Related papers: Improving Latency in a Signal Processing System on…
Data and pipeline parallelism are ubiquitous for training of Large Language Models (LLM) on distributed nodes. Driven by the need for cost-effective training, recent work explores efficient communication arrangement for end to end training.…
Most existing random walk based network embedding methods often follow only one of two principles, homophily or structural equivalence. In real world networks, however, nodes exhibit a mixture of homophily and structural equivalence, which…
We review our last work on dispersion-engineered heterogeneous multicore fiber links designed to act as tunable true time delay lines for radiofrequency signals. This approach allows the realization of fiber distributed signal processing in…
By placing computation resources within a one-hop wireless topology, the recent edge computing paradigm is a key enabler of real-time Internet of Things (IoT) applications. In the context of IoT scenarios where the same information from a…
A variety of computing platform like Field Programmable Gate Array (FPGA), Graphics Processing Unit (GPU) and multicore Central Processing Unit (CPU) in data centers are suitable for acceleration of data-intensive workloads. Especially,…
The nanoPU is a new networking-optimized CPU designed to minimize tail latency for RPCs. By bypassing the cache and memory hierarchy, the nanoPU directly places arriving messages into the CPU register file. The wire-to-wire latency through…
This paper describes a parallel implementation of Viterbi decoding algorithm. Viterbi decoder is widely used in many state-of-the-art wireless systems. The proposed solution optimizes both throughput and memory usage by applying…
Neuromorphic systems that learn and predict from streaming inputs hold significant promise in pervasive edge computing and its applications. In this paper, a neuromorphic system that processes spatio-temporal information on the edge is…
IoT applications increasingly rely on on-device AI accelerators to ensure high performance, especially in low-connectivity and safety-critical scenarios. However, the limited on-chip memory of these accelerators forces inference runtimes to…
For a deep learning model, efficient execution of its computation graph is key to achieving high performance. Previous work has focused on improving the performance for individual nodes of the computation graph, while ignoring the…
The Internet Engineering Task Force (IETF) group "IPv6 over the TSCH mode of IEEE 802.15.4e" (6TiSCH) introduced a protocol, utilizing Time-Slotted Channel Hopping (TSCH) from IEEE802.15.4e due to its high reliability and time-deterministic…
Lattice reduction (LR) is a preprocessing technique for multiple-input multiple-output (MIMO) symbol detection to achieve better bit error-rate (BER) performance. In this paper, we propose a customized homogeneous multiprocessor for LR. The…
While FPGA accelerator boards and their respective high-level design tools are maturing, there is still a lack of multi-FPGA applications, libraries, and not least, benchmarks and reference implementations towards sustained HPC usage of…
Breakthroughs in the generative AI domain have fueled an explosion of large language model (LLM)-powered applications, whose workloads fundamentally consist of sequences of inferences through transformer architectures. Within this rapidly…
Dataflow-based CNN accelerators on FPGAs achieve low latency and high throughput by mapping computations of each layer directly to corresponding hardware units. However, layers such as pooling and strided convolutions reduce the data at…
Developing high-performance and energy-efficient algorithms for maximum matchings is becoming increasingly important in social network analysis, computational sciences, scheduling, and others. In this work, we propose the first maximum…
The bulk-synchronous parallel (BSP) model provides a framework for writing parallel programs with predictable performance. In this paper we extend the BSP model to support what we will call pseudo-streaming algorithms for accelerators. We…
Multi-port memory controllers (MPMCs) have become increasingly important in many modern applications due to the tremendous growth in bandwidth requirement. Many approaches so far have focused on improving either the memory access latency or…
Manycore processors feature a high number of general-purpose cores designed to work in a multithreaded fashion. Recent manycore processors are kept coherent using scalable distributed directories. A paramount example is the Intel Mesh…
Micro-core architectures combine many low memory, low power computing cores together in a single package. These are attractive for use as accelerators but due to limited on-chip memory and multiple levels of memory hierarchy, the way in…