Related papers: DISC: A Dynamic Shape Compiler for Machine Learnin…
Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such as CPUs and GPUs. They organize computation around…
Despite the rapidly evolving field of computational electromagnetics, few open-source tools have managed to tackle the problem of automatic mesh generation for properly discretizing the problem of interest into a finite set of elements…
While polyhedral compilers have shown success in implementing advanced code transformations, they still face challenges in selecting the ones that lead to the most profitable speedups. This has motivated the use of machine learning based…
Performance optimization is the art of continuous seeking a harmonious mapping between the application domain and hardware. Recent years have witnessed a surge of deep learning (DL) applications in industry. Conventional wisdom for…
Emerging technologies present opportunities for system designers to meet the challenges presented by competing trends of big data analytics and limitations on CMOS scaling. Specifically, memristors are an emerging high-density technology…
Digital computing-in-memory (DCIM) has been a popular solution for addressing the memory wall problem in recent years. However, the DCIM design still heavily relies on manual efforts, and the optimization of DCIM is often based on human…
While GPUs dominate massively parallel computing through the single-instruction, multiple-thread (SIMT) programming model, their underlying single-instruction, multiple-data (SIMD) execution incurs substantial energy overhead from frequent…
Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it minimizes data movement and provides large computational parallelism. Similar to machine learning accelerators, application mapping, which determines the…
We present a prototypical linear algebra compiler that automatically exploits domain-specific knowledge to generate high-performance algorithms. The input to the compiler is a target equation together with knowledge of both the structure of…
We propose a language and compiler to productively build high-performance {\it software systolic arrays} that run on GPUs. Based on a rigorous mathematical foundation (uniform recurrence equations and space-time transform), our language has…
Emerging multi-model workloads with heavy models like recent large language models significantly increased the compute and memory demands on hardware. To address such increasing demands, designing a scalable hardware architecture became a…
The growing volume of scientific simulation data presents a significant challenge for storage and transfer. Error-bounded lossy compression has emerged as a critical solution for mitigating these challenges, providing a means to reduce data…
One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate…
Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes, which discretize the space into a regular 3D grid (or…
Indexing is an effective way to support efficient query processing in large databases. Recently the concept of learned index, which replaces or complements traditional index structures with machine learning models, has been actively…
Irregular embedding lookups are a critical bottleneck in recommender models, sparse large language models, and graph learning models. In this paper, we first demonstrate that, by offloading these lookups to specialized access units,…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval but faces challenges on edge devices due to high storage, energy, and latency demands. Computing-in-Memory (CIM) offers a…
Recent deep learning workloads increasingly push computational demand beyond what current memory systems can sustain, with many kernels stalling on data movement rather than computation. While modern dataflow accelerators incorporate…
Simulation-driven shape optimisation (SDSO) of marine propellers is often obstructed by high-dimensional design spaces stemming from its complex geometry and baseline parameterisation, which leads to the notorious curse of dimensionality.…
Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications. Recently, there has been a surge in data-driven methods to complement traditional numerical simulations…