Parallel multithreaded actors without locks P&L: -8 (≃ -2315 TWD)
Implement efficient scalable multiple thread communication
github.com/samsquire/multiversion-concurrency-control/blob/main/src/main/java/main/Main.java
YAML
項目
產品
This project is to implement efficient multithreading to maximise use of all CPU cores, without too much overhead.
-8.0000 ħ (8.0 HUR) (+0.0)
For 100 threads I managed to get 100 million multithread communication event requests a second, taking 10 nanoseconds to communicate between threads
大多數計算機使用鎖來同步,這非常慢。這種設計速度要快得多,並且允許省略鎖以提高性能。
我使用非同步數據結構,並以每批消息 10 納秒的成本實現每秒 1 億次請求的原始通信性能。
- 以原本語言顯示 -
Most computers use locks to synchronize, which are very slow. This design is far faster and allows locks to be elided for performance.
I use unscynchronized data structures and achieve 100 million requests a second raw communication performance for a cost of 10 nanoseconds per batch of messages.