Related papers: Minotaur: A SIMD-Oriented Synthesizing Superoptimi…

If we can automatically derive compiler optimizations, we might be able to sidestep some of the substantial engineering challenges involved in creating and maintaining a high-quality compiler. We developed Souper, a synthesizing…

Code optimization remains a core objective in software development, yet modern compilers struggle to navigate the enormous optimization spaces. While recent research has looked into employing large language models (LLMs) to optimize source…

Creating high performance implementations of deep learning primitives on CPUs is a challenging task. Multiple considerations including multi-level cache hierarchy, and wide SIMD units of CPU platforms influence the choice of program…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly…

Many hardware vendors have introduced specialized deep neural networks (DNN) accelerators owing to their superior performance and efficiency. As such, how to generate and optimize the code for the hardware accelerator becomes an important…

Automated code optimization aims to improve performance in programs by refactoring code, and recent studies focus on utilizing LLMs for the optimization. Typical existing approaches mine optimization commits from open-source codebases to…

Numerical software is usually shipped with built-in hyperparameters. By carefully tuning those hyperparameters, significant performance enhancements can be achieved for specific applications. We developed MindOpt Tuner, a new automatic…

Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional…

Existing iterative compilation and machine-learning-based optimization techniques have been proven very successful in achieving better optimizations than the standard optimization levels of a compiler. However, they were not engineered to…

We introduce Mirage, the first multi-level superoptimizer for tensor programs. A key idea in Mirage is $\mu$Graphs, a uniform representation of tensor programs at the kernel, thread block, and thread levels of the GPU compute hierarchy.…

This paper presents the interesting observation that by performing fewer of the optimizations available in a standard compiler optimization level such as -O2, while preserving their original ordering, significant savings can be achieved in…

Object-oriented programming (OOP) has long been regarded as too inefficient for SIMD high-performance computing, despite the fact that many important HPC applications have an inherent object structure. We discovered a broad subset of OOP…

Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize…

Object-oriented programming has long been regarded as too inefficient for SIMD high-performance computing, despite the fact that many important HPC applications have an inherent object structure. On SIMD accelerators, including GPUs, this…

We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization. Nautilus compiles a high-level algebraic specification of tensor operators into efficient tiled GPU kernels. Nautilus's successive…

Hardware accelerators, especially those designed for tensor processing, have become ubiquitous in today's computing landscape. However, even with significant efforts in building compilers, programming these tensor accelerators remains…

Software optimization refines programs for resource efficiency while preserving functionality. Traditionally, it is a process done by developers and compilers. This paper introduces a third option, automated optimization at the source code…

Computing-in-memory (CIM) architectures demonstrate superior performance over traditional architectures. To unleash the potential of CIM accelerators, many compilation methods have been proposed, focusing on application scheduling…

This paper proposes a novel set of trigonometric implementations which are 5x faster than the inbuilt C++ functions. The proposed implementation is also highly memory efficient requiring no precomputations of any kind. Benchmark comparisons…