nanobench
nanobench copied to clipboard
martinus
Simple, fast, accurate single-header microbenchmarking functionality for C++11/14/17/20
Trying to add nanobench via vcpkg manifest yields bizarre results. vcpkg manifest dependency looks like so, ``` ... "dependencies": [ "xtensor-blas", "nanobench", { "name": "highfive", "default-features": false, "features": [ "xtensor"...
Is there a mechanism (similar to google benchmark) to perform manual timing. I.e. not use the clock builtin to nanbench but provide our own iteration time to nanobench.
Can give hugely (about 100 times slower) differ results when run AVX2 code ```c++ int main(int argc, char ** argv) { alignas(32) float res[8]; float * mem = static_cast(operator new(256,...
I added this to debug the syscall auto fd = static_cast(syscall(__NR_perf_event_open, &pea, pid, cpu, mFd, flags)); std::cout
Currently `Result` doesn't have [any mutable method](https://github.com/martinus/nanobench/blob/master/src/include/nanobench.h#L419), which makes it hard to add custom variable or modify. For example we have a `relative(true)` benchmark result and we would like to...
The context variables are not used enough in this library by default. For instance, if you want to implement parametrised tests, you will need to put a lot of effort...
Hi there, thank you for making this library, it is pretty sweet! I'm looking for a micro-bencmarking library that could be used in a bare metal context as well as...
I'm looking for a way to create input for each batch. As an example, if I wanted to benchmark something like sorting algorithms I need to have a new unsorted...
