-
It looks like .NET Core 3 supports hardware intrinsics and has support for CRC32C:
https://github.com/dotnet/designs/blob/master/accepted/platform-intrinsics.md
_mm_crc32_u64
https://github.com/d…
-
The proposal seems to be geared towards a seamless interraction between intrinsics and std::simd, so that you can fall back to intrinsics when the standard does not provide the tools you want.
This…
-
### Background and motivation
Arm64 has `PRFM` instruction that prefetches the specified memory region into processor's cache.
A32 also has similar instructions.
It's nice to have support for Arm64…
-
Fast Fourier transforms are widely used for [applications](https://en.wikipedia.org/wiki/Discrete_Fourier_transform#Applications) in engineering, music, science, and mathematics.The current fft im…
Qiyu8 updated
3 years ago
-
support for effectively doing float32 float64, but actually operating on the 2 lower lanes of a float32. Currently the narrowest conversion operation is float32 float64, which results in emitting ex…
-
Rather than interoping to zlib when the Crc32 intrinsics are available on Arm and x86/x64
https://github.com/dotnet/runtime/blob/995224db011f77eb095279122244704ccca01d5f/src/libraries/System.IO.Com…
-
It would be interesting to have some benchmark so that we could check for possible performance issues.
-
### What is the problem this feature will solve?
As I am looking into ways to improve astropy performance, I can see that using the new'ish compiler feature of function multi-versioning should improv…
-
https://groups.google.com/forum/#!topic/julia-users/Jndl9sYwj5Q reports a performance regression in some simple code from a blog post that was meant to illustrate the importance of type stability: htt…
-
For a project I'm working on (DCT computation) I would really like to have `.powi()` and `.abs()` functions for `f64x2`. `.cos()` would be nice as well but I can live with a Taylor series approximatio…