NVIDIA HGX-1 Professional Computing Solution

8x Tesla V100

Product status: Released | Report Error
Overview
Manufacturer
NVIDIA
Original Series
Tesla Volta
Release Date
May 10th, 2017
Graphics Processing Unit
GPU Model
8× GV100
Architecture
Volta
Fabrication Process
14 nm FinFET
Die Size
8× 815 mm2
Transistors Count
8× 21.1B
Transistors Density
25.9M TRAN/mm2
CUDAs
8× 5120 (40960)
SM
8× 80 (640)
GPCs
8× 6 (48)
TMUs
8× 320 (2560)
Clocks
Base Clock
1455 MHz
Boost Clock
1455 MHz
Memory Clock
880 MHz
Effective Memory Clock
1760 Mbps
Memory Configuration
Memory Size
8× 16384 (131072) MB
Memory Type
HBM2
Memory Bus Width
8× 4096 (32768)-bit
Memory Bandwidth
8× 901.1 (7208.8) GB/s
VideoCardz.com

Physical
Interface
NVLINK 2.0
Power Connectors
-
API Support
DirectX
12.0
Vulkan
1.0
OpenGL
4.5
OpenCL
2.1
Shader Model
5.0

Performance
Texture Fillrate
3.7 TTexel/s
SPFP Performance
119.2 TFLOPS
Performance per mm2
18.3 GFLOPS/mm2





 ModelClocksMemory
NVIDIA DGX-1V
40960 Unified Cores
1455 / 880 MHz 128 GB HBM2
NVIDIA HGX-1
40960 Unified Cores
1455 / 880 MHz 128 GB HBM2
NVIDIA DGX Station
20480 Unified Cores
1455 / 880 MHz 64 GB HBM2
NVIDIA Tesla V100 PCIe
5120 Unified Cores
1455 / 880 MHz 16 GB HBM2
NVIDIA Tesla V100 SMX2
5120 Unified Cores
1455 / 880 MHz 16 GB HBM2
NVIDIA Tesla V100 FHHL PCIe
5120 Unified Cores
1200 / 880 MHz 16 GB HBM2
 ModelClocksMemory
NVIDIA Tesla V100 SMX2
5120 Cores
1455 / 880 MHz 16 GB HBM2
NVIDIA Tesla V100 PCIe
5120 Cores
1455 / 880 MHz 16 GB HBM2
NVIDIA Tesla V100 FHHL PCIe
5120 Cores
1200 / 880 MHz 16 GB HBM2
NVIDIA HGX-1
40960 Cores
1455 / 880 MHz 128 GB HBM2
NVIDIA DGX-1V
40960 Cores
1455 / 880 MHz 128 GB HBM2
NVIDIA DGX Station
20480 Cores
1455 / 880 MHz 64 GB HBM2

HGX-1 HYPERSCALE GPU ACCELERATOR FOR AI CLOUD COMPUTING

Powered by NVIDIA® Tesla® GPUs and NVIDIA NVLink high-speed interconnect technology; the HGX-1 comes as AI workloads—from autonomous driving and personalized healthcare to superhuman voice recognition—are taking off in the cloud.

Purpose-built for cloud computing, the HGX-1 enclosure architecture provides revolutionary performance with unprecedented configurability and future-proofing. It taps into the power of eight NVIDIA Tesla GPUs interconnected with the NVLink hybrid cube, that was introduced with the NVIDIA DGX-1 for class-leading performance. Its innovative PCIe switching architecture enables a CPU to be dynamically connected to any number of GPUs. This allows cloud service providers that standardize with a single HGX-1 infrastructure to offer customers a range of CPU and GPU machine instances, while a standard NVLink fabric architecture allows the rich GPU software ecosystem to accelerate AI and other workloads.

With HGX-1, hyperscale data centers can provide optimal performance and flexibility for virtually any accelerated workload, including deep learning training, inference, advanced analytics, and high-performance computing. For deep learning, it provides up to 100X faster performance when compared with legacy CPU-based servers and is estimated to be one-fifth the cost for AI training and one-tenth the cost for AI inferencing.

With its modular design, HGX-1 is suited for deployment in existing data center racks across the globe, offering hyperscale data centers a quick, simple path to be ready for AI. HGX-1 is architected to be Tesla V100 ready and extract the full AI performance that Tesla V100 provides. With a simple drop-in upgrade, Tesla V100 GPUs will create an even more flexible and powerful cloud computing platform.