Graphene: An IR for Optimized Tensor Computations on GPUs
Bastian Hagedorn, Bin Fan, Hanfeng Chen, Cris Cecka, Michael J. Garland, Vinod Grover · 2023
Modern GPUs accelerate computations and data movements of multi-dimensional tensors in hardware. However, expressing optimized tensor computations in software is extremely challenging even for experts. Languages like CUDA C++ are centered around flat buffers in one-dimensional memory and lack reasonable abstractions for multi-dimensional data and threads. Existing tensor IRs are not expressive enough to represent the complex data-to-thread mappings required by the GPU tensor instructions.