sleef
sleef copied to clipboard
SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT
There have been several requests for providing vectorized SLEEF functions in a header file, https://github.com/shibatch/sleef/issues/230 It turned out that this functionality is not too hard to implement. We can use...
In PyTorch, we'd like to use Sleef's vectorized implementation of elementary functions as building blocks. For example, we'd like to implement a vectorized [`sigmoid()`](https://en.wikipedia.org/wiki/Sigmoid_function) function using `exp`. However, calling into...
Currently, ``sleefgnuabi`` follows... GNU ABI, also used by ``libmvec``. ### Problem Problems could arise if linking is not done perfectly correctly (presence, in right position, of ``-lsleefgnuabi`` in the linker...
Would it be possible to get the settings used for each of the gencoef invocations in order to reproduce each of the polynomials?
Raising scalars and vectors to integer powers is very common (e.g. [`llvm.powi`](https://llvm.org/docs/LangRef.html#llvm-powi-intrinsic)), so I think the following APIs would be very useful: * double Sleef_ipow_u10(double x, int32_t y); * __m128d...
I feel there's something wrong with the usage of the build tool when I have to make a complete native build prior to cross compiling. I found this script which...
This is the first step in a slightly long path of removing compiled binaries used as part of the build process. This performs the generation of mkalias and most of...
After collecting some evidence and doing some research, I believe sleef is not using the vector calling convention on windows. 1. there is no mention of `__vectorcall` in the code....
Hello, I'm trying to install Sleef on Windows. My system is Windows 10 Pro 64 Bit with Visual Studio 2017 (15.5.6). The problem is Cmake requires a file called `CMakeLists.txt`....
I replace all appearance of `#include ` with `#include "sleef_math.h"` in my project, while `sleef_math.h` looks like: ```cpp #define sin Sleef_sinf_u35 #define cos Sleef_cosf_u35 ... ``` However, i don't see...