相关论文: Scaling Data Center TCP to Terabits with Laminar

The rapid expansion of the model context protocol (MCP) ecosystem enables large language model (LLM)-based agents to access a wide range of external tools via a standardized interface. However, identifying appropriate MCP servers for a…

This paper introduces a parallel and asynchronous Transformer framework designed for efficient and accurate multilingual lip synchronization in real-time video conferencing systems. The proposed architecture integrates translation, speech…

We present a highly parallelizable text compression algorithm that scales efficiently to terabyte-sized datasets. Our method builds on locally consistent grammars, a lightweight form of compression, combined with simple recompression…

Portability, performance, and productivity are three critical dimensions for evaluating a programming model or compiler infrastructure. Several modern programming models for computational science focus on performance and portability. On the…

A hybrid transmit precoder (TPC) and receive combiner (RC) pair is conceived for millimeter wave (mmWave) multiple input multiple output (MIMO) integrated sensing and communication (ISAC) systems. The proposed design considers a practical…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…

This paper presents the Distributed Adaptive Multi-Radio Cross-Layer Routing (DAMCR) protocol, designed to enhance reliability, adaptability, and energy efficiency in smart grid and industrial Internet of Things (IoT) communication…

As parallelism becomes critically important in the semiconductor technology, high-performance computing, and cloud applications, parallel network systems will increasingly follow suit. Today, parallelism is an essential architectural…

This paper presents the first reliable physical-layer network coding (PNC) system that supports real TCP/IP applications for the two-way relay network (TWRN). Theoretically, PNC could boost the throughput of TWRN by a factor of 2 compared…

Large-scale distributed Multiuser MIMO (MU-MIMO) is a promising wireless network architecture that combines the advantages of "massive MIMO" and "small cells." It consists of several Access Points (APs) connected to a central server via a…

Distributed storage employs replication to mask failures and improve availability. However, these systems typically exhibit a hard tradeoff between consistency and performance. Ensuring consistency introduces coordination overhead, and as a…

Modern high-performance servers commonly integrate Simultaneous Multithreading (SMT) processors, which efficiently boosts throughput over single-threaded cores. Optimizing performance in SMT processors faces challenges due to the…

The performance of large-scale computing systems often critically depends on high-performance communication networks. Dynamically reconfigurable topologies, e.g., based on optical circuit switches, are emerging as an innovative new…

Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…

The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving…

While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed -…

We present and evaluate the ExaNeSt Prototype, a liquid-cooled rack prototype consisting of 256 Xilinx ZU9EG MPSoCs, 4 TBytes of DRAM, 16 TBytes of SSD, and configurable interconnection 10-Gbps hardware. We developed this testbed in…

A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a…

Conformer models maintain a large number of internal states, the vast majority of which are associated with self-attention layers. With limited memory bandwidth, reading these from memory at each inference step can slow down inference. In…

With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands.…