Related papers: TPU-MLIR: A Compiler For TPU Using MLIR

Recently, multimodal large language models (MLLMs) have attracted increasing research attention due to their powerful visual understanding capabilities. While they have achieved impressive results on various vision tasks, their performance…

The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this…

This work studies the problem of high-dimensional data (referred to as tensors) completion from partially observed samplings. We consider that a tensor is a superposition of multiple low-rank components. In particular, each component can be…

Code understanding and generation have fast become some of the most popular applications of language models (LMs). Nonetheless, research on multilingual aspects of Code-LMs (i.e., LMs for code generation) such as cross-lingual transfer…

Efficiently exploiting GPUs is increasingly essential in scientific computing, as many current and upcoming supercomputers are built using them. To facilitate this, there are a number of programming approaches, such as CUDA, OpenACC and…

Modern out-of-order processors have increased capacity to exploit instruction level parallelism (ILP) and memory level parallelism (MLP), e.g., by using wide superscalar pipelines and vector execution units, as well as deep buffers for…

Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low…

Llama$.$lisp is a compiler framework intended to target offload processor backends such as GPUs, using intermediate representation languages (IRs) that are device-agnostic. The Llama$.$lisp IRs are formulated as S-expressions. This makes…

Transformer-based large language models (LLMs) have demonstrated surprisingly robust performance across a wide range of language-related tasks, including programming language understanding and generation. In this paper, we take the first…

As the usage of deep learning becomes increasingly popular in mobile and embedded solutions, it is necessary to convert the framework-specific network representations into executable code for these embedded platforms. This paper consists of…

Deep Neural Networks (DNNs) have revolutionized many aspects of our lives. The use of DNNs is becoming ubiquitous including in softwares for image recognition, speech recognition, speech synthesis, language translation, to name a few. he…

Large Language Models (LLMs) built on transformer architectures have transformed natural language processing, achieving remarkable performance across diverse applications. While distributed inference frameworks enable practical deployment…

Discrete Fourier Transform (DFT) libraries are one of the most critical software components for scientific computing. Inspired by FFTW, a widely used library for DFT HPC calculations, we apply compiler technologies for the development of…

Various processing-in-memory (PIM) accelerators based on various devices, micro-architectures, and interfaces have been proposed to accelerate deep neural networks (DNNs). How to deploy DNNs onto PIM-based accelerators is the key to explore…

The efficacy of deep learning has resulted in its use in a growing number of applications. The Volta graphics processor unit (GPU) architecture from NVIDIA introduced a specialized functional unit, the "tensor core", that helps meet the…

While Model Based Iterative Reconstruction (MBIR) of CT scans has been shown to have better image quality than Filtered Back Projection (FBP), its use has been limited by its high computational cost. More recently, deep convolutional neural…

The Cerebras Wafer-Scale Engine (WSE) delivers performance at an unprecedented scale of over 900,000 compute units, all connected via a single-wafer on-chip interconnect. Initially designed for AI, the WSE architecture is also well-suited…

Calculating the most efficient schedule of work in a neural network compiler is a difficult task. There are many parameters to be accounted for that can positively or adversely affect that schedule depending on their configuration - How…

Intermediate Representations (IRs) are central to optimizing compilers as the way the program is represented may enhance or limit analyses and transformations. Suitable IRs focus on exposing the most relevant information and establish…

This paper presents a meta-compilation framework, the MCompiler. The main idea is that different segments of a program can be compiled with different compilers/optimizers and combined into a single executable. The MCompiler can be used in a…