Related papers: DFabric: Scaling Out Data Parallel Applications wi…
A new scalable parallel math library, dMath, is presented in this paper that demonstrates leading scaling when using intranode, or internode, hybrid-parallelism for deep-learning. dMath provides easy-to-use distributed base primitives and a…
The ever-growing demands for memory with larger capacity and higher bandwidth have driven recent innovations on memory expansion and disaggregation technologies based on Compute eXpress Link (CXL). Especially, CXL-based memory expansion…
Recent Serverless workloads tend to be largescaled/CPU-memory intensive, such as DL, graph applications, that require dynamic memory-to-compute resources provisioning. Meanwhile, recent solutions seek to design page management strategies…
The ongoing shift of cloud services from monolithic designs to microservices creates high demand for efficient and high performance datacenter networking stacks, optimized for fine-grained workloads. Commodity networking systems based on…
Limited memory bandwidth is a critical bottleneck in modern systems. 3D-stacked DRAM enables higher bandwidth by leveraging wider Through-Silicon-Via (TSV) channels, but today's systems cannot fully exploit them due to the limited internal…
In the landscape of High-Performance Computing (HPC), the quest for efficient and scalable memory solutions remains paramount. The advent of Compute Express Link (CXL) introduces a promising avenue with its potential to function as a…
Because of the recent trends in Deep Neural Networks (DNN) models being memory-bound, inter-operator pipelining for DNN accelerators is emerging as a promising optimization. Inter-operator pipelining reduces costly on-chip global memory and…
As AI models outpace the capabilities of single processors, interconnects across chips have become a critical enabler for scalable computing. These processors exchange massive amounts of data at cache-line granularity, prompting the…
The rapid advancement of embedded multicore and many-core systems has revolutionized computing, enabling the development of high-performance, energy-efficient solutions for a wide range of applications. As models scale up in size, data…
A noise-tolerant data communications fabric has been developed to meet the real-time data acquisition and control requirements of fast feedback loops, machine protection systems, pulse-to-pulse sequencing, and machine-experiment…
As emerging deep neural network (DNN) models continue to grow in size, using large GPU clusters to train DNNs is becoming an essential requirement to achieving acceptable training times. In this paper, we consider the case where future…
In the last decade, specific-purpose computing and storage devices, such as GPUs, TPUs, or high-speed storage, have been incorporated into server nodes of Supercomputers and Data centers. The development of high-bandwidth memory (HBM)…
The rapid growth of blockchain systems leads to increasing interest in understanding and comparing blockchain performance at scale. In this paper, we focus on analyzing the performance of Hyperledger Fabric v1.1 - one of the most popular…
Memory disaggregation has attracted great attention recently because of its benefits in efficient memory utilization and ease of management. So far, memory disaggregation research has all taken one of two approaches: building/emulating…
Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…
The increasing demand for on-device intelligence in Edge AI and TinyML applications requires the efficient execution of modern Convolutional Neural Networks (CNNs). While lightweight architectures like MobileNetV2 employ Depthwise Separable…
CXL has been the emerging technology for expanding memory for both the host CPU and device accelerators with load/store interface. Extending memory coherency to the PCIe root complex makes the codesign more flexible in that you can access…
It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…
With the increasing adoption of private blockchain platforms, consortia operating in various sectors such as trade, finance, logistics, etc., are becoming common. Despite having the benefits of a completely decentralized architecture which…
Large-scale AI training and inference require hundreds of gigabytes to terabytes of DRAM with high peak to average utilization ratios, resulting in overprovisioning. In cloud computing, DRAM constitutes a significant share of the cost. Yet,…