Related papers: Prefill vs. Decode Bottlenecks: SRAM-Frequency Tra…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Many modern workloads, such as neural networks, databases, and graph processing, are fundamentally memory-bound. For such workloads, the data movement between main memory and CPU cores imposes a significant overhead in terms of both latency…

The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…

Stencil algorithms on regular lattices appear in many fields of computational science, and much effort has been put into optimized implementations. Such activities are usually not guided by performance models that provide estimates of…

Prior studies have shown that the retention time of the non-volatile spin-transfer torque RAM (STT-RAM) can be relaxed in order to reduce STT-RAM's write energy and latency. However, since different applications may require different…

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenarios. In many real-world applications, the full scale and…

The aggressive scaling of technology may have helped to meet the growing demand for higher memory capacity and density, but has also made DRAM cells more prone to errors. Such a reality triggered a lot of interest in modeling DRAM behavior…

Phase change memory (PCM) has recently emerged as a promising technology to meet the fast growing demand for large capacity memory in computer systems, replacing DRAM that is impeded by physical limitations. Multi-level cell (MLC) PCM…

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…

Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs. We introduce EfficientLLM, a novel benchmark and the first…

This paper studies three fundamental aspects of an OS that impact the performance and energy efficiency of network processing: 1) batching, 2) processor energy settings, and 3) the logic and instructions of the OS networking paths. A…

In the last decade, specific-purpose computing and storage devices, such as GPUs, TPUs, or high-speed storage, have been incorporated into server nodes of Supercomputers and Data centers. The development of high-bandwidth memory (HBM)…

Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it is important to choose the right LRM and operate it in the right way. As a result, the…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

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…

Multichip systems with memory stacks and various processing chips are at the heart of platform based designs such as servers and embedded systems. Full utilization of the benefits of these integrated multichip systems need a seamless, and…

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…