Related papers: FlexiNS: A SmartNIC-Centric, Line-Rate and Flexibl…
GPUs are the heart of the latest generations of supercomputers. We efficiently accelerate a compressible multiphase flow solver via OpenACC on NVIDIA and AMD Instinct GPUs. Optimization is accomplished by specifying the directive clauses…
Increasing data center network speed coupled with application requirements for high throughput and low latencies have raised the efficiency bar for network stacks. To reduce substantial kernel overhead in network processing, recent…
Data-intensive applications in data centers, especially machine learning (ML), have made the network a bottleneck, which in turn has motivated the development of more efficient network protocols and infrastructure. For instance, remote…
A surge in artificial intelligence and autonomous technologies have increased the demand toward enhanced edge-processing capabilities. Computational complexity and size of state-of-the-art Deep Neural Networks (DNNs) are rising…
Deploying deep neural networks (DNNs) on resource-constrained IoT devices remains a challenging problem, often requiring hardware modifications tailored to individual AI models. Existing accelerator-generation tools, such as AMD's FINN, do…
We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…
The rapid scaling of Large Language Models (LLMs) has achieved remarkable performance, but it also leads to prohibitive memory costs. Existing parameter-efficient approaches such as pruning and quantization mainly compress pretrained models…
Software Defined Networking (SDN) promises greater flexibility for directing packet flows, and Network Function Virtualization promises to enable dynamic management of software-based network functions. However, the current divide between an…
Efficient virtualization of CPU and memory is standardized and mature. Capabilities such as Intel VT-x [3] have been added by manufacturers for efficient hypervisor support. In contrast, virtualization of a block device and its presentation…
FPGAs have shown great potential in providing low-latency and energy-efficient solutions for deep neural network (DNN) inference applications. Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division…
Data center networks leverage multiple parallel paths connecting end host pairs to offer high bisection bandwidth for cluster computing applications. However, state of the art distributed multi-pathing protocols such as Equal Cost Multipath…
Modern data-driven applications expose limitations of von Neumann architectures - extensive data movement, low throughput, and poor energy efficiency. Accelerators improve performance but lack flexibility and require data transfers.…
Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature…
Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute-efficiencies. However, the intrinsic non-idealities associated with the…
Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) are promising solutions to enable $\mu$s-level inference latency and ultra-low energy in edge vision applications. Yet, their current lack of flexibility at both the…
DotGrid platform is a Grid infrastructure integrated with a set of open and standard protocols recently implemented on the top of Microsoft .NET in Windows and MONO .NET in UNIX/Linux. DotGrid infrastructure along with its proposed…
Today's datacenter applications rely on datastores that are required to provide high availability, consistency, and performance. To achieve high availability, these datastores replicate data across several nodes. Such replication is managed…
Convolutional neural networks (CNNs) have recently demonstrated superior quality for computational imaging applications. Therefore, they have great potential to revolutionize the image pipelines on cameras and displays. However, it is…
On-chip communication infrastructure is a central component of modern systems-on-chip (SoCs), and it continues to gain importance as the number of cores, the heterogeneity of components, and the on-chip and off-chip bandwidth continue to…
Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed…