Accelerating Apache Spark with FPGAs: A Case Study for 10TB TPCx-HS Spark Benchmark Acceleration with FPGA - Databricks

Accelerating Apache Spark with FPGAs: A Case Study for 10TB TPCx-HS Spark Benchmark Acceleration with FPGA

Nowadays, Fieldâ€-Programmable Gate Array (FPGA) is widely used on data centers, and for a wide range of data center workloads, FPGA-enabled data centers have shown greate potential for providing dramatically speed performance and energy efficiency improvement.

So how to efficiently integrate FPGAs to accelerate popular frameworks for big data processing like Apache Spark is an interesting topic. In this talk, We are going to present the feasibility of incorporating FPGA acceleration into Spark based on the Intel recently-announced FPGA Programmable Acceleration Cards (PACs) for Xeon servers and using the TPCx-HS, the industry standard for benchmarking big data systems, to show that acceleration is possible.

With a step-by-step case study for the TPCx-HS, we demonstrate how a straightforward integration with FPGA can offer an efficient integration with 1.2x overall system speedup and more energy efficiency improvement.

Session hashtag: #SAISEco1

About Qi Xie

Xie Qi is a senior architect of Intel Big Data team. He once worked for IT Flags at Intel and joined Intel Big Data team in 2016 and has a broad experience across Big Data, Multi Media and Wireless.

About Sophia Sun

Sophia sun is a big data software engineer at intel, focusing on spark workload performance analyzing and tuning. She has rich experience on big data benchmark(such as TPC-DS, TPCx-BB, HiBench etc.) analyzing and tuning on large-scale cluster.