--- title: pg_vexec one month on: ahead of ClickHouse on Parquet,... description: A month into building pg_vexec, a vectorized PostgreSQL engine that started as a way to extract Greenplum's ORCA planner, the engine now beats ClickHouse on... canonical: https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: pg_vexec one month on: ahead of ClickHouse on Parquet, close behind on MergeTree | daily.dev og:description: A month into building pg_vexec, a vectorized PostgreSQL engine that started as a way to extract Greenplum's ORCA planner, the engine now beats ClickHouse on... og:url: https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3 og:image: https://api.daily.dev/og/posts/HTiQ6EUu3.png og:image:alt: pg_vexec one month on: ahead of ClickHouse on Parquet, close behind on MergeTree og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # pg_vexec one month on: ahead of ClickHouse on Parquet, close behind on MergeTree **[Planet PostgreSQL](https://daily.dev/sources/planet-postgresql)** · 1 min read · 0 upvotes · 0 comments ## Summary A month into building pg_vexec, a vectorized PostgreSQL engine that started as a way to extract Greenplum's ORCA planner, the engine now beats ClickHouse on Parquet and nearly matches it on MergeTree in ClickBench. A rough-draft GPU version is said to be faster still. On an MSI Raider A18 HX A9W laptop, pg_vexec runs 1.9x faster by geometric mean (1.3x by total time) than LTS ClickHouse on MergeTree, and 13x faster by geometric mean (18x by total time) on vexec_parquet. Full telemetry, charts, metrics and DBMS logs from the runs are published online. The CPU version's source code is also available. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does pg_vexec's performance compare to ClickHouse on ClickBench? pg_vexec, a vectorized PostgreSQL extension built on Greenplum's ORCA planner, beats ClickHouse on Parquet queries and nearly matches it on MergeTree in ClickBench runs. A rough-draft GPU version tested on an MSI Raider A18 HX A9W laptop ran 1.9x faster by geometric mean (1.3x total time) on MergeTree and 13x faster by geometric mean (18x total time) on vexec_parquet versus LTS ClickHouse. _Engineers evaluating analytical databases can follow fast-moving benchmark comparisons like this on daily.dev._ ### What is pg_vexec built from? pg_vexec is built by extracting Greenplum's ORCA analytical query planner and porting it onto PostgreSQL 19, turning PostgreSQL into a modern vectorized, high-performance DBMS. It started as a project to isolate the minimal PostgreSQL core patches needed to run this Greenplum-derived fork, published about a month before these benchmark results. _Developers tracking vectorized database engines can follow projects like pg_vexec on daily.dev._ ## Similar posts on daily.dev - [pg\_clickhouse is the fastest Postgres extension on ClickBench](https://daily.dev/posts/pg-clickhouse-is-the-fastest-postgres-extension-on-clickbench-kslwk5lud) · ClickHouse · 4 upvotes · 0 comments - [Rebuilding Postgres for 300x faster analytics: batching, operator fusion, and SIMD](https://daily.dev/posts/rebuilding-postgres-for-300x-faster-analytics-batching-operator-fusion-and-simd-tgtpnmlyi) · Hacker News · 0 upvotes · 0 comments - [Switching from PostgreSQL to ClickHouse for Improved Performance and Scalability](https://daily.dev/posts/switching-from-postgresql-to-clickhouse-for-improved-performance-and-scalability-kjtwee69g) · InfoQ · 5 upvotes · 0 comments --- Tags: [#postgresql](https://daily.dev/tags/postgresql), [#big-data](https://daily.dev/tags/big-data), [#clickhouse](https://daily.dev/tags/clickhouse) [View this post on daily.dev](https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"pg_vexec one month on: ahead of ClickHouse on Parquet, close behind on MergeTree","url":"https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3"},"datePublished":"2026-10-30T20:31:36.816Z","dateModified":"2026-10-30T20:32:00.765Z","description":"A month into building pg_vexec, a vectorized PostgreSQL engine that started as a way to extract Greenplum's ORCA planner, the engine now beats ClickHouse on...","image":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","thumbnailUrl":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","isAccessibleForFree":true,"articleSection":"Planet PostgreSQL","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Planet PostgreSQL","logo":"https://media.daily.dev/image/upload/logos/placeholder.jpg","url":"https://daily.dev/sources/planet-postgresql"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"postgresql,big-data,clickhouse","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Planet PostgreSQL","item":"https://daily.dev/sources/planet-postgresql"},{"@type":"ListItem","position":3,"name":"pg_vexec one month on: ahead of ClickHouse on Parquet, close behind on MergeTree"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/pg-vexec-one-month-on-ahead-of-clickhouse-on-parquet-close-behind-on-mergetree-htiq6euu3#faq","mainEntity":[{"@type":"Question","name":"How does pg_vexec's performance compare to ClickHouse on ClickBench?","acceptedAnswer":{"@type":"Answer","text":"pg_vexec, a vectorized PostgreSQL extension built on Greenplum's ORCA planner, beats ClickHouse on Parquet queries and nearly matches it on MergeTree in ClickBench runs. A rough-draft GPU version tested on an MSI Raider A18 HX A9W laptop ran 1.9x faster by geometric mean (1.3x total time) on MergeTree and 13x faster by geometric mean (18x total time) on vexec_parquet versus LTS ClickHouse. Engineers evaluating analytical databases can follow fast-moving benchmark comparisons like this on daily.dev."}},{"@type":"Question","name":"What is pg_vexec built from?","acceptedAnswer":{"@type":"Answer","text":"pg_vexec is built by extracting Greenplum's ORCA analytical query planner and porting it onto PostgreSQL 19, turning PostgreSQL into a modern vectorized, high-performance DBMS. It started as a project to isolate the minimal PostgreSQL core patches needed to run this Greenplum-derived fork, published about a month before these benchmark results. Developers tracking vectorized database engines can follow projects like pg_vexec on daily.dev."}}]} ```