Related papers: numaPTE: Managing Page-Tables and TLBs on NUMA Sys…
Neural language models (NLMs) exist in an accuracy-efficiency tradeoff space where better perplexity typically comes at the cost of greater computation complexity. In a software keyboard application on mobile devices, this translates into…
A new emerging class of parallel database management systems (DBMS) is designed to take advantage of the partitionable workloads of on-line transaction processing (OLTP) applications. Transactions in these systems are optimized to execute…
Existing memory reclamation policies on mobile devices may be no longer valid because they have negative effects on the response time of running applications. In this paper, we propose SWAM, a new integrated memory management technique that…
Real-world applications are now processing big-data sets, often bottlenecked by the data movement between the compute units and the main memory. Near-memory computing (NMC), a modern data-centric computational paradigm, can alleviate these…
Emerging computing architectures such as near-memory computing (NMC) promise improved performance for applications by reducing the data movement between CPU and memory. However, detecting such applications is not a trivial task. In this…
The efficient deployment of large language models (LLMs) in online settings requires optimizing inference performance under stringent latency constraints, particularly the time-to-first-token (TTFT) and time-per-output-token (TPOT). This…
Graph partitioning has long been seen as a viable approach to address Graph DBMS scalability. A partitioning, however, may introduce extra query processing latency unless it is sensitive to a specific query workload, and optimised to…
Attention is a fundamental computational kernel that accounts for the majority of the workload in transformer and LLM computing. Optimizing dataflow is crucial for enhancing both performance and energy efficiency in attention computation.…
Task parallelism as employed by the OpenMP task construct, although ideal for tackling irregular problems or typical producer/consumer schemes, bears some potential for performance bottlenecks if locality of data access is important, which…
Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with…
Image bitmaps have been widely used in in-memory applications, which consume lots of storage space and energy. Compared with legacy DRAM, non-volatile memories (NVMs) are suitable for bitmap storage due to the salient features in capacity…
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models. Addressing this challenge, this study delves deep into the Rotated Tensor…
As persistent memory (PM) technologies emerge, hybrid memory architectures combining DRAM with PM bring the potential to provide a tiered, byte-addressable main memory of unprecedented capacity. Nearly a decade after the first proposals for…
As distributed optimization scales to meet the demands of Large Language Model (LLM) training, hardware failures become increasingly non-negligible. Existing fault-tolerant training methods often introduce significant computational or…
This paper presents a broad, pathfinding design space exploration of memory management units (MMUs) for heterogeneous systems. We consider a variety of designs, ranging from accelerators tightly coupled with CPUs (and using their MMUs) to…
Packet-level discrete-event simulation (PLDES) is a prevalent tool for evaluating detailed performance of large model training. Although PLDES offers high fidelity and generality, its slow performance has plagued networking practitioners.…
Disaggregated memory (DM) separates compute and memory resources, allowing flexible scaling to achieve high resource utilization. To ensure atomic and consistent data access on DM, distributed transaction systems have been adapted, where…
Existing single-stream logging schemes are unsuitable for in-memory database management systems (DBMSs) as the single log is often a performance bottleneck. To overcome this problem, we present Taurus, an efficient parallel logging scheme…
Traditional digital implementations of neural accelerators are limited by high power and area overheads, while analog and non-CMOS implementations suffer from noise, device mismatch, and reliability issues. This paper introduces a CMOS…
Region-based memory management (RBMM) is a form of compile time memory management, well-known from the functional programming world. In this paper we describe our work on implementing RBMM for the logic programming language Mercury. One…