Cris Cecka

Dr. Cris Cecka received his PhD from Stanford University in Computational and Mathematical Engineering in 2011. He joined the new Institute for Applied Computational Science at Harvard University as a lecturer and research scientist where he created courses on parallel computing and robust software development. He also worked in the Mathematics Department at the Massachusetts Institute of Technology as a research associate where he focused on integral equation methods, structured dense matrix factorizations, and generalized N-body problems using hierarchical algorithms. In 2015, Cris joined NVIDIA Research to combine all of these interests in designing advanced numerical algorithms and software.
Avatar photo

Posts by Cris Cecka

Models / Libraries / Frameworks

CUTLASS 3.x: Orthogonal, Reusable, and Composable Abstractions for GEMM Kernel Design

GEMM optimization on GPUs is a modular problem. Performant implementations need to specify hyperparameters such as tile shapes, math and copy instructions, and... 12 MIN READ
Models / Libraries / Frameworks

CUTLASS: Principled Abstractions for Handling Multidimensional Data Through Tensors and Spatial Microkernels

In the era of generative AI, utilizing GPUs to their maximum potential is essential to training better models and serving users at scale. Often, these models... 12 MIN READ
GPU Pro Tip
Simulation / Modeling / Design

Pro Tip: cuBLAS Strided Batched Matrix Multiply

There’s a new computational workhorse in town. For decades, general matrix-matrix multiply—known as GEMM in Basic Linear Algebra Subroutines (BLAS)... 10 MIN READ