Search Results for "simd"

Highly optimized 2D|3D math library, also known as OpenGL Mathematics (glm) for `C`. cglm provides lot of utils to help math operations to be fast and quick to write. It is community-friendly, feel free to bring any issues, bugs you faced. Almost all functions (inline versions) and parameters are documented inside the corresponding headers. OpenGL-related functions are dropped to make this lib platform/third-party independent. Make sure you have the latest version and feel free to report...

SLEEF stands for SIMD Library for Evaluating Elementary Functions. SLEEF implements vectorized versions of all C99 math functions, that utilize SIMD instructions of modern processors to make computation more efficient. The library also includes vectorized DFT subroutines.

* Fast C++ library for linear algebra (matrix maths) and scientific computing * Easy to use functions and syntax, deliberately similar to Matlab / Octave * Uses template meta-programming techniques to increase efficiency * Provides user-friendly wrappers for OpenBLAS, Intel MKL, LAPACK, ATLAS, ARPACK, SuperLU and FFTW libraries * Useful for machine learning, pattern recognition, signal processing, bioinformatics, statistics, finance, etc. * Downloads:...

...It provides fixed-size vector, matrix, and quaternion types with APIs that mirror the operations you actually use in inner loops—dot, cross, normalize, transforms, and projections. Implementations are carefully tuned to leverage SIMD instruction sets such as SSE and NEON while preserving a clean fallback path for portability. Because types are fixed at compile time, the compiler can aggressively inline and unroll code, producing predictable performance and tiny binaries. The design emphasizes minimal dependencies and clear ownership so the library can be embedded into engines without dragging in heavyweight frameworks. ...

The first parallel and distributed library for pairwise correlation/dependence computation on Intel Xeon Phi clusters. This library is written in C++ template classes and achieves high speed by exploring the SIMD-instruction-level and thread-level parallelism within Xeon Phis as well as accelerator-level parallelism among multiple Xeon Phis. To facilitate balanced workload distribution, we have proposed a general framework for symmetric all-pairs computation by building provable bijective functions between job identifier and coordinate space for the first time.

...author's page http://www.slis.tsukuba.ac.jp/~s1530534/index.html e-mail hishinuma@slis.tsukuba.ac.jp Double-Double (DD) precision operations are used to reduce rounding errors and improve the convergence of Krylov subspace methods. This library has Double-Double precision operations accelerated by AVX and AVX2. AVX and AVX2 are intel SIMD instructions. They operate four double precision operation simultaneously. This library needs to merge "Lis" for DD precision iterative solvers. Official support "Lis" version is "lis-1.4.58." After merge "lis" and "DD-AVX," the interface is same as "lis." Lis web page http://www.ssisc.org/lis/index.en.html This library is managed by git. old version can search "code" page.

Highly efficient implementation of BLAS for sparse block matrices. Accelerated using heavy-duty C++ meta-programming, SIMD instructions and GPU.

GENIAL is a C++ library for signal and image processing. It uses template-generic techniques, multi threading, cache optimization and SIMD instructions for Pentium (MMX, SSE, SSE2, SSE3) to achieve high performance: FFT,DCT,Convolution,Linear Algebra...

This library is meant for high performance calculations for science or 3D games/rasterizers using SIMD instructions of x86 processors to allow an unparalleled level of optimization. This takes advantage of MMX, 3DNow!, 3DNow!+/MMX+, & SSE/SSE2/SSE3/SSSE3

ObjC framework for mathematical operations. Various DSP (inc. FFT + wavelet), statistical operations and more on vector and array types. Optimized for SIMD and multi-threading where possible.

Improving the speed of the signal analysis code for Seti@home. Leveraging modern processors advanced features such as SIMD and parallel execution units, as well as identifying better methods to code existing functions.