Related papers: The DMA Streaming Framework: Kernel-Level Buffer O…
To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a "preemptible"…
Ensuring the confidentiality and integrity of DNN accelerators is paramount across various scenarios spanning autonomous driving, healthcare, and finance. However, current security approaches typically require extensive hardware resources,…
Protected user-level libraries have been proposed as a way to allow mutually distrusting applications to safely share kernel-bypass services. In this paper, we identify and solve several previously unaddressed obstacles to realizing this…
For NVIDIA GPUs, CUDA is the primary interface through which applications orchestrate GPU execution, yet much of the logic that realizes CUDA operations resides in NVIDIA's closed-source userspace driver. As a result, the translation from…
The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm for scaling compute capabilities, memory latency and…
Embedded and Internet-of-Things (IoT) devices have seen an increase in adoption in many domains. The security of these devices is of great importance as they are often used to control critical infrastructure, medical devices, and vehicles.…
Popular deep learning frameworks require users to fine-tune their memory usage so that the training data of a deep neural network (DNN) fits within the GPU physical memory. Prior work tries to address this restriction by virtualizing the…
Cloud applications need network data encryption to isolate from other tenants and protect their data from potential eavesdroppers in the network infrastructure. This paper presents SMT, a protocol design for emerging datacenter transport…
Many reasons make NFV an attractive paradigm for IT security: lowers costs, agile operations and better isolation as well as fast security updates, improved incident responses and better level of automation. On the other side, the network…
Traditional data processing pipelines are typically static and handcrafted for specific tasks, limiting their adaptability to evolving requirements. While general-purpose agents and coding assistants can generate code for well-understood…
DIFT (Dynamic Information Flow Tracking) has been a hot topic for more than a decade. Unfortunately, existing hardware DIFT approaches have not been widely used neither by research community nor by hardware vendors. It is due to two major…
Data redundancy provides resilience in large-scale storage clusters, but imposes significant cost overhead. Substantial space-savings can be realized by tuning redundancy schemes to observed disk failure rates. However, prior design…
Recent model-based congestion control algorithms such as BBR use repeated measurements at the endpoint to build a model of the network connection and use it to achieve optimal throughput with low queuing delay. Conversely, applying this…
SU3\_Bench is a microbenchmark developed to explore performance portability across multiple programming models/methodologies using a simple, but nontrivial, mathematical kernel. This kernel has been derived from the MILC lattice quantum…
Cloud resource management has been a key factor for the cloud datacenters development. Many cloud datacenters have problems in understanding and implementing the techniques to manage, allocate and migrate the resources in their premises.…
This work presents a compositional approach for schedulability analysis of Distributed Integrated Modular Avionics (DIMA) systems that consist of spatially distributed ARINC-653 modules connected by a unified AFDX network. We model a DIMA…
High-performance clusters and datacenters pose increasingly demanding requirements on storage systems. If these systems do not operate at scale, applications are doomed to become I/O bound and waste compute cycles. To accelerate the data…
A general form of codebook design for code-domain non-orthogonal multiple access (CD-NOMA) can be considered equivalent to an autoencoder (AE)-based constellation design for multi-user multidimensional modulation (MU-MDM). Due to a…
Multicore systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterising this influence is complex, and understanding the effect of particular…
Data analytics systems commonly utilize in-memory query processing techniques to achieve better throughput and lower latency. Modern computers increasingly rely on Non-Uniform Memory Access (NUMA) architectures in order to achieve…