Related papers: Unleashing the Hidden Power of Compiler Optimizati…

Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We…

We have developed several autotuning benchmarks in CUDA that take into account performance-relevant source-code parameters and reach near peak-performance on various GPU architectures. We have used them during the development and evaluation…

The design of binary error-correcting codes is a challenging optimization problem with several applications in telecommunications and storage, which has also been addressed with metaheuristic techniques and evolutionary algorithms. Still,…

Test optimization contains test case selection and minimization, which is an important challenge in software testing and has been addressed with search-based approaches intensively in the past. Inspired by the recent advancement of using…

Compiler optimizations are designed to improve run-time performance while preserving input-output behavior. Correctness in this sense does not necessarily preserve security: it is known that standard optimizations may break or weaken…

Effective communication is essential in distributed training, with predictability being one of its most significant characteristics. However, existing studies primarily focus on exploiting predictability through online profiling for runtime…

Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and, more critically, inconsistent with their diffs-known as message-code inconsistency (MCI). MCIs mislead…

When a software transformation or software security task needs to analyze a given program binary, the first step is often disassembly. Since many modern disassemblers have become highly accurate on many binaries, we believe reliable…

Binary analysis is an important capability required for many security and software engineering applications. Consequently, there are many binary analysis techniques and tools with varied capabilities. However, testing these tools requires a…

We present Code Comparison Tuning (CCT), a simple and effective tuning method for code large language models (Code LLMs) to better handle subtle code errors. Specifically, we integrate the concept of comparison into instruction tuning, both…

Automatic identification of the differences between two versions of a file is a common and basic task in several applications of mining code repositories. Git, a version control system, has a diff utility and users can select algorithms of…

Early modular fault tolerant quantum computers remain constrained by costly inter-module communication and limited magic state factory service. Understanding such bottlenecks and investigating compiler optimizations most close the gap…

Compilers are fundamental to modern software development, making the effective identification and resolution of compiler faults essential. However, localizing these faults to specific source files remains highly challenging due to the…

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale…

Compilers play a foundational role in building reliable software systems, and bugs within them can lead to catastrophic consequences. The compilation process typically involves hundreds of files, making traditional automated bug isolation…

CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for…

We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with no syntax errors).…

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…