Using accelerators in HPC has pushed performance to new levels. Starting with early GPUs, the ability to take advantage of the parallel processing hardware (in the form of SIMD processing) has been a huge boon for HPC performance. As a result, the HPC market has been a big driver for GPU designs, including features like ECC memory and fast 64-bit double precision, not to mention toolsets aimed at languages like Fortran and C.
The post Have You Heard About the Ozaki Scheme? You Will appeared first on HPCwire.
