Abstract: Matrix-vector multiplication (MVM) underpins modern AI workloads, yet scaling it on electronic hardware is increasingly constrained by energy, bandwidth, and latency bottlenecks. Photonic ...
* Program re-ordering for improved L2 cache hit rate. * Automatic performance tuning. # Motivations # Matrix multiplications are a key building block of most modern high-performance computing systems.
In this tutorial, you will write a very short high-performance FP32 matrix multiplication kernel. You will specifically learn about: * Block-level matrix multiplications. * Multi-dimensional pointer ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results