Items tagged with rocm 1.3

For those of you that have been keeping up with AMD’s Boltzmann Initiative, the company has been moving at a rapid clip to overhaul its HPC software stack for use with its GPUs. AMD's solution not only compares favorably with NVIDIA's CUDA, but developers can also reuse much of its code base (up to 90 percent according to AMD). When AMD initially launched the Boltzmann Initiative late last year, it had these three goals in mind: New Linux Driver and Runtime Stack optimized for HPC & Ultra-scale class computing, Heterogeneous C and C++ compiler which best address the whole system not just a single device HIP acknowledging the need for platform choice when utilizing GPU computing API Since... Read more...