Related papers: Re-enabling high-speed caching for LSM-trees

The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized…

The billion-scale Large Language Models (LLMs) need deployment on expensive server-grade GPUs with large-storage HBMs and abundant computation capability. As LLM-assisted services become popular, achieving cost-effective LLM inference on…

Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…

Skiplists are widely used for in-memory indexing in many key-value stores, such as RocksDB and LevelDB, due to their ease of implementation and simple concurrency control mechanisms. However, traditional skiplists suffer from poor cache…

The persistence diagram, which describes the topological features of a dataset, is a key descriptor in Topological Data Analysis. The "Discrete Morse Sandwich" (DMS) method has been reported to be the most efficient algorithm for computing…

Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size…

High-level synthesis (HLS) enhances digital hardware design productivity through a high abstraction level. Even if the HLS abstraction prevents fine-grained manual register-transfer level (RTL) optimizations, it also enables automatable…

The performance of today's in-memory indexes is bottlenecked by the memory latency/bandwidth wall. Processing-in-memory (PIM) is an emerging approach that potentially mitigates this bottleneck, by enabling low-latency memory access whose…

Heterogeneous device-edge-cloud computing infrastructures have become widely adopted in telecommunication operators and Wide Area Networks (WANs), offering multi-tier computational support for emerging intelligent services. With the rapid…

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by…

Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (close to) real-time features, for instance, to respond or…

LLMs have seen rapid adoption in all domains. They need to be trained on high-end high-performance computing (HPC) infrastructures and ingest massive amounts of input data. Unsurprisingly, at such a large scale, unexpected events (e.g.,…

We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units. This extends the feedforward neural network parser of Chen and Manning (2014) and enables modelling of entire…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

While mobile devices provide ever more compute power, improvements in DRAM bandwidth are much slower. This is unfortunate for large language model (LLM) token generation, which is heavily memory-bound. Previous work has proposed to leverage…

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of…

The widening gap between processor speed and storage latency has made data movement a dominant bottleneck in modern systems. Two lines of storage-layer innovation attempted to close this gap: persistent memory shortened the latency…

Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred…

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…