Related papers: Domain-Specific Multi-Level IR Rewriting for GPU

Growing heterogeneity and configurability in HPC architectures has made auto-tuning applications and runtime parameters on these systems very complex. Users are presented with a multitude of options to configure parameters. In addition to…

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we…

Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

Due to the growing complexity of modern Integrated Circuits (ICs), there is a need for automated circuit design methods. Recent years have seen rising research in hardware design language generation to facilitate the design process. In this…

Modern compilers optimize programs through a sequence of modular passes over intermediate representations (IR). While this pass-by-pass paradigm offers engineering benefits, it suffers from a pass coordination problem: locally beneficial…

Field programmable gate arrays (FPGAs) can accelerate image processing by exploiting fine-grained parallelism opportunities in image operations. FPGA language designs are often subsets or extensions of existing languages, though these…

Region-based compilation repartitions a program into more desirable compilation units using profiling information and procedure inlining to enable region formation analysis. Heuristics play a key role in determining when it is most…

Recent trends in language modeling have focused on increasing performance through scaling, and have resulted in an environment where training language models is out of reach for most researchers and practitioners. While most in the…

Optimizing GPU kernels for high performance is a complex task, often demanding deep architectural knowledge, extensive profiling, and iterative experimentation. This challenge is amplified when targeting newer or less-documented GPU…

Inference algorithms in probabilistic programming languages (PPLs) can be thought of as interpreters, since an inference algorithm traverses a model given evidence to answer a query. As with interpreters, we can improve the efficiency of…

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…

Binary (0-1) integer programming (BIP) is pivotal in scientific domains requiring discrete decision-making. As the advance of AI computing, recent works explore neural network-based solvers for integer linear programming (ILP) problems.…

Domain-specific languages raise the level of abstraction in software development. While it is evident that programmers can more easily reason about very high-level programs, the same holds for compilers only if the compiler has an accurate…

The main focus of this work is a novel framework for the joint reconstruction and segmentation of parallel MRI (PMRI) brain data. We introduce an image domain deep network for calibrationless recovery of undersampled PMRI data. The proposed…

Domain-specific optimizing compilers have demonstrated significant performance and portability benefits, but require programs to be represented in their specialized IRs. Existing frontends to these compilers suffer from the "language subset…

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers…

GPU compilers merge all data types into a single unified register file, erasing the type information that binary-analysis tools rely on. We show that type recovery from this untyped register file is the central challenge of GPU binary…

Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive.…

Providing access to information across languages has been a goal of Information Retrieval (IR) for decades. While progress has been made on Cross Language IR (CLIR) where queries are expressed in one language and documents in another, the…