-
The vectorized query execution pipeline works automatically for some queries over the compressed hypertables, no user configuration is required.
Add a short explanation in https://docs.timescale.co…
-
OpenCV is a large dependency for cscore, but outside of interfaces is only used for image storage, resize, color conversion, and JPEG compression/decompression. The SIMD library (https://github.com/e…
-
**Is your feature request related to a problem? Please describe.**
Currently primitive array are serialized by copy the data buffer directly using `sun.misc.Unsafe`, this is super fast. Buf if all v…
-
PR #3101 added alignment in page layout and chunk layout, but PR #3099 still need to do a copy of the raw data read from disk to start decoding, [see the code here](https://github.com/lancedb/lance/bl…
-
Idea:
Each lane of SIMD computes an interleaved path in the input. Maybe 8-chars at a time. Compiler should be able to produce masked operations automatically in case of predicted or not predicted …
-
## Reason
Opencv use `libjpeg-turbo` as the default option of jpeg library. However, according to the official page of `libjpeg-turbe` project,
> libjpeg-turbo is a JPEG image codec that uses **…
-
The RISC-V vectors are finally stable, and even dev boards are realized. I suppose it's a perfect time to start working on RISC-V support.
Spec is here https://github.com/riscv/riscv-v-spec/releas…
-
Impressive results, well done Vlad.
Am I correct in thinking this improvement could apply not only to the `jpegtran` command line tool but also any compression made via the libjpeg shared library?
I…
-
Instead of the current 5 byte fixed encoding every time there's an alpha change, do a 2 byte alpha change followed by OP_DIFF/OP_LUMA/OP_RGB to encode the rgb elements. This changes nothing for RGB im…
-
**Abstract**
The open-source FastLanes project aims to improve big data formats, such as Parquet, ORC and columnar database formats, in multiple ways. In this paper, we significantly accelerate dec…