sleef
sleef copied to clipboard
SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT
It actually works fine.
In GCC12 and GCC13 latest versions, the bug which was causing test failures in this project has been fixed. In GCC14 release series, the bug is not present. Hence we...
Although sleef 3.6 is supposed to be an ABI-compatible update for 3.5.1 (the SONAME version is still 3), comparing the main shared library using [`fedabipkgdiff`](https://sourceware.org/libabigail/manual/fedabipkgdiff.html) from libabigail shows that a...
It looks like the build system is special-cased for clang on windows (using SLEEF_CLANG_ON_WINDOWS variable). Most of these cases make sense, but in Configure.cmake we do not able GNUABI if...
Here `CONFIG=1` defaults to a run-time determination of the hardware vector length: https://github.com/shibatch/sleef/blob/cf532e214843c30023c269cf48aa7e84eaffb432/src/arch/helperrvv.h#L20 If the symbol `__riscv_v_fixed_vlen` is defined then the compiler is generating code which supports _only_ that specified...
https://github.com/ARM-software/optimized-routines/tree/master/math/aarch64 implements some math operations with neon simd instructions. The perf looks good, especially for exp(). I'm wondering if it's possible to integrate ARM-software/optimized-routines into sleef? Thanks!
aarch64-gcc-12, ppc64el-gcc-12, and s390x-gcc-12 are not enabled as they are failing with https://github.com/shibatch/sleef/issues/483
after mkdir build cd build cmake .. cmake --build . --config Release -- /maxcpucount:1 getting error C:\Users\savel\sleef\build\src\libm\dispscalar.c(26,1): error C2065: 'Sleef_sind1_u35purec': undeclared identifier [C:\ Users\savel\sleef\build\src\libm\dispscalar_obj.vcxproj] C:\Users\savel\sleef\build\src\libm\dispscalar.c(26,1): error C2065: 'Sleef_sind1_u35purecfma': undeclared identifier...
I use this cmake cmd for configuration for arm arch64 for crossing compile and my desktop is ubuntu system. I runinto some errors please see the logs. how to solve...