Michel Migdal

Michel Migdal holds a double master’s degree in Engineering and Computer Science from the University of Paris Saclay and the ENSIIE. Michel currently works as a senior GPU software engineer with the cuBLAS team at NVIDIA, where he started a new analytical GEMM heuristics initiative for kernel generators. In parallel, he works on optimizing and developing new kernels for current and upcoming architectures. Previously Michel worked in the nvJpeg team to develop new codecs.
Avatar photo

Posts by Michel Migdal

Models / Libraries / Frameworks

Improving GEMM Kernel Auto-Tuning Efficiency on NVIDIA GPUs with Heuristics and CUTLASS 4.2

Selecting the best possible General Matrix Multiplication (GEMM) kernel for a specific problem and hardware is a significant challenge. The performance of a... 8 MIN READ