BestHub
Sign in
Tagged articles

Velox

13 articles · Page 1 of 1
DataFunTalk
DataFunTalk
Jun 21, 2026 · Big Data

How Zhihu Optimized Spark Jobs with Gluten: A Practical Deep‑Dive

This article details Zhihu's end‑to‑end experience of migrating Spark SQL workloads to the open‑source Gluten framework, covering background performance benchmarks, the architecture of Gluten and Velox, consistency and performance challenges encountered during migration, the concrete fixes applied, and the resulting resource savings and future plans.

Big DataGlutenOptimization
0 likes · 22 min read
How Zhihu Optimized Spark Jobs with Gluten: A Practical Deep‑Dive
DataFunSummit
DataFunSummit
Mar 1, 2026 · Big Data

How Ant Group’s Flex Engine Supercharges Flink with Vectorization

This article details Ant Group’s Flex vectorized engine built on Velox, covering the current state of vectorization, Flex’s architecture (Flink + Velox), core feature development, correctness guarantees, large‑scale deployment results, and future directions for full‑link vectorization and broader hardware support.

Big DataFlexFlink
0 likes · 18 min read
How Ant Group’s Flex Engine Supercharges Flink with Vectorization
SF Technology Team
SF Technology Team
Sep 29, 2025 · Big Data

How SF Tech Cut 10,000 CPU Cores with Apache Gluten – A Deep Dive

This article details how SF Technology adopted Apache Gluten with Velox to accelerate Spark queries, describing the architecture, task lifecycle, management framework, simulation system, unified SQL, fallback mechanisms, dynamic memory tuning, columnar shuffle, and future plans that together saved over 10,000 CPU cores and reduced operator fallback rates to around 4%.

Apache SparkGlutenVelox
0 likes · 16 min read
How SF Tech Cut 10,000 CPU Cores with Apache Gluten – A Deep Dive
AntData
AntData
Dec 11, 2024 · Big Data

Flex: A Stream‑Batch Integrated Vectorized Engine for Flink

This article introduces Flex, a Flink‑compatible stream‑batch vectorized engine built on Velox and Gluten, explains the SIMD‑based execution model, details native operator optimizations, fallback mechanisms, correctness and usability improvements, and presents performance results and future development plans.

Distributed ComputingFlinkSIMD
0 likes · 17 min read
Flex: A Stream‑Batch Integrated Vectorized Engine for Flink
DataFunSummit
DataFunSummit
Aug 17, 2024 · Big Data

AnalyticDB Spark Architecture and Vectorized Engine Performance Overview

This article introduces the AnalyticDB Spark architecture, explains the need for Spark vectorization, surveys industry vectorized solutions, details ADB Spark's own vectorized implementation with Gluten and Velox, and presents performance test results showing a 6.98‑fold speedup over open‑source Spark.

AnalyticDBBig DataGluten
0 likes · 9 min read
AnalyticDB Spark Architecture and Vectorized Engine Performance Overview
DataFunSummit
DataFunSummit
Aug 5, 2024 · Big Data

Velox Memory Management and Execution Engine Overview

This article presents a comprehensive overview of Meta's open‑source Velox query execution engine, detailing its architecture, vectorized execution model, memory‑pool hierarchy, arbitrator and allocator designs, spilling techniques, and future development plans for large‑scale data processing.

Big DataMemory ManagementQuery Execution
0 likes · 24 min read
Velox Memory Management and Execution Engine Overview
Past Memory Big Data
Past Memory Big Data
Jun 27, 2024 · Big Data

Inside Presto 2.0: The Native C++ Query Engine Explained

This article provides a detailed technical overview of Presto 2.0, the native C++ query engine built on the Velox library, covering its motivation, vectorized architecture, memory management, performance benchmarks from Meta and IBM, and deployment practices for large‑scale data warehouses.

Big DataC#Data Warehouse
0 likes · 15 min read
Inside Presto 2.0: The Native C++ Query Engine Explained
Past Memory Big Data
Past Memory Big Data
Jun 20, 2024 · Big Data

How Meituan Scaled Spark with Vectorized Execution Using Gluten + Velox

This article details Meituan's production‑grade adoption of Spark vectorized execution via the open‑source Gluten and Velox stack, explaining SIMD fundamentals, performance motivations, the end‑to‑end integration workflow, staged rollout, encountered challenges, and the resulting resource savings and speedups.

Big DataGlutenORC
0 likes · 33 min read
How Meituan Scaled Spark with Vectorized Execution Using Gluten + Velox
Meituan Technology Team
Meituan Technology Team
Jun 20, 2024 · Big Data

Vectorized Execution in Apache Spark: Meituan’s Practice with Gluten and Velox

Meituan enhances Apache Spark by integrating the Gluten‑Velox vectorized execution engine, converting row‑wise operations to columnar SIMD processing, which yields over 40 % memory savings and up to 13 % faster runtimes across thousands of ETL jobs, while addressing stability, ORC support, shuffle redesign, and off‑heap memory optimization.

Apache SparkBig DataC#
0 likes · 30 min read
Vectorized Execution in Apache Spark: Meituan’s Practice with Gluten and Velox
dbaplus Community
dbaplus Community
Jan 30, 2023 · Databases

Why Velox, ReadySet, and Neon Are Redefining the 2022 Database Landscape

The article reviews the cooling of 2022 database funding, highlights Velox as a shared execution engine, examines ReadySet's transparent caching, profiles Neon’s serverless PostgreSQL, surveys other notable databases, and outlines emerging trends and predictions for 2023, offering a comprehensive technical and market analysis for developers and DB professionals.

AIDatabasesExecution Engine
0 likes · 19 min read
Why Velox, ReadySet, and Neon Are Redefining the 2022 Database Landscape
Past Memory Big Data
Past Memory Big Data
Oct 13, 2022 · Big Data

Step-by-Step Guide: Integrating Presto with Velox on macOS (Build, Configure, and Run)

This article walks through the performance bottleneck of CPU in data analytics, introduces the Velox vectorized execution engine, and provides a detailed, zero‑to‑one tutorial for downloading Presto source, syncing Velox, fixing build paths, compiling both Java and C++ components, configuring CLion and IntelliJ, launching the servers, and executing SQL queries while noting stability concerns.

JavaSQLVelox
0 likes · 19 min read
Step-by-Step Guide: Integrating Presto with Velox on macOS (Build, Configure, and Run)
Past Memory Big Data
Past Memory Big Data
Sep 13, 2022 · Databases

Velox: An Open‑Source Unified Execution Engine for Data Systems

Velox is Meta's open‑source unified execution engine that consolidates common data‑intensive components, integrates with engines like Presto, Spark, and TorchArrow, and delivers up to ten‑fold speedups on CPU‑bound queries while simplifying development and fostering a reusable, community‑driven ecosystem.

Data ManagementSparkUnified Execution Engine
0 likes · 9 min read
Velox: An Open‑Source Unified Execution Engine for Data Systems