Related papers: SWARM: Replicating Shared Disaggregated-Memory Dat…
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…
Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address…
Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device…
Safe memory reclamation (SMR) schemes are an essential tool for lock-free data structures and concurrent programming. However, manual SMR schemes are notoriously difficult to apply correctly, and automatic schemes, such as reference…
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…
Disaggregation and rack-scale systems have the potential of drastically decreasing TCO and increasing utilization of cloud datacenters, while maintaining performance. While the concept of organising resources in separate pools and…
WebAssembly (Wasm for short) brings a new, powerful capability to the web as well as Edge, IoT, and embedded systems. Wasm is a portable, compact binary code format with high performance and robust sandboxing properties. As Wasm…
Large Language Models (LLMs) have revolutionized natural language processing tasks, but their deployment in datacenter environments faces significant challenges due to the massive memory requirements of key-value (KV) caches. During the…
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…
Sparse matrix-matrix multiplication (SpGEMM) is a critical kernel widely employed in machine learning and graph algorithms. However, real-world matrices' high sparsity makes SpGEMM memory-intensive. In-situ computing offers the potential to…
Storage replication is one of the essential requirements for network environments. While many forms of Network Attached Storage (NAS), Storage Area Networks (SAN) and other forms of network storage exist, there is a need for a reliable…
Next-generation real-time compute-intensive applications, such as extended reality, multi-user gaming, and autonomous transportation, are increasingly composed of heterogeneous AI-intensive functions with diverse resource requirements and…
We introduce $\textit{sorted weight sectioning}$ (SWS): a weight allocation algorithm that places sorted deep neural network (DNN) weight sections on bit-sliced compute-in-memory (CIM) crossbars to reduce analog-to-digital converter (ADC)…
Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate this bottleneck by providing the memory with computing…
Intermittent computing systems operate by relying only on harvested energy accumulated in their tiny energy reservoirs, typically capacitors. An intermittent device dies due to a power failure when there is no energy in its capacitor and…
Retrieval-augmented generation (RAG) systems commonly improve robustness via query-time adaptations such as query expansion and iterative retrieval. While effective, these approaches are inherently stateless: adaptations are recomputed for…
Disaggregated memory is promising for improving memory utilization in computer clusters in which memory demands significantly vary across computer nodes under utilization. It allows applications with high memory demands to use memory in…
Resistive random-access memory (ReRAM) is a promising candidate for the next generation non-volatile memory technology due to its simple read/write operations and high storage density. However, its crossbar array structure causes a severe…
Modern applications demand high performance and cost efficient database management systems (DBMSs). Their workloads may be diverse, ranging from online transaction processing to analytics and decision support. The cloud infrastructure…
As its core computation, a self-attention mechanism gauges pairwise correlations across the entire input sequence. Despite favorable performance, calculating pairwise correlations is prohibitively costly. While recent work has shown the…