Related papers: A System Level Compiler for Massively-Parallel, Sp…

We present the design and implementation of a macro-embedding of a family of compiler intermediate languages, from a Scheme-like language to x86-64, into Racket. This embedding is used as part of a testing framework for a compilers course…

Many recent machine learning models show dynamic shape characteristics. However, existing AI compiler optimization systems suffer a lot from problems brought by dynamic shape models, including compilation overhead, memory usage,…

We propose the Sparse Abstract Machine (SAM), an abstract machine model for targeting sparse tensor algebra to reconfigurable and fixed-function spatial dataflow accelerators. SAM defines a streaming dataflow abstraction with sparse…

Massive MIMO is a cornerstone of next-generation wireless communication, offering significant gains in capacity, reliability, and energy efficiency. However, to meet emerging demands such as high-frequency operation, wide bandwidths,…

Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where…

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…

As part of the EU-funded Center of Excellence SPACE (Scalable Parallel Astrophysical Codes for Exascale), seven commonly used astrophysics simulation codes are being optimized to exploit exascale computing platforms. Exascale cosmological…

We present XgenSilicon ML Compiler, a fully automated end-to-end compilation framework that transforms high-level machine learning models into optimized RISC-V assembly code for custom ASIC accelerators. By unifying the system's cost model…

Tensors naturally model many real world processes which generate multi-aspect data. Such processes appear in many different research disciplines, e.g, chemometrics, computer vision, psychometrics and neuroimaging analysis. Tensor…

Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited precision of network signals and parameters, constrained…

General-purpose processor vendors have integrated customized accelerator in their products due to the widespread use of General Matrix-Matrix Multiplication (GEMM) kernels. However, it remains a challenge to further improve the…

Typical schedulers in multi-tenancy environments make use of reactive, feedback-oriented mechanisms based on performance counters to avoid resource contention but suffer from detection lag and loss of performance. In this paper, we address…

In this work, we present a new approach to high level synthesis (HLS), where high level functions are first mapped to an architectural template, before hardware synthesis is performed. As FPGA platforms are especially suitable for…

This study presents a novel computer architecture where a last level cache and a SIMD accelerator are replaced by an Associative Processor. Associative Processor combines data storage and data processing and provides parallel computational…

We present a software framework called CARAVAN, which was developed for comprehensive simulations on massive parallel computers. The framework runs user-developed simulators with various input parameters in parallel without requiring the…

State-of-the-art sequential reasoning in Large Language Models (LLMs) has expanded the capabilities of Copilots beyond conversational tasks to complex function calling, managing thousands of API calls. However, the tendency of compositional…

This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heterogeneous hardware, significantly reduce the cost of building…

A novel language system has given rise to promising alternatives to standard formal and processor network models of computation. An interstring linked with a abstract machine environment, shares sub-expressions, transfers data, and…

The growing adoption of domain-specific architectures in edge computing platforms for deep learning has highlighted the efficiency of hardware accelerators. However, integrating custom accelerators into modern machine learning (ML)…

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software…