Related papers: DISC: A Dynamic Shape Compiler for Machine Learnin…
As customized accelerator design has become increasingly popular to keep up with the demand for high performance computing, it poses challenges for modern simulator design to adapt to such a large variety of accelerators. Existing…
Digital Compute-in-Memory (CIM) architectures have shown great promise in Deep Neural Network (DNN) acceleration by effectively addressing the "memory wall" bottleneck. However, the development and optimization of digital CIM accelerators…
This paper discusses our proposal and implementation of Distill, a domain-specific compilation tool based on LLVM to accelerate cognitive models. Cognitive models explain the process of cognitive function and offer a path to human-like…
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…
High-quality training data are not always available in dynamic MRI. To address this, we propose a self-supervised deep learning method called deep image prior with structured sparsity (DISCUS) for reconstructing dynamic images. DISCUS is…
Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells…
In this paper we present DYNAMIC, an open-source C++ library implementing dynamic compressed data structures for string manipulation. Our framework includes useful tools such as searchable partial sums, succinct/gap-encoded bitvectors, and…
SRAM-based compute-in-memory (CIM) offers high computational density and energy efficiency for deep neural network (DNN) accelerators, but its limited capacity causes on/off-chip data movement overhead for large DNN models. Existing CIM…
With the rapid development of deep learning models and hardware support for dense computing, the deep learning workload characteristics changed significantly from a few hot spots on compute-intensive operations to a broad range of…
Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…
Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such workflows, i.e., selecting configurations for each sub-agent…
FPGAs are well-suited for dataflow architectures that process data in a streaming or pipelined manner, thus satisfying the high computational and communication demands of emerging applications. However, manually implementing an efficient…
Runtime-reconfigurable software coupled with reconfigurable hardware is highly desirable as a means towards maximizing runtime efficiency without compromising programmability. Compilers for such software systems are extremely difficult to…
We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models. For this problem, current…
Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…
We introduce DISTAL, a compiler for dense tensor algebra that targets modern distributed and heterogeneous systems. DISTAL lets users independently describe how tensors and computation map onto target machines through separate format and…
High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory…
The enhanced efficiency of hardware accelerators, including Single Instruction Multiple Data (SIMD) architectures and Coarse-Grained Reconfigurable Architectures (CGRAs), is driving significant advancements in Artificial Intelligence and…
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…
New information technologies provide a lot of prospects for performance improvement. One of them is "Dynamic Source Code Generation and Compilation". This article shows how this way provides high performance for engineering problems.