All blogs / Performance / optimization
Experiments in program optimisation ququMy blogwewe
Experiments and research in program performance and optimisation
Performance / optimizationJava / JVMAlgorithms / data structures
- Posts
- 40 from 15 Apr 2014 to 7 Oct 2019
- Posting
- quiet since 2019
- Kind
- personal blog
- Feed
- http://pzemtsov.github.io/feed.xml
2019 4
2018 1
2017 2
2016 6
2015 12
- Implementing Peano arithmetic
- Choosing the hash map's capacity
- Optimising the hash-based Life
- CRC32: intrinsic, Java or C with JNI?
- Don't trust a micro-benchmark
- More optimisations of division-based hash: Karatsuba's method
- The fun and the cost of refactoring
- Optimising division-based hash functions
- Hash functions: disassembling and measuring performance
- Game of Life, hash tables and hash codes
- Standard input, buffering and affinity mask
- On the benefits of stream buffering in Java
2014 15
- More experiments with cache
- How cache affects demultiplexing of E1
- Lambdas and other callbacks in Java
- Macros, call by name, lambda and Jensen's device
- Bug story 2: Unrolling the 16×16 matrix transposition, or be careful with macros
- How to transpose a 16×16 byte matrix using SSE
- A bug story: testing your test code
- Fast E1 de-multiplexing in C using SSE/AVX
- Size does matter
- How to make C run as fast as Java
- The mystery of an unstable performance
- From macros to templates
- One handy C idiom: multi-statement macro
- De-multiplexing of E1 stream: converting to C
- De-multiplexing of E1 streams in Java