Related papers: A Case for Fine-grain Coherence Specialization in …
We consider a transportation system of heterogeneously connected vehicles, where not all vehicles are able to communicate. Heterogeneous connectivity in transportation systems is coupled to practical constraints such that (i) not all…
Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…
Massive MIMO is a cornerstone of next-generation wireless communication, offering significant gains in capacity, reliability, and energy efficiency. However, to meet emerging demands such as high-frequency operation, wide bandwidths,…
With the rapid evolution of GPU architectures, the heterogeneity of model training infrastructures is steadily increasing. In such environments, effectively utilizing all available heterogeneous accelerators becomes critical for distributed…
Heterogeneous architectures can deliver higher performance and energy efficiency than symmetric counterparts by using multiple architectures tuned to different types of workloads. While previous works focused on CPUs, this work extends the…
On-chip communication infrastructure is a central component of modern systems-on-chip (SoCs), and it continues to gain importance as the number of cores, the heterogeneity of components, and the on-chip and off-chip bandwidth continue to…
We present a number of novel algorithms, based on mathematical optimization formulations, in order to solve a homogeneous multiprocessor scheduling problem, while minimizing the total energy consumption. In particular, for a system with a…
Convolutional neural networks (CNNs) require both intensive computation and frequent memory access, which lead to a low processing speed and large power dissipation. Although the characteristics of the different layers in a CNN are…
The significant resource demands in LLM serving prompts production clusters to fully utilize heterogeneous hardware by partitioning LLM models across a mix of high-end and low-end GPUs. However, existing parallelization approaches often…
Fast-evolving artificial intelligence (AI) algorithms such as large language models have been driving the ever-increasing computing demands in today's data centers. Heterogeneous computing with domain-specific architectures (DSAs) brings…
Distributed processing across a networked environment suffers from unpredictable behavior of speedup due to heterogeneous nature of the hardware and software in the remote machines. It is challenging to get a better performance from a…
Sparse-dense linear algebra is crucial in many domains, but challenging to handle efficiently on CPUs, GPUs, and accelerators alike; multiplications with sparse formats like CSR and CSF require indirect memory lookups. In this work, we…
Conventional wisdom holds that an efficient interface between an OS running on a CPU and a high-bandwidth I/O device should use Direct Memory Access (DMA) to offload data transfer, descriptor rings for buffering and queuing, and interrupts…
Heterogeneous multi-core architectures combine a few "host" cores, optimized for single-thread performance, with many small energy-efficient "accelerator" cores for data-parallel processing, on a single chip. Offloading a computation to the…
Heterogeneous computing can potentially offer significant performance and performance per watt improvements over homogeneous computing, but the question "what is the ideal mapping of algorithms to architectures?" remains an open one. In the…
Privacy, security and data governance constraints rule out a brute force process in the integration of cross-silo data, which inherits the development of the Internet of Things. Federated learning is proposed to ensure that all parties can…
Structured Cartesian grids are a fundamental component in numerical simulations. Although these grids facilitate straightforward discretization schemes, their na\"{i}ve use in sparse domains leads to excessive memory overhead and…
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural…
Embedded systems are parts of our daily life and used in many fields. They can be found in smartphones or in modern cars including GPS, light/rain sensors and other electronic assistance mechanisms. These systems may handle sensitive data…
The widely-adopted practice is to train deep learning models with specialized hardware accelerators, e.g., GPUs or TPUs, due to their superior performance on linear algebra operations. However, this strategy does not employ effectively the…