Related papers: High-Level Synthesis Case Study: Implementation of…

The CMS experiment has been designed with a 2-level trigger system: the Level 1 Trigger, implemented on custom-designed electronics, and the High Level Trigger (HLT), a streamlined version of the CMS offline reconstruction software running…

Recent advancements in large language models (LLMs) necessitate extensive computational resources, prompting the use of diverse hardware accelerators from multiple vendors. However, traditional distributed training frameworks struggle to…

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by…

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due to the quadratic computational complexity of attention in…

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…

Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred…

To satisfy increasing storage demands in both capacity and performance, industry has turned to multiple storage technologies, including Flash SSDs and SMR disks. These devices employ a translation layer that conceals the idiosyncrasies of…

High-level synthesis (HLS) accelerates hardware design by enabling the automatic translation of high-level descriptions into efficient hardware implementations. However, debugging HLS code is a challenging and labor-intensive task,…

Deep reinforcement learning (RL) is computationally demanding and requires processing of many data points. Synchronous methods enjoy training stability while having lower data throughput. In contrast, asynchronous methods achieve high…

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

Machine Learning (ML) will play significant role in success of the upcoming High-Luminosity LHC (HL-LHC) program at CERN. The unprecedented amount of data at the Exa-Byte scale to be collected by the CERN experiments in next decade will…

SystemVerilog Assertions (SVAs) are crucial for hardware verification. Recent studies leverage general-purpose LLMs to translate natural language properties to SVAs (NL2SVA), but they perform poorly due to limited data. We propose a data…

FPGAs have found their way into data centers as accelerator cards, making reconfigurable computing more accessible for high-performance applications. At the same time, new high-level synthesis compilers like Xilinx Vitis and runtime…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Large language models (LLMs) iteratively generate text token by token, with memory usage increasing with the length of generated token sequences. Since the request generation length is generally unpredictable, it is difficult to estimate…

The High Level Trigger (HLT) of the future ALICE heavy-ion experiment has to reduce its input data rate of up to 25 GB/s to at most 1.25 GB/s for output before the data is written to permanent storage. To cope with these data rates a large…

Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists. However, traditional logic synthesis methods are computationally intensive,…

Modern large language models (LLMs) place extraordinary pressure on memory and compute budgets, making principled compression indispensable for both deployment and continued training. We present Hierarchical Sparse Plus Low-Rank (HSS)…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Hyperledger Fabric (HLF) is a modular, permissioned blockchain widely adopted in enterprise settings. Enhancing its throughput and latency remains challenging, as optimization decisions made in one phase of the transaction lifecycle can…