Name: GPU Acceleration in Python
Start: 2021-02-16T17:00:00Z
End: 2021-02-16T17:00:59.000Z
Location: BrightTALK
Rating: 0

The GPU, our invention, is the engine of computer graphics and GPU deep learning has ignited modern AI — the next era of computing.

Tech support: http://nvda.ws/2ei5pio
Our blog: http://blogs.nvidia.com
All NVIDIA social media: http://nvda.ws/2dlhWo9

NVIDIA BlueField data-processing units (DPUs) with NVIDIA DOCA are very good at accelerating many applications, but they're great at accelerating networked storage solutions. With multiple up to 200 Gb network ports and many lanes of gen4 PCIe, it's the perfect solution to sit between high-performance NVMe solid-state drives and high-performance network ports. Add to that the ease of development with DOCA and line speed NVMe over fabrics offloads, like encryption, decompression, and deduplication accelerators, and you have the perfect controller for a networked storage solution in any part of the data path.

Presented by:
Rob Davis, VP Storage Technology, Networking Platform Group, NVIDIA

BlueField Partner’s DPU Storage Solutions and Use Cases

High-performance private cloud networks are incorporating data processing units (DPUs) for powerful, distributed networking and security capabilities running on servers without compromising performance. But not every server will have a DPU on Day One, and some devices connecting to the network can't incorporate one. We'll describe a highly scalable, SDN-automated distributed cloud network fabric that operates in a unified, consistent manner across both data center switches and DPUs and supports seamless insertion of DPU endpoints into the fabric. 

The fabric design provides a uniform network operating environment with automation, network virtualization, and resource pooling for efficient infrastructure utilization and security to all workloads and devices across the data center. The fabric design supports single-tenant or multi-tenant environments and is independent of virtualization frameworks supporting bare metal, any mix of hypervisors (KVM, ESXi, HyperV), and Kubernetes container orchestration frameworks.

Presented by:
Alessandro Barbieri, VP Product Management, Pluribus Networks
Pete Lumbis, NVIDIA

Unifying and securing cloud networks by extending SDN fabric automation to DPUs

Today's challenges for the modern data center include the computation scalability required for complex, data-intensive workloads such as AI/machine learning, 3D modeling, and big data. NVIDIA DPUs, integrated with VMware infrastructure, are revolutionizing the data center, providing applications and workloads with a unified and integrated infrastructure solution on which the capabilities of the processor are unlocked, enabling secure, parallelized, and accelerated computing by offloading network and storage processing needs from the CPU. 

This new transformative technology is democratizing AI/ML for all enterprises, providing the modern data center with unbounded scalability and huge compute capabilities. New workloads requiring huge processing power and 3D rendering capabilities are powered by NVIDIA DPUs on VMware. 

Learn about how VMware and NVIDIA have partnered to unlock the power of today’s data center across diverse industries.

Presented by:
Michael Kagan, CTO, NVIDIA
Marc Fleischmann, CTO Cloud Infrastructure, VMware

Unleash and Democratize AI for All Enterprises with NVIDIA DPUs and VMware

VMware’s Project Monterey introduces new capabilities for vSphere, enabling new hardware to provide better security and higher network performance, especially with software-defined networks. Learn about Lenovo and NVIDIA's joint solution and the value propositions it enables when running modern workloads over software-defined data center architecture.

Presented by:
Motti Beck, Enterprise Market Development, NVIDIA
Gregory Pruett, Distinguished Engineer, Lenovo DCG

Why Project Monterey Innovative Architecture is Required for the New Gen Apps

Massive Edge deployments that are associated with modern workloads such as AI/ML that require real time data streaming analysis and the on growing security threats, put heavy loads on the server uP, which reduces that Data Center efficiency and prevents IT to meet their SLA. New data center architecture that enables offloading, Isolation and acceleration is needed. 

In this session, we will deep-dive into the unique value proposition that VMware’s Project Monterey over NVIDIA’s BlueField DPU architecture enables by taking advantage of next-generation hardware innovations that accelerate the software defined data center to deliver dramatically improved performance, manageability and higher security.

Presented by:
Motti Beck, Enterprise Market Development, NVIDIA

Software-Defined, Hardware-Accelerated Data Center with Project Monterey

Today’s data centers must be architected to support cloud native accelerated computing workloads. This will enable customers to model, design, and deliver advanced AI services and develop more efficient factories, hospitals, offices, and even the data centers themselves. As AI becomes more prevalent applications grow to span multiple servers and locations, it becomes critical to implement software-defined infrastructure and accelerate it with domain-specific processors such as a DPU. The DPU accelerates data center infrastructure services: networking, security, storage, data streaming. The DPU enables businesses and service providers to efficiently scale to support millions of online users. The entry point for all these users is the Domain Name Service (DNS). 

The session will feature a leading Internet services company, who will present how use the DPU to offload, accelerate, and secure the DNS service over HTTPS. Use of GPU and DPU acceleration ensures data centers are ready to support new solutions including AI, Edge computing, and the Omniverse.

Presented by:
Kevin Deierling, SVP of Networking, NVIDIA
Thomas Jacob, Engineer 4, Software Development and Engineering, Comcast

Accelerated Software-defined Infrastructure for Today's Data Centers

At the end of 2021, NVIDIA introduced "Host Based Networking," a solution running on top of BlueField-2 DPUs. In this session, NVIDIA and Northern Data talk about this solution, the network integration, and deployment at Northern Data.

Presented by:
Atilla de Groot, Enterprise Market Development, NVIDIA 
Tom Eichhorn, Head of Networking, Northern Data

Integrating Host Networking with EVPN on BlueField-2 DPU

As Data Centers are growing in complexity and scale, network fabrics must get faster, bigger, and more reliable. In this session, learn how NVIDIA’s Spectrum platform addresses these demands on the network with current and future Spectrum Ethernet offerings. Leveraging a rich history of performance and hardware excellence, the Spectrum platform brings accelerated data center switching to any Data Center.

Presented by:
David Iles, Senior Director of Ethernet Switching, NVIDIA

Accelerating Data Center Fabrics with Spectrum Ethernet Switches

Red Hat OpenShift is a leading software-defined container platform, built on Kubernetes. The growing demand for data-center security, application performance, and infrastructure scaling are pushing software-only solutions to their limits. The NVIDIA BlueField data processing unit (DPU) ignites unprecedented innovation for modern data centers, delivering a broad range of advanced networking, storage, and security services for complex compute and AI workloads, thus enabling software-defined hardware-accelerated cloud data centers. NVIDIA and Red Hat are working together on managing and orchestrating DPUs utilizing OpenShift to create next-generation hybrid cloud infrastructure that spans on-premises data centers to clouds and all the way to the edge. 

Learn about the next wave of computing in the data centers and its impact on the hybrid cloud. We'll showcase how NVIDIA's DOCA SDK can be utilized with OpenShift to unlock the power of the NVIDIA BlueField DPU.

Presented by:
Kris Murphy, Senior Principal Software Engineer, Red Hat
Ash Bhalgat, Senior Director of Cloud, Telco and Security Market Development, NVIDIA

Accelerating Kubernetes Hybrid Clouds with BlueField DPUs and OpenShift

To keep up with the explosion of data, data centers are deploying high-speed networks from 25G to 100G. While network speed has been increasing, security functions such as next-generation firewalls (NGFW) need to keep up with higher traffic loads. Software-defined NGFW offers the flexibility and agility to build modern data centers; however, scaling them for performance, efficiency, and economics has been a challenge. The need for a software-defined, hardware accelerated NGFW is more pressing than ever. NVIDIA and Palo Alto Networks have developed a DPU-accelerated NGFW solution for the enterprise and cloud-scale data centers. 

In this session, they'll jointly present the PAN VM-Series NGFW solution and discuss availability and customer trials. We'll show a live demonstration of PAN NGFW utilizing BlueField-2 DPU’s rich set of network offloads to improve performance by up to 5x while addressing the security needs of data centers and enterprise deployments.

Presented by:
Ash Bhalgat, Senior Director of Cloud, Telco and Security Market Development, NVIDIA
John McDowall, Senior Distinguished Engineer, Palo Alto Networks
Mukesh Gupta, VP of Product Management, Palo Alto Networks

Accelerating Enterprise Cybersecurity with Software-defined DPU Firewall

Learn how Omniverse can power your projects in the architecture, engineering, and construction industries. We'll cover how Omniverse can be used in AEC workflows and projects for greater collaboration and simulation, and provide a visualization, focusing on how to use Autodesk Revit, McNeel Rhino, Trimble SketchUp, and more with Omniverse and its related tools and applications. Learn best practices and how to build projects with a team.

A Guide To Leveraging Omniverse in AEC

During GTC Fall 2020. NVIDIA is announcing the Quadro RTX A6000 and the NVIDIA A40 GPUs based on the NVIDIA Ampere architecture. 

In this session you will learn all about these new GPUs for professional visual computing and how they provide the power of the next generation of RTX from the desktop to the data center.

Ampere: Leveraging the Latest Architectures for Professional Workflows

We'll step through the process of migrating code from native Python to Numba, and then to a CuPy Raw Kernel (CUDA C++). Basic workflow, best practices, lessons learned, and coding samples will be provided. NVIDIA Nsight Systems profilers will be used to demonstrate how minor optimizations can provide substantial performance benefits to custom developed code. The techniques discussed in this session can be used in any domain.

GPU Acceleration in Python

Data Science

Python

Data Management

Big Data

Big Data Analytics

Welcome to the big data and data management community on BrightTALK. Join thousands of data quality engineers, data scientists, database administrators and other professionals to find more information about the hottest topics affecting your data. Subscribe now to learn about efficiently storing, optimizing a complex infrastructure, developing governing policies, ensuring data quality and analyzing data to make better informed decisions. Join the conversation by watching live and on-demand webinars and take the opportunity to interact with top experts and thought leaders in the field.

Big Data and Data Management

As an IT professional, many of the problems you face are multifaceted, complex and don’t lend themselves to simple solutions. The information technology community features useful and free information technology resources. Join to browse thousands of videos and webinars on ITIL best practices, IT security strategy and more presented by leading CTOs, CIOs and other technology experts.

GPU Acceleration in Python

Presented by

About this talk

More from this channel