Related papers: BPF for storage: an exokernel-inspired approach
This paper introduces a parallel directional fast multipole method (FMM) for solving N-body problems with highly oscillatory kernels, with a focus on the Helmholtz kernel in three dimensions. This class of oscillatory kernels requires a…
Binarized Neural Networks (BNNs) significantly reduce the computation and memory demands with binarized weights and activations compared to full-precision NNs. Executing a layer in a BNN on different devices of a heterogeneous…
Modern parallel filesystems such as Lustre are designed to provide high, scalable I/O bandwidth in response to growing I/O requirements; however, the bursty I/O characteristics of many data-intensive scientific applications make it…
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…
Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated…
Simultaneously supporting latency- and throughout-sensitive workloads in a shared environment is an increasingly more common challenge in big data clusters. Despite many advances, existing cluster schedulers force the same performance goal…
Modern high-performance computing (HPC) applications run on compute resources but share global storage systems. This design can cause problems when applications consume a disproportionate amount of storage bandwidth relative to their…
The substantial computational and memory demands of Large Language Models (LLMs) hinder their deployment. Block Floating Point (BFP) has proven effective in accelerating linear operations, a cornerstone of LLM workloads. However, as…
Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…
Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly…
Compartmentalization effectively prevents initial corruption from turning into a successful attack. This paper presents O2C, a pioneering system designed to enforce OS kernel compartmentalization on the fly. It not only provides immediate…
With the tremendous advances in processor and memory technology, I/O has risen to become the bottleneck in high-performance computing for many applications. The development of parallel file systems has helped to ease the performance gap,…
Extended Berkeley Packet Filter (eBPF) allows developers to extend Linux kernel functionality without modifying its source code. To ensure system safety, an in-kernel safety checker, the verifier, enforces strict safety constraints (for…
PIM architectures aim to reduce data transfer costs between processors and memory by integrating processing units within memory layers. Prior PIM architectures have shown potential to improve energy efficiency and performance. However, such…
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…
System calls have no place on the fast path of microsecond-scale systems. However, kernel bypass prevents the OS from controlling and supervising access to the hardware. In this paper we introduce the fastcall space, a new layer in the…
Datacenters are witnessing a rapid surge in the adoption of serverless functions for microservices-based applications. A vast majority of these microservices typically span less than a second, have strict SLO requirements, and are chained…
Fast Multipole Methods (FMMs) based on the oscillatory Helmholtz kernel can reduce the cost of solving N-body problems arising from Boundary Integral Equations (BIEs) in acoustic or electromagnetics. However, their cost strongly increases…
Convolutional Neural Networks (CNNs) have demonstrated their effectiveness in numerous vision tasks. However, their high processing requirements necessitate efficient hardware acceleration to meet the application's performance targets. In…
Modern enterprise servers are increasingly embracing tiered memory systems with a combination of low latency DRAMs and large capacity but high latency non-volatile main memories (NVMMs) such as Intel's Optane DC PMM. Prior works have…