# How we scaled raw GROUP BY to 100 B+ rows in under a second

DevFeed: [How we scaled raw GROUP BY to 100 B+ rows in under a second](<https://devfeed.tech/articles/how-we-scaled-raw-group-by-to-100-b-rows-in-under-a-second-5111.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/clickhouse-parallel-replicas>)

Author: Tom Schreiber

Published: 2025-09-29T00:00:00Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [AI, ML & Data Engineering](<https://devfeed.tech/topics/ai-ml-data-engineering.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [internals](<https://devfeed.tech/tags/internals.md>), [performance](<https://devfeed.tech/tags/performance.md>), [scale](<https://devfeed.tech/tags/scale.md>), [spark](<https://devfeed.tech/tags/spark.md>)

## AI overview

ClickHouse Cloud introduces parallel replicas to distribute a single analytical query across cluster cores, aiming to scale GROUP BY workloads horizontally without data reshuffling.

## Source excerpt

ClickHouse Cloud now scales analytical queries with parallel replicas, fanning a single query across thousands of cores for terabyte-per-second throughput. This post dives into the internals and lets you see and feel the speed.