Leverage HPDA to Bring New Levels of Data-Driven Innovation

0



High Performance Computing (HPC) is one of the areas of computing that is expected to experience rapid growth in the coming years. A report from analytics firm GrandView Research Demand for the technology suggests that it will grow at a compound annual growth rate of 6.5% through 2027.

The underlying reason is very simple. The continuous evolution of various industry sectors for digitization, AI, IoT and a large number of other data-driven applications has increased the need for increased computing power and the ability to compute complex algorithms. . As Grand View Research argues, “The ability of HPC systems to process large amounts of data faster has led government agencies, defense agencies, academia, energy companies and utilities to adopt HPC systems. It is also a precursor of growth. In the HPC market

In other words, one of the main drivers of adoption and investment in HPC is the desire for access to high performance data analytics (HPDA), faster data processing functionality and more powerful.

Provide major HPDA platforms

The HPDA plays an important social, cultural and economic role. HPC, for example, allows us to complete whole genome sequencing, which initially took 13 years, in one day. HPC is also used to speed up drug screening and molecular analysis, allowing new essential drugs to move faster to the R&D phase. HPC’s enhanced data computation capabilities facilitate more accurate weather forecasting, but in the long run, HPDA will improve the astronomically complex number of computations required for safe autonomous driving. This is the key.

Self-driving car training needs to generate around 60TB of data per day to visualize the amount of relevant data. Third-generation sequencers generate 6 TB of data daily, which must be stored and accessed at all times. Now that mining and resource organizations are working on 3D exploration instead of traditional 2D imagery, the mid-term data needs are multiplied by 20.

To meet these complex data challenges, businesses need robust HPDA solutions combined with advanced data storage technologies with high speed, low latency and higher bandwidth.

After hands-on testing of the performance and functionality of the Huawei OceanStor Pacific storage system, including multi-protocol support, hybrid workloads, high-density design, and total cost of ownership (TCO) analysis, The Enterprise Strategy Group makes the ideal storage system for HPDA technology. Next generation storage solution.

One of the main features of the Huawei OceanStor Pacific solution, and one of the reasons it is so efficient at processing large amounts of data, is that it is designed to optimize the placement of I / O metadata. and keep them close. It is a parallel file system. To data on the node that owns it. This enables storage systems to handle AI / ML, big data and analytics, large-scale virtualization, content repositories, seismic analysis, life sciences or applications used by a large number of persons.

According to the Enterprise Strategy Group, OceanStor Pacific storage systems deliver consistently high performance for very large data sets, demanding real-world data-centric applications that run in performance-critical environments. Obviously suitable for support. Enterprise Strategy Group Five-Year TCO Analysis Shows OceanStor Pacific Storage System Deployment Can Reduce Storage TCO by Up to 61% Compared to Traditional Scalable NAS Systems, Improving Uptime and Effort operational. It has also been shown to be reduced. at the same time.

Huawei

In a typical scenario, using the OceanStor Pacific storage system can also improve processing efficiency by over 30%. In addition, the high density design used in the OceanStor Pacific storage system reduces the cabinet footprint by 66.6% compared to general purpose servers. At the same time, the efficiency of the storage system allows up to 91.6% disk usage.

Huawei HPC in operation in energy, science and technology sectors

Lundin Energy Norway is not only one of the largest exploration and production companies in Europe, but also one of the leading innovators in this sector. As stated on its website, “Today we are not just looking for oil and gas. We are looking for new ideas and new solutions. When you find what you’re looking for, it’s a little better. If you can’t find it, you’re a little smarter. “

Innovations in the energy sector require processing large amounts of data, and Huawei’s disrupted storage products provide Lundin with it. Thanks to Huawei, the company offers high bandwidth, input / output operations per second (IOPS) and access to storage systems that support the processing, interpretation and simulation analysis of seismic data. by Lundin. These changes improved the efficiency of Lundin’s data processing by 28%. In addition, intelligent prioritization of hot and cold data saves 73% physical storage space and 35% overall total cost of ownership.

Huawei

Across the science and technology industry, Huawei has helped Tsinghua University and Chinese Academy of Sciences promote cutting-edge scientific research using HPDA solutions, as well as science and technology leaders such as BGI, Orbita and the Chinese Meteorological Bureau. I did.

HPDA has a wide variety of applications. As Steve Conway, senior advisor at Hyperion Research, who coined the term ‘HPDA’, said in a recent interview, “Important use cases for autonomous driving, precision medicine, smart cities, IoT, advanced computing, etc. at the forefront of these areas, you use HPC.

In other words, in almost every area of ​​innovation, the demand for IT has reached the point where HDPA is the best solution of the future.

To learn more about OceanStor Pacific Storage and HPDA, and ESG reports, click here.

Copyright © 2021 IDG Communications, Inc.



Leave A Reply

Your email address will not be published.