Related papers: ConcurORAM: High-Throughput Stateless Parallel Mul…
Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS)…
The configurable building blocks of current FPGAs -- Logic blocks (LBs), Digital Signal Processing (DSP) slices, and Block RAMs (BRAMs) -- make them efficient hardware accelerators for the rapid-changing world of Deep Learning (DL).…
We present a framework for concurrency control and availability in multi-datacenter datastores. While we consider Google's Megastore as our motivating example, we define general abstractions for key components, making our solution…
In this paper, we present PARTIME, a software library written in Python and based on PyTorch, designed specifically to speed up neural networks whenever data is continuously streamed over time, for both learning and inference. Existing…
Transactional Memory (TM) is an approach aiming to simplify concurrent programming by automating synchronization while maintaining efficiency. TM usually employs the optimistic concurrency control approach, which relies on transactions…
We take an important step forward in making Oblivious RAM (O-RAM) practical. We propose an O-RAM construction achieving an amortized overhead of 20X-35X (for an O-RAM roughly 1 terabyte in size), about 63 times faster than the best existing…
In this paper, we propose the Stateless Permutation of Application Memory (SPAM), a software defense that enables fine-grained data permutation for C programs. The key benefits include resilience against attacks that directly exploit…
Multicore CPUs and large memories are increasingly becoming the norm in modern computer systems. However, current database management systems (DBMSs) are generally ineffective in exploiting the parallelism of such systems. In particular,…
Resistive memory (RM) based neuromorphic systems can emulate synaptic plasticity and thus support continual learning, but they generally lack biologically inspired mechanisms for active forgetting, which are critical for meeting modern data…
A new neural network architecture (PSCNN) is developed to improve performance and speed of such networks. The architecture has all the advantages of the previous models such as self-organization and possesses some other superior…
Quorum systems are useful tools for implementing consistent and available storage in the presence of failures. These systems usually comprise a static set of servers that provide a fault-tolerant read/write register accessed by a set of…
When multiple processor cores (CPUs) and a GPU integrated together on the same chip share the off-chip DRAM, requests from the GPU can heavily interfere with requests from the CPUs, leading to low system performance and starvation of cores.…
The massive amounts of machine-type user equipments (UEs) will be supported in the future fifth generation (5G) networks. However, the potential large random access (RA) delay calls for a new RA scheme and for a detailed assessment of its…
In the burgeoning realm of Internet of Things (IoT) applications on edge devices, data stream compression has become increasingly pertinent. The integration of added compression overhead and limited hardware resources on these devices calls…
We present a deterministic sorting algorithm, SPMS (Sample, Partition, and Merge Sort), that interleaves the partitioning of a sample sort with merging. Sequentially, it sorts $n$ elements in $O(n \log n)$ time cache-obliviously with an…
Quantum Random Access Memory (QRAM) has the potential to revolutionize the area of quantum computing. QRAM uses quantum computing principles to store and modify quantum or classical data efficiently, greatly accelerating a wide range of…
Modern computing systems are limited in performance by the memory bandwidth available to processors, a problem known as the memory wall. Processing-in-Memory (PIM) promises to substantially improve this problem by moving processing closer…
In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…
Processing-using-DRAM has been proposed for a limited set of basic operations (i.e., logic operations, addition). However, in order to enable the full adoption of processing-using-DRAM, it is necessary to provide support for more complex…
Object-oriented programming has long been regarded as too inefficient for SIMD high-performance computing, despite the fact that many important HPC applications have an inherent object structure. On SIMD accelerators, including GPUs, this…