vectorized computing — 3 Technical Articles

Sep 27, 2024 · Big Data

How Alibaba Cloud’s New Vectorized Engines Are Revolutionizing Real‑Time Big Data Processing

At the 2024 Cloud Xi Conference, Alibaba Cloud unveiled a suite of vectorized big‑data solutions—including the Flash engine for Flink, EMR Serverless Spark with a 300% speed boost, upgraded lakehouse architecture, and real‑world case studies—showcasing massive performance gains, cost reductions, and broader serverless adoption.

Big DataFlinkServerless

0 likes · 8 min read

How Alibaba Cloud’s New Vectorized Engines Are Revolutionizing Real‑Time Big Data Processing

Alibaba Cloud Observability

Aug 15, 2024 · Cloud Native

How SPL’s High‑Performance Mode Transforms Log Query at Scale

This article explains how the SLS Processing Language (SPL) combines pipeline syntax with SQL‑like operators, introduces a high‑performance mode that pushes computation to storage nodes and uses vectorized processing, and demonstrates sub‑second query times on billions of log entries while supporting rich filtering, histogram visualization, and random paging.

SPLhigh performance queryobservability

0 likes · 17 min read

How SPL’s High‑Performance Mode Transforms Log Query at Scale

Alibaba Cloud Native

Aug 12, 2024 · Cloud Native

How SPL’s High‑Performance Mode Supercharges Log Queries in the Cloud

Log data’s immutable, random, and multi‑source nature makes traditional search inefficient, so Alibaba Cloud’s SLS introduces the SPL pipeline language, combining Unix‑style piping with SQL‑like functions, and leverages computation push‑down, vectorized processing, and optimized I/O to deliver high‑performance log queries at scale.

High PerformanceSPLcloud native

0 likes · 18 min read

How SPL’s High‑Performance Mode Supercharges Log Queries in the Cloud