The high performance stack

on YouTube ↗08m

" summary

Claims a production integrated metal plus software stack built from Lenovo SR650 hardware, Intel processors, IBM software and Hortonworks that runs Hadoop and Spark on hundreds of terabytes / hundreds of billions of rows and yields 5× faster query times versus a traditional cluster. Describes an SR650 virtual rack reference architecture, an F1 analytics platform combining DB2, Spark and data science tools, a public demo that runs queries against 100 TB, and says the system is available now.

AI-written summary · about

" related talks

• 06mAchieve predictable performanceAlexander Grbic · Velocity 2017
• 06mDemocratizing Big Data and Hadoop-Based Platforms and SolutionsBoyd Davis · Strata Conference 2014
• 22mPresto for Your Fast, Open SQL LakehouseSteven Mih · OSA Con 2022
• 38mOn the path to data Nirvana: Supporting OLTP and OLAP on HadoopMonte Zweben · Data By the Bay 2016
• 09mThe DNA of Next-generation Data CJohn Busch · Velocity 2009
• 44mRiak, Redis, Apache Solr & Spark: Deploying with the Basho Data PlatformBryan Hunt · GOTO London 2015
• 59mHadoop Essentials for the SQL Server ProfessionalBill Preachuk · 24 Hours of PASS: Summit Preview 2015
• 48mAnalytics Architectures on Microsoft FabricBradley Schacht, Freddie Santos · SQLBits 2024