Related papers: TransforMAP: Transformer for Memory Access Predict…

Transformer-based methods have shown great potential in long-term time series forecasting. However, most of these methods adopt the standard point-wise self-attention mechanism, which not only becomes intractable for long-term forecasting…

Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…

The Transformer model has shown leading performance in time series forecasting. Nevertheless, in some complex scenarios, it tends to learn low-frequency features in the data and overlook high-frequency features, showing a frequency bias.…

Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…

Hardware based memory pooling enabled by interconnect standards like CXL have been gaining popularity amongst cloud providers and system integrators. While pooling memory resources has cost benefits, it comes at a penalty of increased…

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

We propose an approach to data memory prefetching which augments the standard prefetch buffer with selection criteria based on performance and usage pattern of a given instruction. This approach is built on top of a pattern matching based…

The growth of the World Wide Web has emphasized the need for improvement in user latency. One of the techniques that are used for improving user latency is Caching and another is Web Prefetching. Approaches that bank solely on caching offer…

Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…

The conventional designs of mobile computation offloading fetch user-specific data to the cloud prior to computing, called offline prefetching. However, this approach can potentially result in excessive fetching of large volumes of data and…

Large Language Models (LLMs) have achieved impressive performance across diverse tasks but continue to struggle with learning transitive relations, a cornerstone for complex planning. To address this issue, we investigate the Multi-Token…

Neural preconditioners for real-time physics simulation offer promising data-driven priors, but they often fail to capture long-range couplings efficiently because they inherit local message passing or sparse-operator access patterns. We…

Caching techniques are widely used in the era of cloud computing from applications, such as Web caches to infrastructures, Memcached and memory caches in computer architectures. Prediction of cached data can greatly help improve cache…

Content Delivery Networks carry the majority of Internet traffic, and the increasing demand for video content as a major IP traffic across the Internet highlights the importance of caching and prefetching optimization algorithms.…

Multivariate time series forecasting focuses on predicting future values based on historical context. State-of-the-art sequence-to-sequence models rely on neural attention between timesteps, which allows for temporal learning but fails to…

There has been an explosion of interest in designing high-performance Transformers. While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all…

Memory latencies and bandwidth are major factors, limiting system performance and scalability. Modern CPUs aim at hiding latencies by employing large caches, out-of-order execution, or complex hardware prefetchers. However, software-based…

Predictive business process monitoring focuses on predicting future characteristics of a running process using event logs. The foresight into process execution promises great potentials for efficient operations, better resource management,…

For decades, memory capabilities have scaled up much slower than compute capabilities, leaving memory utilization as a major bottleneck. Prefetching and cache hierarchies mitigate this in applications with easily predictable memory accesses…