CelerData Products
Sub-second SQL engine for real-time analytics, lakehouse, and AI. Fully managed StarRocks on the cloud.
Sub-Second Queries for End Users and Agents
Deliver interactive analytics for end users and AI agents, with consistent sub-second performance at PB scale.
Sub-Second Queries
Delivers sub-second latency even under heavy concurrency, maintaining stable performance to meet strict SLA requirements.
On-the-Fly Join
Perform JOINs without denormalizing. The engine handles optimization while keeping performance high and pipelines simple.
Real-Time Updates
Apply appends, updates, and deletes with second-level data freshness so applications and users always work with up-to-date data.
Unlimited Scalability
Supports high-concurrency, multi-tenant workloads with predictable latency, even as thousands of users query the system simultaneously.
Fully Managed BYOC
Runs inside your own cloud environment with deployment, auto scaling, and operations fully managed by CelerData.
SQL Engine for Real-Time, Lakehouse, and AI
Innovative Cost-Based Optimizer
Support multi-table joins on the fly. Solve for good the slowness of distributed joins and enjoy the industry's best query performance.
Intelligent Caching System
Ensures a stable, data warehouse-like performance by eliminating the bottleneck of the underlying data lake system's slow performance.
SIMD-Optimized
Vectorized Query Engine
Experience the best in query performance with CelerData’s approach to pipeline execution using the massive parallelism of CPU cores.
CelerData Cloud BYOC
Your Cloud, Fully Managed. The only platform that delivers the full power of StarRocks with the security of a Bring-Your-Own-Cloud architecture. Retain complete data sovereignty and slash infrastructure costs with our fully managed, cloud-native solution.
Available on AWS, Azure, and GCP today.
Elasticity Without Compromise
CelerData Cloud's shared-data architecture decouples storage from compute, enabling independent scaling for every use case with multi-warehouse clusters.
Our autoscaling policies let you scale your cluster incrementally or in batches, using metrics like hardware usage and query queue depth to precisely align capacity with workload.
“After this migration to StarRocks, we observed multiple improvements. The migration reduced the p90 latency by 50% with only 32% of the instances required by the previous set up. This resulted in a 3-fold increase in cost-performance efficiency. The data ingestion process was also streamlined, achieving a data freshness of just 10 seconds.”
PINTEREST，CELERDATA CUSTOMER
"StarRocks is at the center of our real-time data analytics. We strive for quicker and easier insights into day to day operations. We chose StarRocks for its ability to upsert data in real-time, support for joins across large fact tables with very low latency, and the ability to serve and join native and external tables from the same cluster."
FANATICS，CELERDATA CUSTOMER
-2.webp)
“CelerData made migrating off of ClickHouse possible, and they’ve been there for everything we’ve needed. From ensuring cluster performance and stability to optimizing queries and rolling out enhancements at a rapid pace, we see a bright future with CelerData.”
DEMANDBASE，CELERDATA CUSTOMER
"We chose StarRocks primarily for its full compatibility with ANSI SQL and it's simple architecture, which simplifies application development, maintenance, and operations. It also delivers super-fast performance out of the box with minimal tuning, reducing our dashboard loading time from 5 minutes to 2 seconds.”
A TOP 3 U.S. GAME STUDIO，CELERDATA CUSTOMER
“We provide booking services for over 1.5 million hotels worldwide. By using CelerData we realized high-speed data analysis with an average query response speed of 200ms. Thanks to the unified data analytical architecture, manpower and hardware costs are greatly reduced.”
TRIP.COM GROUP，CELERDATA CUSTOMER