A Benchmark Toolkit for Assembly Instructions Using the LLVM JIT
Project description
asmbench
A benchmark toolkit for assembly instructions using the LLVM JIT.
Usage
To benchmark latency and throughput of a 64bit integer add use the following command:
python -m asmbench 'add {src:i64:r}, {srcdst:i64:r}'
To benchmark two instructions interleaved use this:
python -m asmbench 'add {src:i64:r}, {srcdst:i64:r}' 'sub {src:i64:r}, {srcdst:i64:r}'
To find out more add -h for help and -v for verbose mode.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
asmbench-0.1.4.tar.gz
(30.4 kB
view hashes)