Questo sito utilizza cookie di profilazione (propri e di terze parti) per ottimizzare la tua esperienza online e per inviarti pubblicità in linea con le tue preferenze. Continuando a utilizzare questo sito senza modificare le tue preferenze acconsenti all’uso dei cookie. Se vuoi saperne di più o negare il consenso a tutti o ad alcuni cookie clicca qui>
The website that you are visiting also provides Arabian language. Do you wish to switch language version?
يوفر موقع الويب الذي تزوره المحتوى باللغة العربية أيضًا. هل ترغب في تبديل إصدار اللغة؟
The website that you are visiting also provides Russia language Do you wish to switch language version?
Данный сайт есть в английской версии. Желаете ли Вы перейти на английскую версию?
Peking University is one of the top universities in China and enjoys its reputation in global educational circle. The College of Information Science and Technology is the biggest college of Peking University. It has 2700 full-time students and 340 faculty members, with three academicians from the Chinese Academy of Sciences and one academician from the Chinese Academy of Engineering. The college is leading the industry in the big data application field. In addition, the college is one of SAP's HANA independent software vendors (ISVs).
Along with the emergence of new technologies, such as mobile Internet, social network, e-commerce, and Internet of things, data of the human society grows in unprecedented scale. The total volume of data generated in 2012 and 2013 almost equals to the total volume that is previously generated in ZB level.
Data changes from the object to be processed to the basic resource. Nowadays, the common topic is how to manage and use big data. The scale effect of big data causes great challenges to data storage, management, and analysis. Data complexity keeps increasing, and massive unstructured data is generated. The new challenge to the industry is how to process and analyze PB-level data without constructing complex distributed storage and computing clusters and support on-demand capacity expansion.
As a top research institution in China, the college has many key laboratories and rich teaching resources, making it suitable for big data research. As the first SAP HANA ISV in China, the college mainly serves the governmental institutes and public utilities and uses big data to solve problems in traffic and transportation, city planning, sanitation, finance, and education. In addition, the college uses big data to create the analysis model for predicting disease prevalence and analyzing public opinions.
The computing system of the big data platform needs to offer high-speed I/O, high performance, and high reliability. This is also the most important standard for selecting a solution.
The system hardware must be certified by SAP HANA.
After a series of researches and performance tests, the college chose the Huawei RH5885 V2-based SAP HANA appliance solution.
The high-end 4-socket/8-socket RH5885 V2 rack server is the first server that is certified by SAP HANA in China. The server supports Intel E7 series processors. A single processor supports a maximum of ten cores at the maximum frequency of 2.66 GHz, with a maximum L3 cache capacity of 30 MB. The server fully meets performance requirements for big data analysis and mining.
An RH5885 supports two high-performance GPUs and 64 DIMMs with a maximum memory capacity of 2 TB, which ensures high in-memory computing, graphics processing, and floating-point computing performance for graphics displaying of big data analysis. With solid hardware basis, the RH5885 V2 ranked first in the TPC-E performance test and shattered 12 world records in the SPEC test.
The RH5885 V2 provides two 10GE NICs and four GE NICs for network connection and one ES3000 PCIe SSD for improving disk read and write bandwidth, with the maximum IOPS of 770,000, 20% higher than the average level in the industry. The ES3000 PCIe SSD provides over 2700 transactions per second (TPS) for online transaction processing (OLTP) performance, write response latency less than 10 µs, two times faster than the average level in the industry. The high read and write performance ensures high-speed I/O for big data analysis.
In addition, the RH5885 V2 supports 35 RAS features, hot-swap PCIe cards, maintenance for key components without opening the chassis cover, and comparable reliability to midrange computers.
Thanks to the high-speed I/O, high performance, high reliability of the RH5885 V2, advantages of SAP HANA in-memory computing can be fully used to support fast query, analysis, and computing for massive real-time service data.
After operation for one year (2013), high reliability of the RH5885 V2 has been approved. Huawei's innovative PCIe SSD improves the appliance I/O performance by five times and saves the hardware investments by 60%.
The RH5885 V2-based SAP HANA appliance fully meets hardware application and security requirements for the Chinese government . During this cooperation, Huawei also learns more about features of the education, governmental security, and big data applications, aiming at helping more customers from other industries to build excellent IT architecture.
"The high-speed Huawei PCIe SSD improves I/O performance for the appliance by five times. Huawei's hardware devices save Peking University's investment on important researches by 60%. More important, the high-performance Huawei RH5885 V2-based HANA appliance helped us achieve great results on our intelligent big data research."
-- Director of the Key Laboratory of College of Information Science and Technology of Peking University