fury
fury copied to clipboard
A blazingly fast multi-language serialization framework powered by JIT and zero-copy.
### Question Is there a benchmark comparison with proto buffer?
### Question Hi, Fury shows the following (correct) warning for one of my classes: > class xy.SimplePrincipalCollection customized jdk serialization, which is inefficient. Please replace it with a org.apache.fury.serializer.Serializer or...
### Feature Request `Map` is very common in java, we can provide a fast serialization path for it to provide faster performance. ### Is your feature request related to a...
### Feature Request From the current [Kotlin README](https://github.com/apache/fury/blob/main/kotlin/README.md), Fury's Kotlin integration is described as "This provides additional Fury support for Kotlin Serialization on **JVM**". With the increasing adoption of KMP...
### Search before asking - [x] I had searched in the [issues](https://github.com/apache/fury/issues) and found no similar issues. ### Version 对象缓存到 redis 了,然后我新增了一个字段,就没办法反序列化了 ### Component(s) Java ### Minimal reproduce step 如果系统修改了实体类,更新系统的时候,就需要统一删除缓存...
### Search before asking - [X] I had searched in the [issues](https://github.com/apache/fury/issues) and found no similar issues. ### Version fury 0.9.0 Temurin 21.0.5 (x64) Windows 11 ### Component(s) Java ###...
## What does this PR do? Introduced simdutf to Fury, evaluated the implementation, and then chose a better implementation. First look at the execution rendering:  Here `_SIMD` represents the...
## What does this PR do? ## Related issues ## Does this PR introduce any user-facing change? - [ ] Does this PR introduce any public API change? - [...
### Feature Request Maybe we can try some portable SIMD libraries, like https://github.com/xtensor-stack/xsimd https://github.com/google/highway .. instead of handwritten intrinsic calls. because `xsimd` is also often used on `apache arrow` to...
## What does this PR do? This PR implemented an optimized version of `PyUnicode_FromUCS1/Fury_PyUnicode_FromUCS2` for faster performance by : - replace max char check using SIMD - Cast ucs2 array...