Related papers: Morphlux: Transforming Torus Fabrics for Efficient…

The rapid scaling of large language models (LLMs) has significantly increased GPU memory pressure, which is further aggravated by training optimization techniques such as virtual pipeline and recomputation that disrupt tensor lifespans and…

Legacy codes in computational science and engineering have been very successful in providing essential functionality to researchers. However, they are not capable of exploiting the massive parallelism provided by emerging heterogeneous…

Serverless computing has attracted a broad range of applications due to its ease of use and resource elasticity. However, developing serverless applications often poses a dilemma -- relying on general-purpose serverless platforms can fall…

As models become larger, ML accelerators are a scarce resource whose performance must be continually optimized to improve efficiency. Existing performance analysis tools are coarse grained, and fail to capture model performance at the…

We propose a dense tensor accelerator called VectorMesh, a scalable, memory-efficient architecture that can support a wide variety of DNN and computer vision workloads. Its building block is a tile execution unit~(TEU), which includes…

As supercomputers advance towards exascale capabilities, computational intensity increases significantly, and the volume of data requiring storage and transmission experiences exponential growth. Adaptive Mesh Refinement (AMR) has emerged…

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and…

Transformer neural networks (TNNs) are being applied across a widening range of application domains, including natural language processing (NLP), machine translation, and computer vision (CV). Their popularity is largely attributed to the…

FPGA-based hardware accelerators have received increasing attention mainly due to their ability to accelerate deep pipelined applications, thus resulting in higher computational performance and energy efficiency. Nevertheless, the amount of…

Machine learning (ML) computations commonly execute on expensive specialized hardware, such as GPUs and TPUs, which provide high FLOPs and performance-per-watt. For cost efficiency, it is essential to keep these accelerators highly…

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three…

Offloading compute-intensive kernels to hardware accelerators relies on the large degree of parallelism offered by these platforms. However, the effective bandwidth of the memory interface often causes a bottleneck, hindering the…

This paper proposes a new hardware accelerator for sparse convolutional neural networks (CNNs) by building a hardware unit to perform the Image to Column (IM2COL) transformation of the input feature map coupled with a systolic array-based…

In-memory computing hardware accelerators allow more than 10x improvements in peak efficiency and performance for matrix-vector multiplications (MVM) compared to conventional digital designs. For this, they have gained great interest for…

Modular extremely large-scale MIMO (XL-MIMO) architectures combined with wireless fronthaul provide a scalable alternative to monolithic arrays, but their performance is sensitive to hardware impairments and resource allocation strategies.…

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

The design of divertor targets and baffles for optimal heat and particle exhaust from magnetically confined fusion plasmas requires a combination of fast, low-fidelity models (such as EMC3-lite [1]) for scoping studies and high-fidelity…

Matrix factorization (MF) discovers latent features from observations, which has shown great promises in the fields of collaborative filtering, data compression, feature extraction, word embedding, etc. While many problem-specific…

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…