2024年11月1日发(作者：笪鸾)
REINVENTING THE WORKSTATION
WITH REAL-TIME RAY TRACING AND AI
/GV100
NVIDIA Quadro GV100
From stunning industrial design to advanced special effects to complex scientific
visualization, and the frontiers of AI and Deep Learning, Quadro is the world’s preeminent
visual computing platform. Only Quadro has the most advanced ecosystem of hardware,
software and tools to transform the disruptive challenges of today into the business
successes of tomorrow – and the new Quadro GV100 exemplifies this trend.
VOLTA GPU ARCHITECTURE
HIGH SPEED HBM2 MEMORY
Built with Volta’s vastly optimized 32GB HBM2 memory
subsystem for the industry’s fastest graphics memory (870 GB/s
sensitive applications handling large datasets. Quadro GV100
offers 2x memory capacity and delivers 20% more memory
bandwidth compared to the previous generation. HBM2 also
capacity or performance penalties.
peak bandwidth), Quadro GV100 is the ideal platform for latency-
Based on state-of-the-art 12nm FFN (FinFET NVIDIA) high-performance
manufacturing process customized for NVIDIA to deliver 5120 CUDA cores,
the Quadro GV100 GPU is the most powerful computing platform for AI,
HPC, graphics, rendering and VR workloads on professional desktops. It
includes 21.1 billion transistors on die size of 815 mm
2
. 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 performance, it
supports a wide range of compute-intensive workloads flawlessly.
provides native support for Error Correcting Code (ECC) without
TENSOR CORES
New mixed-precision cores purpose-built for deep learning matrix
arithmetic, delivers 8x TFLOPS for training, compared to the previous
performs 64 floating point fused multiply-add (FMA) operations per
operations per clock.
generation. Quadro GV100 utilizes 640 Tensor Cores; each Tensor Core
clock, and each SM performs a total of 1024 individual floating point
MIXED-PRECISION COMPUTING
Double the throughput and reduce storage requirements with
and deployment of more sophisticated neural networks. With
16-bit floating point precision computing to enable the training
independent parallel integer and floating point data paths, the
Volta SM (Streaming Multiprocesssor) is also much more efficient on
workloads with a mix of computation and addressing calculations.
To learn more about the NVIDIA Quadro GV100, email *************
PNY Technologies, Inc. 100 Jefferson Road, Parsippany, NJ 07054 | Tel 973-515-9700 | Fax 973-560-5590 | /PNYPRO
Features and specifications subject to change without notice. The PNY logo is a registered trademark of PNY Technologies, Inc.
All other trademarks are the property of their respective owners. © 2018 PNY Technologies, Inc. All rights reserved.
REINVENTING THE
WORKSTATION FOR AI
NVIDIA QUADRO GV100
The Power To Accelerate AI-
Enhanced Workflows
The NVIDIA
®
Quadro
®
GV100 reinvents the workstation
to meet the demands of AI-enhanced design and
visualization workflows. It’s powered by NVIDIA Volta,
delivering extreme memory capacity, scalability, and
performance that designers, architects, and scientists
need to create, build, and solve the impossible.
> Work with full fidelity, massive datasets
> Enjoy fluid visual interactivity with AI-accelerated denoising
FEATURES
> Four DisplayPort 1.4
Connectors
3
> DisplayPort with Audio
> 3D Stereo Support with
Stereo Connector
3
> NVIDIA GPUDirect
™
Support
> NVIDIA NVLink Support
1
> Quadro Sync II
4
Compatibility
> NVIDIA nView
®
Desktop
Management Software
> HDCP 2.2 Support
> NVIDIA Mosaic
5
PNY PART NUMBER
SPECIFICATIONS
GPU Memory
Memory Interface
Memory Bandwidth
ECC
NVIDIA CUDA Cores
NVIDIA Tensor Cores
Single-Precision Performance
Tensor Performance
NVIDIA NVLink
NVIDIA NVLink bandwidth
System Interface
Max Power Consumption
Thermal Solution
Form Factor
Display Connectors
Max Simultaneous Displays
Display Resolution
VCQGV100-PB
32 GB HBM2
4096-bit
Up to 870 GB/s
Yes
5,120
640
14.8 TFLOPS
118.5 TFLOPS
Connects 2 Quadro GV100 GPUs
2
200 GB/s
PCI Express 3.0 x 16
250 W
Active
4.4” H x 10.5” L, Dual Slot, Full
Height
4x DP 1.4
4 direct, DP 1.4
4x 4096x2160 @ 120 Hz
4x 5120x2880 @ 60 Hz
2x 7680x4320 @ 60 Hz
Yes
Shader Model 5.1,
OpenGL 4.5
6
,
DirectX 12.0
7
,
Vulkan 1.0
6
CUDA, DirectCompute, OpenCL™
Supercharge Rendering with AI
Bring Optimal Designs to Market Faster
PACKAGE CONTENTS
> NVIDIA Quadro GV100
> Quick Start Guide
> Quadro Support Guide
> 4 DisplayPort to DVI
Adapters
> 1 DisplayPort to HDMI
Adapter
> 1 Stereo Connector Bracket
> 1 Auxiliary Power Cable
(8-pin to dual 6-pin adapter)
> Work with higher fidelity CAE simulation models
> Explore more design options with faster solver performance
Enjoy Ultimate Immersive Experiences
Double-Precision Performance7.4 TFLOPS
> Work with complex, photoreal datasets in VR
> Enjoy optimal NVIDIA Holodeck experience
Realize New Opportunities with AI
> Access DL frameworks for AI development via NVIDIA NGC
> Accelerate AI training/inferencing with Tensor Cores and
NVLink
All Quadro cards are certified with a broad range of
professional applications, tested by leading workstation
manufacturers, and backed by a global team of support
specialists to give you the peace of mind to focus on doing
your best work.
WARRANTY AND
SUPPORT
> 3-Year Warranty
> Pre- and Post-Sales
Technical Support
> Dedicated Field Application
Engineers
> Direct Tech Support Hot
Lines
To learn more about the NVIDIA Quadro GV100 visit
/quadro
1
VR Ready
Graphics APIs
NVIDIA NVLink sold separately |
2
Connecting two GV100 cards with NVLink to scale
performance and memory capacity to 64 GB is only possible if your application supports
NVLink technology. Please contact your application provider to confirm their support of
NVLink. |
3
VGA/DVI/HDMI/stereo support via adapter/connector/bracket |
4
Quadro
Sync II card sold separately |
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 /
conformance |
7
GPU supports DX 12.0 API, Hardware Feature Level 12_1
© 2018 NVIDIA Corporation and PNY. All rights reserved. NVIDIA, the NVIDIA logo, Quadro,
nView, NVLink, CUDA, GPUDirect, and NVIDIA Volta are trademarks and/or registered
trademarks of NVIDIA Corporation in the U.S. and other countries. The PNY logotype is a
registered trademark of PNY Technologies. OpenCL is a trademark of Apple Inc. used under
license to the Khronos Group Inc. All other trademarks and copyrights are the property of
their respective owners. MAR18
Compute APIs
PNY Technologies, Inc.
100 Jefferson Road, Parsippany, NJ 07054
Tel 408 567 5500 | Fax 408 855 0680
For more information visit: /quadro
2024年11月1日发(作者：笪鸾)
REINVENTING THE WORKSTATION
WITH REAL-TIME RAY TRACING AND AI
/GV100
NVIDIA Quadro GV100
From stunning industrial design to advanced special effects to complex scientific
visualization, and the frontiers of AI and Deep Learning, Quadro is the world’s preeminent
visual computing platform. Only Quadro has the most advanced ecosystem of hardware,
software and tools to transform the disruptive challenges of today into the business
successes of tomorrow – and the new Quadro GV100 exemplifies this trend.
VOLTA GPU ARCHITECTURE
HIGH SPEED HBM2 MEMORY
Built with Volta’s vastly optimized 32GB HBM2 memory
subsystem for the industry’s fastest graphics memory (870 GB/s
sensitive applications handling large datasets. Quadro GV100
offers 2x memory capacity and delivers 20% more memory
bandwidth compared to the previous generation. HBM2 also
capacity or performance penalties.
peak bandwidth), Quadro GV100 is the ideal platform for latency-
Based on state-of-the-art 12nm FFN (FinFET NVIDIA) high-performance
manufacturing process customized for NVIDIA to deliver 5120 CUDA cores,
the Quadro GV100 GPU is the most powerful computing platform for AI,
HPC, graphics, rendering and VR workloads on professional desktops. It
includes 21.1 billion transistors on die size of 815 mm
2
. 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 performance, it
supports a wide range of compute-intensive workloads flawlessly.
provides native support for Error Correcting Code (ECC) without
TENSOR CORES
New mixed-precision cores purpose-built for deep learning matrix
arithmetic, delivers 8x TFLOPS for training, compared to the previous
performs 64 floating point fused multiply-add (FMA) operations per
operations per clock.
generation. Quadro GV100 utilizes 640 Tensor Cores; each Tensor Core
clock, and each SM performs a total of 1024 individual floating point
MIXED-PRECISION COMPUTING
Double the throughput and reduce storage requirements with
and deployment of more sophisticated neural networks. With
16-bit floating point precision computing to enable the training
independent parallel integer and floating point data paths, the
Volta SM (Streaming Multiprocesssor) is also much more efficient on
workloads with a mix of computation and addressing calculations.
To learn more about the NVIDIA Quadro GV100, email *************
PNY Technologies, Inc. 100 Jefferson Road, Parsippany, NJ 07054 | Tel 973-515-9700 | Fax 973-560-5590 | /PNYPRO
Features and specifications subject to change without notice. The PNY logo is a registered trademark of PNY Technologies, Inc.
All other trademarks are the property of their respective owners. © 2018 PNY Technologies, Inc. All rights reserved.
REINVENTING THE
WORKSTATION FOR AI
NVIDIA QUADRO GV100
The Power To Accelerate AI-
Enhanced Workflows
The NVIDIA
®
Quadro
®
GV100 reinvents the workstation
to meet the demands of AI-enhanced design and
visualization workflows. It’s powered by NVIDIA Volta,
delivering extreme memory capacity, scalability, and
performance that designers, architects, and scientists
need to create, build, and solve the impossible.
> Work with full fidelity, massive datasets
> Enjoy fluid visual interactivity with AI-accelerated denoising
FEATURES
> Four DisplayPort 1.4
Connectors
3
> DisplayPort with Audio
> 3D Stereo Support with
Stereo Connector
3
> NVIDIA GPUDirect
™
Support
> NVIDIA NVLink Support
1
> Quadro Sync II
4
Compatibility
> NVIDIA nView
®
Desktop
Management Software
> HDCP 2.2 Support
> NVIDIA Mosaic
5
PNY PART NUMBER
SPECIFICATIONS
GPU Memory
Memory Interface
Memory Bandwidth
ECC
NVIDIA CUDA Cores
NVIDIA Tensor Cores
Single-Precision Performance
Tensor Performance
NVIDIA NVLink
NVIDIA NVLink bandwidth
System Interface
Max Power Consumption
Thermal Solution
Form Factor
Display Connectors
Max Simultaneous Displays
Display Resolution
VCQGV100-PB
32 GB HBM2
4096-bit
Up to 870 GB/s
Yes
5,120
640
14.8 TFLOPS
118.5 TFLOPS
Connects 2 Quadro GV100 GPUs
2
200 GB/s
PCI Express 3.0 x 16
250 W
Active
4.4” H x 10.5” L, Dual Slot, Full
Height
4x DP 1.4
4 direct, DP 1.4
4x 4096x2160 @ 120 Hz
4x 5120x2880 @ 60 Hz
2x 7680x4320 @ 60 Hz
Yes
Shader Model 5.1,
OpenGL 4.5
6
,
DirectX 12.0
7
,
Vulkan 1.0
6
CUDA, DirectCompute, OpenCL™
Supercharge Rendering with AI
Bring Optimal Designs to Market Faster
PACKAGE CONTENTS
> NVIDIA Quadro GV100
> Quick Start Guide
> Quadro Support Guide
> 4 DisplayPort to DVI
Adapters
> 1 DisplayPort to HDMI
Adapter
> 1 Stereo Connector Bracket
> 1 Auxiliary Power Cable
(8-pin to dual 6-pin adapter)
> Work with higher fidelity CAE simulation models
> Explore more design options with faster solver performance
Enjoy Ultimate Immersive Experiences
Double-Precision Performance7.4 TFLOPS
> Work with complex, photoreal datasets in VR
> Enjoy optimal NVIDIA Holodeck experience
Realize New Opportunities with AI
> Access DL frameworks for AI development via NVIDIA NGC
> Accelerate AI training/inferencing with Tensor Cores and
NVLink
All Quadro cards are certified with a broad range of
professional applications, tested by leading workstation
manufacturers, and backed by a global team of support
specialists to give you the peace of mind to focus on doing
your best work.
WARRANTY AND
SUPPORT
> 3-Year Warranty
> Pre- and Post-Sales
Technical Support
> Dedicated Field Application
Engineers
> Direct Tech Support Hot
Lines
To learn more about the NVIDIA Quadro GV100 visit
/quadro
1
VR Ready
Graphics APIs
NVIDIA NVLink sold separately |
2
Connecting two GV100 cards with NVLink to scale
performance and memory capacity to 64 GB is only possible if your application supports
NVLink technology. Please contact your application provider to confirm their support of
NVLink. |
3
VGA/DVI/HDMI/stereo support via adapter/connector/bracket |
4
Quadro
Sync II card sold separately |
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 /
conformance |
7
GPU supports DX 12.0 API, Hardware Feature Level 12_1
© 2018 NVIDIA Corporation and PNY. All rights reserved. NVIDIA, the NVIDIA logo, Quadro,
nView, NVLink, CUDA, GPUDirect, and NVIDIA Volta are trademarks and/or registered
trademarks of NVIDIA Corporation in the U.S. and other countries. The PNY logotype is a
registered trademark of PNY Technologies. OpenCL is a trademark of Apple Inc. used under
license to the Khronos Group Inc. All other trademarks and copyrights are the property of
their respective owners. MAR18
Compute APIs
PNY Technologies, Inc.
100 Jefferson Road, Parsippany, NJ 07054
Tel 408 567 5500 | Fax 408 855 0680
For more information visit: /quadro