Related papers: DecLock: A Case of Decoupled Locking for Disaggreg…
Scaling neural network training increasingly depends on synchronous data-parallelism, yet full-precision gradient all-reduce imposes a severe communication bottleneck. We propose Decoupled Momentum Optimization (DeMo), a drop-in replacement…
Due to amount of data involved in emerging deep learning and big data applications, operations related to data movement have quickly become the bottleneck. Data-centric computing (DCC), as enabled by processing-in-memory (PIM) and…
Verification of concurrent data structures is one of the most challenging tasks in software verification. The topic has received considerable attention over the course of the last decade. Nevertheless, human-driven techniques remain…
Memory disaggregation can potentially allow memory-optimized range indexes such as B+-trees to scale beyond one machine while attaining high hardware utilization and low cost. Designing scalable indexes on disaggregated memory, however, is…
Replicating or caching popular content in memories distributed across the network is a technique to reduce peak network loads. Conventionally, the main performance gain of this caching was thought to result from making part of the requested…
Distributed deep neural network training necessitates efficient GPU collective communications, which are inherently susceptible to deadlocks. GPU collective deadlocks arise easily in distributed deep learning applications when multiple…
Logic locking (LL) has gained attention as a promising intellectual property protection measure for integrated circuits. However, recent attacks, facilitated by machine learning (ML), have shown the potential to predict the correct key in…
A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full network before updating. Several alternatives that can…
Memory disaggregation is an emerging technology that decouples memory from traditional memory buses, enabling independent scaling of compute and memory. Compute Express Link (CXL), an open-standard interconnect technology, facilitates…
Compute eXpress Link (CXL) has emerged as a key enabler of memory disaggregation for future heterogeneous computing systems to expand memory on-demand and improve resource utilization. However, CXL is still in its infancy stage and lacks…
Although the decentralized storage technology based on the blockchain can effectively realize secure data storage on cloud services. However, there are still some problems in the existing schemes, such as low storage capacity and low…
Major chip manufacturers have all introduced multicore microprocessors. Multi-socket systems built from these processors are used for running various server applications. However to the best of our knowledge current commercial operating…
Massive off-chip accesses in GPUs are the main performance bottleneck, and we divided these accesses into three types: (1) Write, (2) Data-Read, and (3) Read-Only. Besides, We find that many writes are duplicate, and the duplication can be…
Byte-addressable persistent memories (PM) has finally made their way into production. An important and pressing problem that follows is how to deploy them in existing datacenters. One viable approach is to attach PM as self-contained…
Deep neural networks (DNN) use a wide range of network topologies to achieve high accuracy within diverse applications. This model diversity makes it impossible to identify a single "dataflow" (execution schedule) to perform optimally…
Masked Diffusion Language Models generate sequences via iterative sampling that progressively unmasks tokens. However, they still recompute the attention and feed-forward blocks for every token position at every step -- even when many…
In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. To prevent performance interference between the two phases, current…
Today, deep learning is an essential technology for our life. To solve more complex problems with deep learning, both sizes of training datasets and neural networks are increasing. To train a model with large datasets and networks,…
Directory-based protocols have been the de facto solution for maintaining cache coherence in shared-memory parallel systems comprising multi/many cores, where each store instruction is eagerly made globally visible by invalidating the…
Despite recent progress in memory augmented neural network (MANN) research, associative memory networks with a single external memory still show limited performance on complex relational reasoning tasks. Especially the content-based…