | 118.5 TFLOPS |
NVIDIA NVLink : | Connects 2 Quadro GV100 GPUs2 |
NVIDIA NVLink bandwidth : | 200 GB/s |
System Interface : | PCI Express 3.0 x 16 |
Max Power Consumption : | 250 W |
Thermal Solution : | Active |
Form Factor : | 4.4” H x 10.5” L, Dual Slot, Full Height |
Display Connectors : | 4 x DP 1.4 |
Max Simultaneous Displays : | 4 direct, DP 1.4 |
Display Resolution : | 4 x 4096 x 2160 @ 120 Hz 4 x 5120 x 2880 @ 60 Hz 2 x 7680 x 4320 @ 60 Hz |
VR Ready : | Yes |
Graphics APIs : | Shader Model 5.1, OpenGL 4.56, DirectX 12.07, Vulkan 1.06 |
Compute APIs : | CUDA, Direct Compute, OpenCL |