daiduo/TurboPFor-Integer-Compression
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

.

Browse Source
This commit is contained in:
x
2018-02-13 19:55:34 +01:00
parent 65361d1393
commit a13293fc8a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -27,8 +27,8 @@ TurboPFor: Fastest Integer Compression [![Build Status](https://travis-ci.org/po
* Delta/Delta of delta + (Differential) Finite Context Method FCM/DFCM floating point compression * Delta/Delta of delta + (Differential) Finite Context Method FCM/DFCM floating point compression
* Using **TurboPFor**, unsurpassed compression and more than 5 GB/s throughput * Using **TurboPFor**, unsurpassed compression and more than 5 GB/s throughput
* :new: **Time Series Compression** * :new: **Time Series Compression**
* **Fastest Gorilla** style compression with **variable byte** or **bit/io**. * **Fastest Gorilla** style compression (incl. **RLE**) with **variable byte** or **bit/io**.
* Full range 32/64 bits, more efficient. > 5 GB/s compression and > 10 GB/s decompression * Full range 32/64 bits, better compression. Up to 15 GB/s compression and > 10 GB/s decompression
* **Inverted Index ...do less, go fast!** * **Inverted Index ...do less, go fast!**
* Direct Access to compressed *frequency* and *position* data w/ zero decompression * Direct Access to compressed *frequency* and *position* data w/ zero decompression
* **Novel** **"Intersection w/ skip intervals"**, decompress the minimum necessary blocks (**~10-15%)!**. * **Novel** **"Intersection w/ skip intervals"**, decompress the minimum necessary blocks (**~10-15%)!**.