March 8th is International Women’s Day – a day when the global community recognizes the vital contributions women make to economics, politics, and culture. Under the theme of “Pledge for Parity,” International Women’s Day is a time to celebrate the many far-reaching accomplishments of women around the globe. It is also a call to action in the fight against disparities associated with women’s rights, equality, health, and safety. Above all, International Women’s Day is a time to remember how gender equality benefits all of us – women and men – at work, at home, and in life.Working at a global company has given me a wonderful window into the many unique and layered stories that shape the ways we understand and move through the world. I think about the story Madeline Martinez, one of our Latina software engineers who recently represented EMC at the White House Initiative on Educational Excellent for Hispanics. I think about our colleague Radia Perlman, who will be inducted into the U.S. National Inventors Hall of Fame this year for her brilliance. I think of Orna Berry, leading innovation at our Israel Center of Excellence and serving as an advisor to government leaders; and I think of Fidelma Russo, leading her team to launch one of our most anticipate products of the year, VMAX All Flash storage. As I think about their stories, I am filled with pride — not only for what they have done, but for the encouragement they give to others.EMC Women in London prior to the Everywoman Advancing Technology ForumPart of my International Women’s Day will be spent thinking about the ways that women and men across EMC can take the actions which result in real and lasting change. I applaud the efforts of Vittorio Colao, the CEO of our valued customer Vodafone, to encourage everyone – and particularly men – to commit to actions in support of gender equality in the #HeForShe campaign. By the next International Women’s Day, I hope to count even more “male allies” who stand with women and help us realize results together.At EMC we understand that gender equality is a vital part of our commitment to a diverse and inclusive workforce, and a true business necessity. We attract and retain women and foster their success by offering world-renowned development and training opportunities. We are visible and vocal at women’s leadership forums – including the Simmons Leadership Conference in Boston, the Everywoman Advancing Technology Forum in London, the Watermark Conference in Silicon Valley and the Global Advancement of Women Conference in Hong Kong. Being present for these international events helps us understand the perspectives of women throughout the world. It also gives strength and resilience to one of our most important assets – our network.At EMC we encourage everyone to tell their individual stories, and create the kind of environment where we can be our “authentic selves.” The more stories that we add, the better and richer our experience becomes. To quote the celebrated author Chimamanda Ngozi Adichie, “The single story creates stereotypes, and the problem with stereotypes is not that they are untrue, but that they are incomplete. They make one story become the only story.”Happy International Women’s Day! Find your voice, own your story, and together, let’s commit to purposeful action in advancing equality and inclusion.
In a recent blog posted to CIO.com, Dell EMC’s Global VP, CTO for Sales, and Distinguished Engineer, Patricia Florissi, Ph.D. talked about how the combination of blockchain technology and federated analytics enables organizations to analyze distributed data with trust, transparency and traceability. I invite you to read more from Dr. Florissi in the blog below, “Using Blockchain to Build Trust into Federated Analytics.”Using Blockchain to Build Trust into Federated AnalyticsWith the rise of the Internet of Things and the explosive growth in data, organizations are increasingly taking computing and analytics to the data, rather than moving the data to a central location for processing and analysis. To address these challenges, Dell EMC has incubated the concept of federated analytics and started developing the World Wide Herd (WWH) platform to make it feasible.So, what is federated analytics? Dell Technologies defines federated analytics as “the analysis of dispersed data in-place, as close as possible to the data source, while these local results are shared, fused and further analyzed along their path to other locations, enabling higher order learning at scale.” Federated analytics is very much the way of the future.This brings us to a challenge at the heart of federated analytics. When you decentralize data analytics, you have to take steps to ensure that you can verify the integrity of all the participants and all the data sources in the analytics process. In particular, you need to have the same assurances of trust, transparency and traceability — the “Three Ts” of data analytics — that you would have in a centralized world.How do you get there? The answer is to bring together the unique capabilities of federated analytics and blockchain technology, which adds a distributed ledger to the federated analytics solution (see sidebar). This is the approach Dell Technologies uses in our WWH.With WWH, the federated analytics network coexists with a blockchain network. Just as it does in the world of bitcoin, the blockchain provides a distributed digital ledger of transactions among entities in the federated analytics network, along with cryptography to prevent unauthorized changes to data and the transparency to enable all participants in the analytics process to see and verify everything that happens in the blockchain. This gives everyone the assurance that no unauthorized sources are participating in computations or using data in malicious ways.Let’s drill down a bit more. In the case of WWH, the blockchain acts as a distributed ledger that records all the details related to each of the computations completed in the federated analytics network. WWH hooks into the blockchain via APIs. These APIs pair up WWH nodes with blockchain nodes. Each computation becomes an entry in a blockchain ledger. The blockchain ledger captures information on things like the ID of the federated analytics node requesting the analytics, a reference to the data resources used in doing the computation, when and where the analytics were run, the results of the analytics, and a unique hash of the actual content of the data used in the analytics.In other words, the blockchain provides a parallel way of logging information and ensuring the integrity of the data and of the participants in the federated analytics network. And this brings us back to the “Three Ts” of federated analytics. Blockchain provides mechanisms for ensuring that you can trust your federated analytics peers, that you have transparency that allows you to see everything that happens to your data to achieve a particular analytics result, and that you have traceability into your sources, via the ability to replay tasks captured in the blockchain.To make this story more tangible, consider, for example, the case of autonomous driving using cloud robotics. Local computations happen in the cars as well as in private and public clouds, and a tremendous amount of these local analytics results are shared through vehicle-to-vehicle and vehicle-to-cloud communications. In the unfortunate event of an accident, litigation procedures will demand full traceability of how the calculations that led to the accident were achieved. All nodes in the federated analytics, including vehicles and clouds, will need to demonstrate the source of the data, the content of the data used, the analytics performed, the local results achieved and the nodes with which they shared results. This is an ideal use case for the Dell Technologies WWH that couples federated analytics with blockchain.As I noted in an earlier series of posts on CIO.com, federated analytics overcomes some of the challenges inherent in centralized analysis of distributed data. These challenges include the need to analyze data at scale in near real-time before the raw data has time to be transmitted from its collection area to a central location, the existence of data in hard-to-reach places, government regulations that restrict the movement of data, the distribution of data over multiple endpoints and clouds, and bandwidth constraints that make it difficult to move data.With federated analytics, data can be analyzed locally, and only the local results are shared — the data itself stays put. This approach enables higher-order learning at scale while conserving bandwidth, accelerating time to insight, and preserving privacy, as the individual data points used to calculate the local results cannot be reverse-engineered from the local results themselves.At the end of the day, federated analytics solves the problem of analyzing data that can’t be moved and the demand to preserve their privacy. Blockchain solves the problem of ensuring that the data can be trusted, the analytics can be performed, and the data used can be transparent, and all distributed and parallel execution flows can be traced and repeated.By integrating federation analytics and blockchain, analytics at a worldwide scale can be achieved in a fully decentralized, peer-to-peer collaboration mode, without including a third party to coordinate the process. Everything is trusted, transparent and traceable, and it all comes together in the Dell Technologies World Wide Herd.Patricia Florissi, Ph.D., is vice president and global CTO for sales and a distinguished engineer for Dell EMC. Twitter link: @florissidelltec  Gartner IT Glossary.
NVIDIA BlueField-2 in use at Durham UniversityAs a group, HPC practitioners are on the cutting edge of innovation, and are always willing to push the boundaries of performance to get to the next big breakthrough. For example, Dell Technologies customer Durham University is a leading research institution in the fields of astrophysics and particle physics. The University is using BlueField-2 DPUs to enable direct access to remote memory and improve the performance of massively parallel codes, which they believe may pave the way for future exascale systems.The Durham University team has been using the half-height, half-width NVIDIA BlueField-2 SmartNIC cards in their “Durham Intelligent NIC Environment” (DINE), a 16-node supercomputer powered by Dell EMC PowerEdge C6525 servers. Each card is then connected with a 25G Ethernet cable, and configured to operate in a “host-separated” mode, providing direct access to the Arm cores on the DPU. Researchers can then launch HPC MPI codes across the cluster making use of both the AMD® EPYC™ server processors, and the Arm processors on the DPUs.To test the DPU technology, the Durham team decided to compile two versions of their code—one that executes on the server processors, and one that executes on the DPU Arm cores. The team reported that recompiling the code for the Arm cores took seconds, while installing the necessary libraries took longer. However, they believe this will be faster in the future now that they have a recipe for the process. When they run a job across the DINE cluster, they direct MPI jobs to run on the DPUs instead of the CPUs, which allows the CPUs to carry on with their tasks without MPI interruptions.The team believes the technology has the potential to become mainstream. Their faculty, staff, students, collaborators and other fundamental researchers will benefit from working with cutting-edge technologies that help them design algorithms and investigate ideas which will help redefine the future of HPC for facilities around the world.Tobias Wienzieri, Project Principal Investigator (PI) for DINE said, “We have been suffering from a lack of MPI progress and, hence, algorithmic latency for quite a while and invested significant compute effort to decide how to place our tasks on the system. We hope that BlueField will help us to realize these two things way more efficiently. Actually, we started to write software that does this for us on BlueField.”Based on the results at Durham University, the new NVIDIA SmartNICs with BlueFiled-2 DPUs are one step further on the journey to the infrastructure-as-code data center, where users can send a job out and have it run where it’s most optimized for performance and efficiency.Ever increasing data drives the need for advanced computing innovationsAs data analytics, artificial intelligence (AI) and High Performance Computing (HPC) converge and mainstream, they’re driving new innovations designed to feed insatiable demands for compute performance. Accelerators—such as graphics processing units (GPUs) and field programmable gate arrays (FPGAs)—have revolutionized advanced computing over the last few decades, by offloading certain tasks from the CPU to speed workloads by several orders of magnitude compared to CPUs alone.However, once Ethernet reaches 10 GB/s, the network interface card (NIC) starts to become the bottleneck, sapping cycles from the processor to handle increasingly complex system and data center networks. For example, when message passing interface (MPI) traffic is running on the CPU, HPC threads have to wait their turn, wasting compute cycles and slowing workload performance.To counter this performance drain, the industry has been pushing the boundaries of software-defined networking (SDN), making the NIC smarter so that it can take over some of the processing functions that can slow down the CPU.NVIDIA announces the SmartNIC, powered by NVIDIA BlueField-2 DPUAfter acquiring networking powerhouse Mellanox in April of this year, NVIDIA began leading the charge on novel SDN technologies by announcing the NVIDIA® Mellanox® ConnectX-6 Lx SmartNIC. The SmartNIC is powered by the new NVIDIA BlueField technology, a high-performance, software programmable, multi-core system on a chip (SOC) CPU based on the Arm processing architecture.The BlueField-2 Data Processing Unit (DPU) offloads critical network, security, and storage tasks from the CPU to boost performance, networking efficiency and security. With the BlueField-2 DPU enabled SmartNIC, the full infrastructure stack—compute, storage and networking—can be more granularly software-defined and disaggregated to handle larger volumes of data faster and more efficiently.Dive into the detail:Durham University will deepen understanding of the universeDurham’s Universe of StorageDell Technologies solutions for HPC