Author: EMail | Price: 0 | License: Freeware
O/S: Win 11 32Bit | Category: Internet | Downloads: 0
DSATS : Research & Project Architecture and Scture Aware Linear Algebra Linear algebra (LA) operations are fundamental to a large number ofputational science algorithms. LA algorithms isplicated by the increasing architectural heterogeneity of the high-performanceputing (HPC) platforms. This project aims to build an Architecture and Data-Scture Aware Linear Algebra (ADSALA) software package that will use machine learning to learn the hardware/data-scture/package/algorithm relationships whenpiled on a specific hardware architecture for a specm of LA packages. DSATS : Research & Project The pursuit of optimal LA algorithms is significantlyplicated by the increasing architectural heterogeneity of the high-performanceputing (HPC) platforms, with a variable mix of general-purpose processors (CPUs) and elerators (GPUs, DSPs, FPGAs, etc.), andplex associated memory hierarchies and file systems. DSATS : Research & Project Linear algebra (LA) operations are fundamental to a large number ofputational science algorithms. The applications span the entire scientific board, with machine learning (ML) algorithms being among the most reliant on LA operations; they provide the mathematics that underpins much of what we do. Historically, this fact has driven the development of a plethora of libraries providing high-performance implementations of LA algorithms: BLAS, OpenBLAS, cuBLAS, CLBLAS, LAPACK, ARPACK, ATLAS, cuSOLVER, MAGMA and many more. For a given LA operation, the choice can be bewildering for the programmer, especially given that within the same library there may be several algorithms yielding different performance depending, for example, on the specific scture of the matrices involved.