Related papers: CVA6-VMRT: A Modular Approach Towards Time-Predict…

Confidential computing safeguards sensitive computations from untrusted clouds, with Confidential Virtual Machines (CVMs) providing a secure environment for guest OS. However, CVMs often come with large and vulnerable operating system…

In this work, we present the design and evaluation of a Processor Tracing System compliant with the RISC-V Efficient Trace specification for Instruction Branch Tracing. We integrate our system into the host domain of a state-of-the-art edge…

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Cloud virtualization technology, ingrained with physical resource sharing, prompts cybersecurity threats on users' virtual machines (VM)s due to the presence of inevitable vulnerabilities on the offsite servers. Contrary to the existing…

Extreme edge devices or Internet-of-thing nodes require both ultra-low power always-on processing as well as the ability to do on-demand sampling and processing. Moreover, support for IoT applications like voice recognition, machine…

Persistent Memory (PM) makes possible recoverable applications that can preserve application progress across system reboots and power failures. Actual recoverability requires careful ordering of cacheline flushes, currently done in two…

With the imminent slowing down of DRAM scaling, Phase Change Memory (PCM) is emerging as a lead alternative for main memory technology. While PCM achieves low energy due to various technology-specific advantages, PCM is significantly slower…

The efficiency of Quantum Characterisation, Verification, and Validation (QCVV) protocols highly hinges on the agreement between the assumed noise model and the underlying error mechanisms. As a matter of fact, errors in Quantum Processing…

Non-volatile memory (NVM) is a class of promising scalable memory technologies that can potentially offer higher capacity than DRAM at the same cost point. Unfortunately, the access latency and energy of NVM is often higher than those of…

Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from…

Memory tiering is the norm to effectively tackle the increasing server memory total cost of ownership (TCO) and the growing data demands of modern data center workloads. However, the host-based state-of-the-art memory tiering solutions can…

In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been widely used for natural language processing, time series…

Microarchitectural timing channels enable unwanted information flow across security boundaries, violating fundamental security assumptions. They leverage timing variations of several state-holding microarchitectural components and have been…

Parameter-Efficient Fine-Tuning (PEFT) has emerged to mitigate the computational demands of large-scale models. Within computer vision, adapter-based PEFT methods are often favored over prompt-based approaches like Visual Prompt Tuning…

Memory disaggregation via CXL enables multi-host resource sharing. However, existing CXL sharing mechanisms enforce coarse-grained, host-level permissions only, leaving isolation to the operating system. Today, virtual memory enables…

Neuromorphic hardware platforms can significantly lower the energy overhead of a machine learning inference task. We present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-…

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.…

Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and convolutions, modern decoder-based transformers interleave attention, normalization, and…

Computation intensive kernels, such as convolutions, matrix multiplication and Fourier transform, are fundamental to edge-computing AI, signal processing and cryptographic applications. Interleaved-Multi-Threading (IMT) processor cores are…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…