Related papers: Parallel Interleaver Design for a High Throughput …
The rapid growth in the size of large language models has necessitated the partitioning of computational workloads across accelerators such as GPUs, TPUs, and NPUs. However, these parallelization strategies incur substantial data…
With the rise of critical machine-to-machine applications, next generation wireless communication systems must be designed with strict constraints on the latency and reliability. A key question in this context relates to channel state…
Despite encouraging advances in the design of relay codes, several important challenges remain. Many of the existing LDPC relay codes are tightly optimized for fixed channel conditions and not easily adapted without extensive…
Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked accelerators with higher memory bandwidth and capacity. As LLMs scale to hundreds of billions or trillions of parameters, distributed inference across…
Fast, scalable decoding architectures that operate in a block-wise parallel fashion across space and time are essential for real-time fault-tolerant quantum computing. We introduce a scalable AI-based pre-decoder for the surface code that…
Pre-training large language models (LLMs) increasingly requires distributed compute, yet bandwidth constraints make it difficult to scale beyond well-provisioned datacenters-especially when model parallelism forces frequent, large…
Synchronization is likely the most critical performance killer in shared-memory parallel programs. With the rise of multi-core and many-core processors, the relative impact on performance and energy overhead of synchronization is bound to…
Due to the high sensitivity of qubits to environmental noise, which leads to decoherence and information loss, active quantum error correction(QEC) is essential. Surface codes represent one of the most promising fault-tolerant QEC schemes,…
Interleaving is a mechanism universally used in wireless access technologies to alleviate the effect of channel correlation. In spite of its wide adoption, to the best of our knowledge, there are no analytical models proposed so far. In…
This paper studies the complicated interplay of the completion time (as a measure of throughput) and the decoding delay performance in instantly decodable network coded (IDNC) systems over wireless broadcast erasure channels with memory,…
The problem of joint source-channel coding is considered for a stationary remote (noisy) Gaussian source and a Gaussian channel. The encoder and decoder are assumed to be causal and their combined operations are subject to a delay…
Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to…
This paper proposes an interleaved transceiver design method for a multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) system utilizing orthogonal frequency division multiplexing (OFDM) waveforms. We consider a…
As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…
Detection algorithms for multiple-input multiple-output (MIMO) wireless systems based on orthogonal frequency-division multiplexing (OFDM) typically require the computation of a QR decomposition for each of the data-carrying OFDM tones. The…
As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on the chip (e.g., Graphcore IPU). It…
In the FPGA (Field Programmable Gate Arrays) design flow, one of the most time-consuming step is the routing of nets. Therefore, there is a need to accelerate it. In a recent paper by Hoo et. al., the authors have developed a Linear…
Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…
The increasing complexity of deep neural networks (DNNs) poses significant challenges for edge inference deployment due to resource and power constraints of edge devices. Recent works on unary-based matrix multiplication hardware aim to…
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…