PNY Technologies Inc.
0
NVIDIA A100X

NVIDIA A100X

NVIDIA® A100X

  • SKU: NVA100XTCGPUCA-KIT

Where to Buy

Commercial Sales

  • Description

    RoHS Compliant Logo
    Certification Request

    EOL Notification Form EOL Notification Form

    NVIDIA A100X

    Converged Accelerators | Networking and Compute, Unified

    The A100X brings together the power of the NVIDIA A100 Tensor Core GPU with the BlueField-2 DPU. It's ideal for I/O intensive, GPU-accelerated workloads. Examples include 5G with massive multiple-input, multiple-output (MIMO) capabilities, AI-on-5G deployments, and specialized workloads such as signal processing and multi-node training

    In one unique, efficient architecture, NVIDIA converged accelerators like the A100X combine the powerful performance of NVIDIA GPUs with the enhanced networking and security of NVIDIA smart network interface cards (SmartNICs) and data processing units (DPUs). Deliver maximum performance and enhanced security for I/O intensive GPU accelerated workloads, from the data center to the edge.

     

    Performance Highlights

    Peak FP64

    		 9.9 TFLOPS

    Peak FP64 Tensor Core

    		 19.1 TFLOPS | Sparsity

    Peak FP32

    		 19.9 TFLOPS

    TF32 Tensor Core

    		 159 TFLOPS | Sparsity

    Peak FP16 Tensor Core

    		 318.5 TFLOPS | Sparsity

    Peak INT8 Tensor Core

    		 637 TOPS | Sparsity

    Multi-Instance GPU Support

    		 Yes | Up to 7

    GPU Memory

    		 80 GB HBM2e

    Memory Bandwidth

    		 2039 GB/s

    Interconnect

    		 PCIe Gen4 (x16 Physical, x8 Electrical) | NVLink Bridge

    Networking

    		 2x 100 Gbps ports, Ethernet or InfiniBand

    Form Factor

    		 Dual-Slot, Full-Height, Full-Length

    Thermal Solution

    		 Passive

    Maximum Power Consumption

    		 300 W

    High-Performance 5G

    • NVIDIA converged accelerators like the A100X provide an extremely high-performing platform for running 5G workloads. Because data doesn't need to go through the host PCIe system, processing latency is greatly reduced. The resulting higher throughput also allows for a greater subscriber density per server. NVIDIA A100X teams with the NVIDIA Aerial SDK, an application framework for building high-performance, software-defined, cloud-native 5G networks to address increasing user demand. It enables GPU-accelerated signal and data processing for 5G virtual radio access networks (vRANs). Aerial is 100% software defined and delivers a highly-programmable PHY layer and has the capability to support L2+ functions seamlessly. The A100X's GPU-accelerated processing lets complex computations run faster than existing L1 processing solutions, giving improved performance results. Together, NVIDIA A100X and the Aerial SDK offer commercial-off-the-shelf (COTS) hardware support, making it easier to deploy cloud-native platforms such as NVIDIA EGX. It's Kubernetes based and provides container orchestration for ease of deployment and management. Available as a .zip package or NVIDIA NGC container image the A100X and Aerial duo is a compelling platform on which to build and deploy GPU-accelerated 5G vRANs. Join the Aerial early access program today.

    Enterprise AI on 5G – From Data Center to Edge

    • The NVIDIA A100X brings enterprise AI and 5G together on one converged, GPU-accelerated platform (NVIDIA EGX), integrating 5G connected devices (including sensors and actuators). This makes it possible for enterprises to deploy edge AI applications over a private 5G network. A100X systems deliver a GPU-accelerated, edge 'data center in a box' that delivers high-performance for AI workloads and software defined 5G vRANs. The same A100X powered platform for AI workloads can be used for 5G RAN infrastructure, which is implemented as an additional software layer. The NVIDIA AI-on-5G platform for enterprises redefines how intelligent edge networks for AI are built; bringing flexibility, efficiency, reliability, and security to reshape how businesses, organizations, and governments operate, while enabling new use cases across manufacturing, retail, smart spaces, automotive, and public sector scenarios. By delivering the first GPU accelerated platform with edge AI and software defined 5G for enterprises, PNY and NVIDIA expect significant amounts of economic value to be realized.


    PNY Pro Logo

    Warranty Shield Icon
    Warranty

    Free dedicated phone and email technical support
    (1-800-230-0130)

    Dedicated NVIDIA professional products Field Application Engineers

    Book Icon
    Resources

    Contact gopny@pny.com for additional information.

  • Features

    NVIDIA A100X

    PERFORMANCE AND USEABILITY FEATURES

    Unprecedented GPU Performance

    NVIDIA Tensor Core GPUs deliver unprecedented performance and scalability for AI, High-performance computing (HPC), data analytics, and other compute-intensive workloads. With Multi-Instance GPU (MIG), each GPU can be partitioned into up to 7 GPU instances – fully isolated and secured at the hardware level. Systems can be configured to offer right-sized GPU acceleration for optimal utilization and sharing across applications big and small in both bare-metal and virtualized environments.

    Enhanced Networking and Security

    NVIDIA's ConnectX family of smart network interface cards (SmartNICs) offer best-in-class network performance, advanced hardware offloads, and accelerations. NVIDIA BlueField DPUs combine the performance of ConnectX with full infrastructure-on-chip programmability. By offloading, accelerating, and isolating networking, storage, and security services, Bluefield DPUs provide a secure, accelerated infrastructure for any workload in any environment.

    A New Level of Data Efficiency

    NVIDIA Converged accelerators include an integrated PCIe switch, allowing data to travel between the GPU and network without flowing across the server PCIe system. This enables a new level of data center performance, efficiency and security for IO-intensive, GPU-accelerated workloads.

    Enterprise-Ready Utilization

    NVIDIA A100X with MIG maximized the utilization of GPU accelerated infrastructure. With MIG, an A100 GPU can be portioned into as many as seven independent instances, giving multiple users access to GPU acceleration. MIG works with Kubernetes, containers, and hypervisor-based server virtualization. MIG lets infrastructure managers offer a right-sized GPU with guaranteed QoS for every job, extending the reach of accelerated computing resources to every user.

    CONVERGED ACCELERATOR BENEFITS

    A More Powerful, Secure Enterprise

    NVIDIA converged accelerators like the A100X combine the power of the NVIDIA Ampere architecture with the enhanced security and networking capabilities of the NVIDIA BlueField-2 data processing unit (DPU), all in a single high-performance package. This advanced architecture delivers unprecedented performance and strong security for GPU powered workloads in enterprise data center, edge computing, telecommunications, and network security.

    Better Performance

    Because the NVIDIA Ampere architecture GPU and BlueField-2 DPU are connected via an integrated PCIe Gen4 switch, there's a dedicated path for data transfer between the GPU, DPU, and the network. This eliminates performance bottlenecks of data going through the host. It also enables much more predictable performance, which is important for time-sensitive applications such as 5G signal processing.

    Enhanced Security

    The convergence of NVIDIA's GPU and DPU creates a more secure AI processing engine, where data generated at the edge can be sent across the network fully encrypted without traveling over the server PCIe bus, ensuring it's isolated from the host. This helps provide better protection for the host from network-based threats.

    Smarter Networking

    Since the NVIDIA A100X's NVIDIA BlueField-2 DPU implements NVIDIA ConnectX-6 Dx functionality, this allows NVIDIA A100 GPU processing to be applied directly to traffic as it flows to and from the network or DPU. This enables a whole new class of applications that involve AI-based networking and security, such as data leak detection, network performance optimization and prediction, and more.

    Cost Savings

    Because the GPU, DPU, and PCIe switch are combined together on a single card, customers can leverage mainstream servers to perform tasks previously only possible with high-end or purpose-built systems. Even edge servers can benefit from the same performance boost that's more typically found in specialized systems.

    MULTI-GPU TECHNOLOGY SUPPORT

    Third Generation NVLink

    Connect two NVIDIA A100X boards with NVLink to double the effective memory footprint and scale application performance by enabling GPU-to-GPU data transfers at rates up to 600 GB/s of bidirectional bandwidth. NVLink bridges are available for motherboards with standard or wide slot spacing.

    SOFTWARE SUPPORT

    NVIDIA AI Enterprise and Virtual GPU Software

    NVIDIA AI Enterprise and support for NVIDIA Virtual Compute Server (vCS) accelerates virtualized compute workloads such as high-performance computing, AI, data science, big-data analytics, and HPC applications.

    Software Optimized for AI

    Deep learning frameworks such as Caffe2, MXNet, CNTK, TensorFlow, and others deliver dramatically faster training times and higher multi-node training performance. GPU accelerated libraries such as cuDNN, cuBLAS, and TensorRT deliver higher performance for both deep learning inference and High-Performance Computing (HPC) applications.

    NVIDIA CUDA Parallel Computing Platform

    Natively execute standard programming languages like C/C++ and Fortran, and APIs such as OpenCL, OpenACC and Direct Compute to accelerate techniques such as ray tracing, video and image processing, and computation fluid dynamics.

  • Specifications

    NVIDIA A100X

    SPECIFICATIONS

    Product

    		 NVIDIA A100X Converged Accelerator

    Architecture

    		 Ampere

    Process Size

    		 7nm | TSMC

    Transistors

    		 54.2 Billion

    Die Size

    		 826 mm2

    Peak FP64

    		 9.9 TFLOPS

    Peak FP64 Tensor Core

    		 19.1 TFLOPS | Sparsity

    Peak FP32

    		 19.9 TFLOPS

    TF32 Tensor Core

    		 159 TFLOPS | Sparsity

    Peak FP16 Tensor Core

    		 318.5 TFLOPS | Sparsity

    Peak INT8 Tensor Core

    		 637 TOPS | Sparsity

    Multi-Instance GPU Support

    		 7 MIGs at 10 GB Each
    3 MIGS at 20 GB Each
    2 MIGs at 40 GB Each
    1 MIG at 80 GB

    GPU Memory

    		 80 GB HBM2e

    Memory Bandwidth

    		 2039 GB/s

    Interconnect

    		 PCIe Gen4 (x16 Physical, x8 Electrical) | NVLink Bridge

    Networking

    		 2x 100 Gbps ports, Ethernet or InfiniBand

    Maximum Power Consumption

    		 300 W

    NVLink

    		 Third-Generation | 600 GB/s Bidirectional

    Media Engines

    		 1 Optical Flow Accelerator (OFA)
    1 JPEG Decoder (NVJPEG)
    4 Video Decoders (NVDEC)

    Integrated DPU

    		 NVIDIA BlueField-2
    Implements NVIDIA ConnectX-6 DX Functionality
    8 Arm A72 Cores at 2 GHz
    Implements PCIe Gen4 Switch

    NVIDIA Enterprise Software

    		 NVIDIA vCS (Virtual Compute Server)
    NVIDIA AI Enterprise

    Form Factor

    		 2-Slot, Full Height, Full Length (FHFL)

    Thermal Solution

    		 Passive

    Maximum Power Consumption

    		 300 W

    AVAILABLE ACCESSORIES

    • RTXA6000NVLINK-KIT provides an NVLink connector for A30X suitable for standard PCIe slot spacing motherboards. Application support is required. All NVIDIA Ampere architecture-based PCIe boards (Data Center or Professional Graphics) utilize the same NVLink bridges.

    SUPPORTED OPERATING SYSTEMS

    • Windows Server 2012 R2
    • Windows Server 2016 1607, 1709
    • Windows Server 2019
    • RedHat CoreOS 4.7
    • Red Hat Enterprise Linux 8.1-8.3
    • Red Hat Enterprise Linux 7.7-7.9
    • Red Hat Linux 6.6+
    • SUSE Linux Enterprise Server 15 SP2
    • SUSE Linux Enterprise Server 12 SP 3+
    • Ubuntu 14.04 LTS/16.04/18.04 LTS/20.04 LTS

    WARRANTY

    • Dedicated NVIDIA professional products Field Application Engineers

    PACKAGE CONTAINS

    • NVIDIA A100X Data Center Converged Accelerator Board
    • Auxiliary power cable
Close