My curiosity got the best me; so I implemented a SIMD-enabled string equality function just to find out ... (find out about the results here:)
https://github.com/the-moisrex/webpp/tree/dev/benchmarks/equals
https://github.com/the-moisrex/webpp/tree/dev/benchmarks/equals
GitHub
the-moisrex/webpp
C++ web framework. Contribute to the-moisrex/webpp development by creating an account on GitHub.
Today's benchmark's results are weird; do you know what's going on?
https://github.com/the-moisrex/webpp/tree/dev/benchmarks/is_alpha
https://github.com/the-moisrex/webpp/tree/dev/benchmarks/is_alpha
GitHub
the-moisrex/webpp
C++ web framework. Contribute to the-moisrex/webpp development by creating an account on GitHub.
Had a nice talk with Sean Baxter about attributes; remind me to use them in this framework when we can use them in our C++ projects in a couple of years.
https://twitter.com/the_moisrex/status/1313878622428594176
https://twitter.com/the_moisrex/status/1313878622428594176
Twitter
The Moisrex
@seanbax @Attribute Amazing. I can't wait to use them in my framework. thanks.
This little trick explains how re-calculating stuff can actually help you improve performance specially in SIMD.
Explained here: https://youtu.be/1ir_nEfKQ7A?t=402
Explained here: https://youtu.be/1ir_nEfKQ7A?t=402
YouTube
Halide: A Language for Fast, Portable Computation on Images and Tensors - Alex Reinking - CppCon 20
https://cppcon.org/
https://github.com/CppCon/CppCon2020
---
Halide is an open-source, domain-specific language for optimizing image processing, machine learning, and general array processing. It is used by major companies like Google, Adobe, and Qualcomm…
https://github.com/CppCon/CppCon2020
---
Halide is an open-source, domain-specific language for optimizing image processing, machine learning, and general array processing. It is used by major companies like Google, Adobe, and Qualcomm…
Web++: A C++ Web Framework
Can you believe this checks if two strings are equal or not case-insensitively? There's actually one more optimization I could do (which is written in shape of a todo comment).
I have no idea why ever that thing worked. The last few versions of that were totally wrong!
Web++: A C++ Web Framework
Don't waste clock cycles.
Implemented Accept-Encoding HTTP header parser. Implementing simple things can really get tricky sometimes.
Source is here:
https://github.com/the-moisrex/webpp/blob/dev/core/include/webpp/http/headers/accept_encoding.hpp
Source is here:
https://github.com/the-moisrex/webpp/blob/dev/core/include/webpp/http/headers/accept_encoding.hpp
Now I gotta learn ZLib for gzip;
What do library you recommend for "br", "compress", and "deflate"? Is there one that supports all of them?
https://zlib.net/zlib_how.html
What do library you recommend for "br", "compress", and "deflate"? Is there one that supports all of them?
https://zlib.net/zlib_how.html
This whole shenanigan is to make fmt library as a fallback for not-yet-implemented std::format.
Can't we just have a "stl_fallback.h" header?
Can't we just have a "stl_fallback.h" header?
Oh look, my reply to Heb Sutter's tweet is in his talk.
https://youtu.be/6lurOCdaj0Y
https://youtu.be/6lurOCdaj0Y
After benchmarking and testing some "normalize" algorithms, I just found out that even Poco library's implementation is faulty and not compatible with the RFC.
You'll find the benchmarks in the benchmark directory of the project.
And here's a test:
https://godbolt.org/z/T4jod8
And twitter thread to follow upon this; thanks to those who contributed their time for this, but I'm not gonna put that much time into this algorithm, it's not in a performance bottleneck of the framework at this point.
https://twitter.com/the_moisrex/status/1322644648435818503?s=20
Benchmark results on quick-bench (but of course 2 of those algorithms are buggy so it's not completely fair):
https://quick-bench.com/q/sT2UaEgvd9HpRCD5AZ6vgBbFWcs
You'll find the benchmarks in the benchmark directory of the project.
And here's a test:
https://godbolt.org/z/T4jod8
And twitter thread to follow upon this; thanks to those who contributed their time for this, but I'm not gonna put that much time into this algorithm, it's not in a performance bottleneck of the framework at this point.
https://twitter.com/the_moisrex/status/1322644648435818503?s=20
Benchmark results on quick-bench (but of course 2 of those algorithms are buggy so it's not completely fair):
https://quick-bench.com/q/sT2UaEgvd9HpRCD5AZ6vgBbFWcs
Found another GCC bug; is it a known issue or I should report this?
https://godbolt.org/z/xWadq6
https://godbolt.org/z/xWadq6
Web++: A C++ Web Framework
Found another GCC bug; is it a known issue or I should report this? https://godbolt.org/z/xWadq6
Here's a work around for this GCC 10.2.0 bug:
https://godbolt.org/z/3x98Y9
https://godbolt.org/z/3x98Y9
float and double is still not implemented for std::to_chars in GCC's STL!
So it's not working for double. Do I have to go and implement the whole thing myself now?
So it's not working for double. Do I have to go and implement the whole thing myself now?