GPU implementations of HPC applications relying on finite difference methods can include
tens of kernels that are memory-bound. Kernel fusion can improve performance by reducing …

Contemporary GPUs have significantly higher arithmetic throughput than a memory
throughput. Hence, many GPU kernels are memory bound and cannot exploit arithmetic …

Transfer learning in natural language processing (NLP) uses increasingly large models that
tackle challenging problems. Consequently, these applications are driving the requirements …

We present automatic horizontal fusion, a novel optimization technique that complements
the standard kernel fusion techniques for GPU programs. Unlike the standard fusion, whose …

Scaling neural network models has delivered dramatic quality gains across ML problems.
However, this scaling has increased the reliance on efficient distributed training techniques …

Chiplets are transforming computer system designs, allowing system designers to combine
heterogeneous computing resources at unprecedented scales. Breaking larger, mono-lithic …

Transfer learning in natural language processing (NLP), as realized using models like BERT
(Bi-directional Encoder Representation from Transformer), has significantly improved …

Graph sampling prepares training samples for graph learning and can dominate the training
time. Due to the increasing algorithm diversity and complexity, existing sampling frameworks …

Scaling neural network models has delivered dramatic quality gains across ML problems.
However, this scaling also increased the reliance on efficient distributed training techniques …

Modern accelerators like GPUs are increasingly executing independent operations
concurrently to improve the device's compute utilization. However, effectively harnessing it …