dremio product
SQL Query Engine
The fastest SQL engine with the best price-performance for Apache Iceberg, built on Apache Arrow
OVERVIEW
The Lakehouse Query Engine optimized for high performance and efficiency on Apache Iceberg and all your data
Sub-second BI workloads directly on your data lake and across all your data sources with no data movement. Deliver a seamless end-user experience with transparent query optimization and acceleration, optimized for Apache Iceberg
The #1 SQL Query Engine for Apache Iceberg
Designed from the ground up to be the fastest, most performant, and powerful SQL Query Engine for Apache Iceberg, Dremio delivers superior query performance and optimized price performance across all your data. Real-time memory management that dynamically manages memory and optimizes allocation reduces memory usage, heightens performance, scalability, and stability, and ensures successful analytical query operations even with vast datasets.
Optimized price performance for every query
Execute every query with the optimal balance of speed and cost-effectiveness. Dremio's multi-engine architecture enables sophisticated workload management. It's simple to create multiple right-sized, physically isolated engines for various workloads in your organization, ensuring market leading concurrency, performance predictability and making it easy to manage critical SLAs. Intelligent autoscaling dynamically manages your query workload based on established engine parameters.
Cost-based optimization ensures the fastest path to complete every query by understanding deep data statistics, including location, cardinality, and distribution.
Up to 100x faster performance with Reflections query acceleration
Attain near-instantaneous query performance with Reflections query acceleration. Reflections are optimized relational caches that use algebraic matching to accelerate entire or partial queries. Reflections are completely transparent to data users. During the query process, the Dremio optimizer matches the best Reflections to accelerate the query. Performance for all queries is also accelerated using Columnar Cloud Cache (C3). C3 selectively caches only the data required to satisfy your workloads, eliminating 90% of I/O costs.
Flexible, fast, lightweight data transformation
Reduce reliance on costly ETL tools and brittle, complex data pipelines. Dremio makes it easy to apply last mile data transformations, including filtering, sorting, aggregating, joining, casting. These transformations can be quickly built as Dremio Views - governed virtual data sets with layered transformations - that can be flexibly shared and modified for downstream data projects.
Federated querying for all your data, everywhere
Designed for interactive analytics and DML on the data lake, the Dremio SQL Query Engine makes it easy to analyze all of your data - whether on the data lake or in other data sources. Our connector ecosystem features dozens of integrations with an array of sources, including object storage, metastores, and databases in the cloud and on premises. Because Dremio queries your data at the source, there is no data movement, no data copies, and no complex ETL.
Built for the Cloud, Multi-Cloud, on-premises, and hybrid environments
Query your data where it lives - whether in the Cloud, across clouds, on-premises, or in hybrid environments. Dremio understands that many organizations choose to distribute their workloads across different cloud platforms, allowing them to leverage the strengths of each provider while avoiding vendor lock-in. With Dremio, you can access all of your data to put it to analytic work in seconds.
Built on Apache Arrow for fastest performance
Dremio's SQL Query Engine, powered by Apache Arrow, is core to delivering the best price-performance for queries across all your data. Dremio delivers lightning fast query performance as well as marketing leading query concurrency for lakehouse analytical workloads. In fact, Dremio developed Arrow and subsequently contributed it to the Apache Foundation. Arrow Flight is designed from the ground-up to support modern analytical workloads for columnar data structures and parallel processing.
customer stories
