The rapidly growing popularity and scale of data-parallel workloads demand a
corresponding increase in raw computational power of Graphics Processing Units (GPUs) …

As modern GPU workloads grow in size and complexity, there is an ever-increasing demand
for GPU computational power. Emerging workloads contain hundreds or thousands of GPU …

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

Resource-constrained system-on-chips (SoCs) are increasingly heterogeneous with
specialized accelerators for various tasks. Acceleration taxes due to control and data …

The fifth generation of cellular mobile communication called 5G will be publicly available in
the near future to connect more than 8.4 billion devices. 5G has been designed to improve …

Performance and efficiency requirements are driving a trend towards specialized
accelerators in both datacenters and embedded devices. In order to cut down …

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

GPUs are known to benefit structured applications with ample parallelism, such as deep
learning in a datacenter. Recently, GPUs have shown promise for irregular streaming …

GPU accelerators have established themselves in the state‐of‐the‐art clusters by offering
high performance and energy efficiency. In such systems, efficient inter‐process GPU …

Chiplet-based architectures have recently emerged as a technique to improve yields and
enable continued performance scaling. However, the increased modularity and scalability …