Andrew Lumsdaine, Chief Scientist at Northwest Institute for Advanced Computing, shares his journey in parallelism, from the HPC community’s early skepticism of and eventual move to C++ to build large systems, to his pursuit to develop a series of C++ libraries to strike at the contradiction between abstraction and performance, to today’s reality that parallelism and heterogeneity are essential for achieving performance. Together, Andrew and Mike Voss, Principal Engineer at Intel, underscore the value of open standards and high-quality implementations of open standards—specifically, the oneAPI specification and Intel oneAPI toolkits, respectively—and provide listeners with ways to get involved in helping shape ISO C++, Khronos SYCL, DPC++ and oneAPI.

Guests:
Andrew Lumsdaine, Chief Scientist, Northwest Institute for Advanced Computing
Mike Voss, Principal Engineer, Intel

To learn more:
oneAPI.com
Intel oneAPI Toolkits

Read/Download the transcript

Tags: C++, deep neural network, DPC++, heterogeneous, high performance computing, hipSYCL, HPC, Intel DevCloud, libraries, Math Kernel Library, MPI, oneAPI, oneDNN, oneMKL, Open Standards, parallel programming, parallelism, portability, Standards, SYCL, Threading Building Blocks, triSYCL
 
Posted in: Audio Podcast, Code Together, Intel