Measured Results

PRISM performance.

Real-world measurements on a single server with 64 GB RAM (recommended specification).
All figures below are the median of three runs in a reproducible environment.

<1s Cube serving response 100M-row source · 200-row result · Median of 3 runs
499 ms p95 at 20 concurrent users 10M rows · 30-column OLAP aggregation · Cube serving path
<200 MB Memory per query Fixed regardless of data size · Columnar streaming architecture
01 · Processing Time by Data Scale

From 100K to 100M rows.

Initial cube build aggregates data from the source database.
All subsequent queries use cube serving — millisecond response, independent of source DB load.

Data ScaleCube Build (one-time)Cube ServingPeak Memory
100K rows0.3 s< 1 s< 200 MB
1M rows0.4 s< 1 s< 200 MB
10M rows1.7 s< 1 s< 200 MB
100M rows14.4 s< 1 s< 200 MB

About these numbers: Cube build time includes source-database aggregation and varies with source DB performance.
Peak memory is measured for a single query (100M rows → 200-row result).

02 · Response Time Under Concurrent Load

Stable response — even at 20 concurrent users.

The cube serving path maintains consistent response times as concurrent user count increases.
Measured on 10M rows with 30-column OLAP aggregation.

Concurrent UsersMedian Response (p50)95th-Percentile (p95)
1 user< 200 ms< 300 ms
10 users~ 300 ms~ 400 ms
20 users417 ms499 ms
03 · System Stability

No query size affects service availability.

Streaming processing writes results in chunks, keeping memory usage independent of data size.

Memory during query stays under 200 MB regardless of data size.
Large queries and other users' workloads are fully isolated.
Group-level resource policies enable balanced allocation across teams.
04 · Measurement Environment

Transparent conditions.

All figures on this page were measured in the following environment, with full reproducibility.

Server64 GB RAM (recommended)
Source DBEnterprise RDBMS
DataSynthetic, reproducible
Run count657 runs · median of 3

Run the benchmark on your environment.

We will replicate these measurements on your hardware and data shape.
Side-by-side comparison delivered within 48 hours.