faster
faster copied to clipboard
AdamNiederer
SIMD for humans
```rust vec![0u8; 100000].iter().map(|&x| { x as u64 * x as u64 }).sum::(); ``` is essentially what I'd like to use this crate to SIMD-accelerate. The issue I'm bumping into is...
Opening another ticket since this is a separate discussion from #47 and might be more controversial: The more I look into the upcoming `std::simd`, the more I wonder if `faster`...
After my last PR I noticed you had to clean up a bit. That made me wonder if it makes sense to configure and use `clippy` and `rustfmt`: * Since...
While working on #47 I noticed what looks like performance regressions in the `cargo bench`, in particular functions like `map_simd` and `map_scalar`, but quite a few others. ``` test tests::map_scalar...
Hi, I am trying to port a project to `aarch64` and `wasm` using the `rust-2018-migration` branch. As of today I receive lots of: ``` 2 | use crate::vektor::x86_64::*; | ^^^^^^...
I'm trying to get into SIMD by implementing a trivial operation: XOR unmasking of a byte stream as required by the WebSocket specification. The implementation in x86 intrinsics is actually...
If I am reading the code correctly, it looks like in the case of SSE2 Faster currently falls back to calling round()/floor() etc on each individual lane via the fallback...
I have a function which looks vaguely like this: ```rust struct Rect { real: f64, imag: f64 } struct KetRef KetRef
hey, I have spent a few minutes trying unsuccessfully to write a simd version of code that uses ndarray's [`zip_mut_with`](https://docs.rs/ndarray/0.10.14/ndarray/struct.ArrayBase.html#method.zip_mut_with) - is there currently a way of combining a `simd_iter_mut`...
I noticed that some methods return `Vec`s. In particular, it's `stride` and `scalar_collect`. I was wondering if it made sense to expose generic version that could use arbitrary `FromIterator` type....
