With the release of version 1.7.9, ZenQL’s Collection API, Thor, received substantial performance improvements, largely driven by a series of memory optimization enhancements. These changes reduced unnecessary allocations, improved data handling efficiency, and significantly accelerated query execution, particularly when working with large in-memory datasets.
From the early stages of development, we established a baseline benchmark to measure both correctness and performance consistently: filtering a slice of 50 million items and validating the result.
The original Collection API completed this benchmark in approximately 9 seconds.
Later, we introduced Thor as a replacement for the default Collection API, reducing the benchmark time to around 4 seconds.
With the latest round of memory optimizations and internal improvements, Thor now completes the same benchmark in less than one second.
