Related papers: Eliminate Branches by Melding IR Instructions

IoT Edge intelligence requires Convolutional Neural Network (CNN) inference to take place in the edge devices itself. ARM big.LITTLE architecture is at the heart of prevalent commercial edge devices. It comprises of single-ISA heterogeneous…

The rise of machine learning methods on heavily resource constrained devices requires not only the choice of a suitable model architecture for the target platform, but also the optimization of the chosen model with regard to execution time…

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

A typical compiler flow relies on a uni-directional sequence of translation/optimization steps that lower the program abstract representation, making it hard to preserve higher-level program information across each transformation step. On…

Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent…

The ability to execute code is a prerequisite for various dynamic program analyses. Learning-guided execution has been proposed as an approach to enable the execution of arbitrary code snippets by letting a neural model predict likely…

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of large foundation models in novel scenarios with limited training data. In the computer vision community, PEFT has shown effectiveness in image…

Real-world graph applications are generally larger than the size of the cache itself. Due to this reason, the memory hierarchy was identified as a key bottleneck by the earlier works. Undoubtedly, the performance can be achieved by…

In dynamic Windows malware detection, deep learning models are extensively deployed to analyze API sequences. Methods based on API sequences play a crucial role in malware prevention. However, due to the continuous updates of APIs and the…

Information about the memory locations accessed by a program is, for instance, required for program parallelisation and program verification. Existing inference techniques for this information provide only partial solutions for the…

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the…

As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current data management strategies face substantial challenges in…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…

Modern processors increasingly rely on SIMD instruction sets, such as AVX and RVV, to significantly enhance parallelism and computational performance. However, production-ready compilers like LLVM and GCC often fail to fully exploit…

Modern OOO CPUs have very deep pipelines with large branch misprediction recovery penalties. Speculatively executed instructions on the wrong path can significantly change cache state, depending on speculation levels. Architects often…

Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…

We introduce preti, a novel framework for predicting software execution time during the early stages of development. preti leverages an LLVM-based simulation environment to extract timing-related runtime information, such as the count of…

Modern AI inference systems treat transformer execution as mandatory, conflating model capability with execution necessity. We reframe inference as a control-plane decision problem: determining when execution is necessary versus when…