Related papers: CHERI Performance Enhancement for a Bytecode Inter…

In real-world Tool-Integrated Reasoning (TIR) scenarios, where LLMs interleave reasoning with external tool calls, a major source of inefficiency is that the toolcalls create pauses between LLM requests and cause KV-Cache eviction, forcing…

Improving software performance is an important yet challenging part of the software development cycle. Today, the majority of performance inefficiencies are identified and patched by performance experts. Recent advancements in deep learning…

The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference, focusing on hardware-imposed bottlenecks in…

Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters have not been sufficiently analyzed to understand if PEFT…

This paper presents CERMET, an energy-efficient hardware architecture designed for hardware-constrained cryptosystems. CERMET employs a base cryptosystem in conjunction with network coding to provide both information-theoretic and…

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

Application performance of modern day processors is often limited by the memory subsystem rather than actual compute capabilities. Therefore, data throughput specifications play a key role in modeling application performance and determining…

MPI+threads is gaining prominence as an alternative to the traditional MPI everywhere model in order to better handle the disproportionate increase in the number of cores compared with other on-node resources. However, the communication…

In cryptographic engineering, extensive attention has been devoted to ameliorating the performance and security of the algorithms within. Nonetheless, in the state-of-the-art, the approaches for increasing the reliability of the efficient…

The \emph{Partial Cache-Coherence (PCC)} model maintains hardware cache coherence only within subsets of cores, enabling large-scale memory sharing with emerging memory interconnect technologies like Compute Express Link (CXL). However,…

Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and…

Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic…

This paper presents important performance improvements for interpreters, exemplified by speedups of up to 5.5$\times$ for CPython. Although the original version of this papers was rejected multiple times, the reported speedups have not been…

Parameter-efficient fine-tuning (PEFT) that was initially developed for exploiting pre-trained large language models has recently emerged as an effective approach to perform transfer learning on computer vision tasks. However, the…

Artificial Intelligence (AI) has the potential to fundamentally change the educational landscape. So far, much of the physics education research relating to AI has focused on lecture-based assessment and the ability of ChatGPT to answer…

There is a tension in dynamic language runtime design between speed and correctness: state-of-the-art JIT compilation, the result of enormous industrial investment and significant research, achieves heroic speedups at the cost of complexity…

This research introduces an innovative voice-assisted debugging plugin for Python that transforms silent runtime errors into actionable audible diagnostics. By implementing a global exception hook architecture with pyttsx3 text-to-speech…

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for adapting large language models (LLMs). In this work we challenge the wide-spread assumption that parameter efficiency equates memory efficiency and on-device adaptability.…

Branch mispredictions cause catastrophic performance penalties in modern processors, leading to performance loss. While hardware predictors and profile-guided techniques exist, data-dependent branches with irregular patterns remain…

The semantics and the recursive execution model of Prolog make it very natural to express language interpreters in form of AST (Abstract Syntax Tree) interpreters where the execution follows the tree representation of a program. An…