Alibaba Cloud achieves world record in big data performance and decision support


Alibaba Cloud, the data intelligence backbone of Alibaba Group, has announced that MaxCompute, the company’s general purpose, fully managed, multi-tenancy data processing platform has achieved a new set of global records in big data performance and decision support optimization. By publishing the industry’s first 100,000 scale factor on the Alibaba Cloud’s MaxCompute Cluster, the company has demonstrated its leadership in delivering high-performance cloud solutions to its customers in a cost-effective manner.

Released in September 2019 by the Transaction Processing Performance Council (TPC), an industry council which sets the standards for transaction processing and database benchmarking, Alibaba Cloud is the first cloud service provider to be evaluated based on a 100 TB data benchmark, following records the company set on 10 TB and 30 TB benchmarks. TPC’s results were based on two sets of benchmarking rests – TPCx-Big Bench (TBCx-BB), which measures big data performance, and TBC-DS, which measures decision support.

“We are very excited to see Alibaba Cloud’s core product MaxCompute represented so well in the international benchmarks released by TPC,” said Yangqing Jia, Vice President of Alibaba Group and President and Senior Fellow of Data Platform, Alibaba Cloud Intelligence. “Receiving the industry-first and record-breaking results through the TPC further bolsters our confidence in delivering the best value for our customers and partners across our 61 availability zones across 20 regions around the world.”

TBCx-BB measures the performance of hardware and software components of Hadoop-based big data systems by executing 30 frequently performed analytical queries in the context of retailers with physical and online store presence. Alibaba Cloud MaxCompute attained 25,641 BBQpm (Big Bench Query-per-minute) with price/performance ratio of up to $224.49/BBQpm on the TBCx-BB tests, placing the platform’s performance ahead of the rest of the industry.

In the meantime, Alibaba Cloud’s Elastic MapReduce (EMR) reached 14,861,137 QphDS (queries per hour) and a price/performance ratio of up to $0.17/QphDS. This result showcased Alibaba Cloud’s industry leadership as a general-purpose decision support system, with industry-leading performance relating to query response time.

A core product of Alibaba Cloud, MaxCompute supports Alibaba’s machine learning platform PAI, to deliver best-in-class big data-driven insights for retail and e-commerce use cases across Alibaba ecosystem, supporting 99% of data warehousing and 95 per cent of computing demand for platforms including Taobao and Tmall, and visual search engine Pailitao. Enterprises can also make use of MaxCompute’s data-importing features and distributed computing models to effectively query massive datasets, reduce production costs, and ensure data security.


Please enter your comment!
Please enter your name here