相关论文: A Performance Vocabulary for Affine Loop Transform…

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

The unknown parameters of simulation models often need to be calibrated using observed data. When simulation models are expensive, calibration is usually carried out with an emulator. The effectiveness of the calibration process can be…

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…

Recently, code-oriented large language models (LLMs) have demonstrated strong capabilities in translating natural language into executable code. Text-to-SQL is a significant application of this ability, enabling non-technical users to…

Automated code generation and performance enhancements for sparse tensor algebra have become essential in many real-world applications, such as quantum computing, physical simulations, computational chemistry, and machine learning. General…

Polly is the LLVM project's polyhedral loop nest optimizer. Recently, user-directed loop transformation pragmas were proposed based on LLVM/Clang and Polly. The search space exposed by the transformation pragmas is a tree, wherein each node…

Customized accelerators have revolutionized modern computing by delivering substantial gains in energy efficiency and performance through hardware specialization. Field-Programmable Gate Arrays (FPGAs) play a crucial role in this paradigm,…

Code-mixing, the practice of switching between languages within a conversation, poses unique challenges for traditional NLP. Existing benchmarks are limited by their narrow language pairs and tasks, failing to adequately assess large…

Writing efficient hybrid parallel code is tedious, error-prone, and requires good knowledge of both parallel programming and multithreading such as MPI and OpenMP, resp. Therefore, we present a framework which is based on a job model that…

The rapidly evolving landscape of AI and machine learning workloads has widened the gap between high-level domain operations and efficient hardware utilization. Achieving near-peak performance still demands deep hardware expertise-experts…

Accurate determination of the performance of parallel GPU code typically requires execution-time profiling on target hardware -- an increasingly prohibitive step due to limited access to high-end GPUs. This paper explores whether Large…

Recent leaps in large language models (LLMs) caused a revolution in programming tools (like GitHub Copilot) that can help with code generation, debugging, and even performance optimization. In this paper, we focus on the capabilities of the…

Programmable Logic Devices (PLDs) continue to grow in size and currently contain several millions of gates. At the same time, research effort is going into higher-level hardware synthesis methodologies for reconfigurable computing that can…

Many shared-memory parallel irregular applications, such as sparse linear algebra and graph algorithms, depend on efficient loop scheduling (LS) in a fork-join manner despite that the work per loop iteration can greatly vary depending on…

Coordinating heterogeneous robot teams from free-form natural-language instructions is hard. Language-only planners struggle with long-horizon coordination and hallucination, while purely formal methods require closed-world models. We…

Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this challenge, Reparameterized Orthogonal Equivalence Training (POET), a spectrum-preserving framework…

Although recent scaling up approaches to training deep neural networks have proven to be effective, the computational intensity of large and complex models, as well as the availability of large-scale datasets, require deep learning…

Our goal is to study the feasibility of porting termination analysis techniques developed for one programming paradigm to another paradigm. In this paper, we show how to adapt termination analysis techniques based on polynomial…

Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such…

Optimizing GPU kernels manually is a challenging and time-consuming task. With the rapid development of LLMs, automated GPU kernel optimization is gradually becoming a tangible reality. However, current LLM-driven automated optimization…