NVIDIA Quadro GP100 Professional Graphics Card

Product status: Released | Report Error
Overview
Manufacturer
NVIDIA
Original Series
Quadro Pascal
Release Date
February 6th, 2017
Graphics Processing Unit
GPU Model
GP100
Architecture
Pascal
Fabrication Process
16 nm FinFET
Die Size
610 mm2
Transistors Count
15.3B
Transistors Density
25.1M TRAN/mm2
CUDAs
3584
TMUs
224
ROPs
128
Clocks
Base Clock
1437 MHz
Boost Clock
1437 MHz
Memory Clock
350 MHz
Effective Memory Clock
700 Mbps
Memory Configuration
Memory Size
16384 MB
Memory Type
HBM2
Memory Bus Width
4096-bit
Memory Bandwidth
358.4 GB/s
Technologies
  • NVIDIA NVLINK
  • NVIDIA PhysX

VideoCardz.com

Physical
Interface
PCI-Express 3.0 x16
Height
2-slot
Power Connectors
1 × 8-pin
TDP/TBP
235 W
Recommended PSU
600 W
Multi-GPU Support
2-way
Display Outputs
DVI-I DualLink
1 ×
DisplayPort
4 ×
API Support
DirectX
12.0
Vulkan
1.0
OpenGL
4.5
OpenCL
1.2
Shader Model
5.0

Performance
Pixel Fillrate
183.9 GPixels/s
Texture Fillrate
321.9 GTexel/s
SPFP Performance
10.3 TFLOPS
Performance per W
43.8 GFLOPS/W
Performance per mm2
16.9 GFLOPS/mm2





 ModelClocksMemory
NVIDIA Quadro P6000
3840 Unified Cores
1417 / 1126 MHz 24 GB GDDR5X
NVIDIA Quadro GP100
3584 Unified Cores
1437 / 350 MHz 16 GB HBM2
NVIDIA Quadro P5000
2560 Unified Cores
1607 / 1126 MHz 16 GB GDDR5
NVIDIA Quadro P4000
1792 Unified Cores
1480 / 1901 MHz 8 GB GDDR5
NVIDIA Quadro P2000
1024 Unified Cores
1470 / 1750 MHz 5 GB GDDR5
NVIDIA Quadro P1000
640 Unified Cores
1400 / 1275 MHz 4 GB GDDR5
NVIDIA Quadro P600
384 Unified Cores
1430 / 1000 MHz 2 GB GDDR5
NVIDIA Quadro P400
256 Unified Cores
1170 / 1000 MHz 2 GB GDDR5
 ModelClocksMemory
NVIDIA Tesla P100 SMX2
3584 Cores
1328 / 704 MHz 16 GB HBM2
NVIDIA Tesla P100 PCIe
3584 Cores
1189 / 714 MHz 16 GB HBM2
NVIDIA Quadro GP100
3584 Cores
1437 / 350 MHz 16 GB HBM2
NVIDIA DGX-1
28672 Cores
1328 / 704 MHz 128 GB HBM2
NVIDIA Tesla P100 PCIe 12GB (V)
3584 Cores
1189 / 357 MHz 12 GB HBM2

World’s Most Advanced Visual Computing Accelerator.

The NVIDIA Quadro GP100, powered by the Pascal GPU architecture, is equipped with the most advanced visualization and simulation capabilities to meet the needs of the most demanding professional workflows. A single GP100 with 3580 FP32/1792 FP64 CUDA cores has incredible horsepower to render photorealistic design concepts interactively, create extremely detailed 3D models, run intensive CAE simulations to validate designs, and evaluate design prototypes in immersive VR. You can even connect two GP100 boards with NVIDIA NVLink™ technology1 to scale performance with an amazing 32 GB of combined HBM2 ultra-high bandwidth memory.2

The GP100 is an excellent choice for developers who want to tap into the power of NVLink and Unified Memory to maximize their application performance. Additionally, its fast FP16 performance makes it an ideal desktop workstation solution for developers working on the latest Deep Learning/AI algorithms and frameworks.

Quadro cards are certified with a broad range of sophisticated professional applications, tested by leading workstation manufacturers, and backed by a global team of support specialists. This gives you the peace of mind to focus on doing your best work. Whether you’re developing revolutionary products or telling spectacularly vivid visual stories, Quadro gives you the performance to do it brilliantly.

(1)  NVIDIA NVLink sold separately | 2 Access to 32 GB of memory via NVLink requires specific application support. | 3 VGA/DVI/HDMI/stereo support via adapter/connector/bracket | 4 GP100 and Quadro Sync II bundles available | 5 Windows 7, 8, 8.1, 10 and Linux | 6 Product is based on a published Khronos Specification, and is expected to pass the Khronos Conformance Testing Process when available. Current conformance status can be found at www.khronos.org/conformance | 7 GPU supports DX 12.0 API, Hardware Feature Level 12_1