There’s a new computational workhorse in town. For decades, general matrix-matrix multiply—known as GEMM in Basic Linear Algebra Subroutines (BLAS) libraries—has been a standard benchmark for computational performance.
This is the second part of the blog post about explicit multi-GPU programming with DirectX 12. In this part, I’ll describe frame pipelining - a new way for utilizing multiple GPUs that was not possible before DirectX 12.
Want to see what’s next for NVIDIA Nsight™ Visual Studio Edition? A preview of version 5.3 is being shown at GDC 2017. This version will soon be available for download in the NVIDIA Registered Developer Program, but you can see it now at GDC or at least read about it here.