Related papers: Experience and performance of persistent memory fo…
Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial…
3D die stacking has often been proposed to build large-scale DRAM-based caches. Unfortunately, the power and performance overheads of DRAM limit the efficiency of high-bandwidth memories. Also, DRAM is facing serious scalability challenges…
Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…
The Deep Underground Neutrino Experiment (DUNE) is a long-baseline neutrino experiment designed to mainly investigate oscillation parameters, supernova physics and proton decay. Its far detector will be composed of four liquid argon time…
The Deep Underground Neutrino Experiment (DUNE) is a next generation long baseline (1300 km) neutrino oscillation experiment. The neutrino beam measurements will be performed by a near detector (ND) and far detector (FD). The far detector…
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which…
This paper presents some of our findings on the scalability of parallel 3D mesh generation on distributed memory machines. The primary objective of this study was to evaluate a distributed memory approach for implementing a 3D parallel…
The Deep Underground Neutrino Experiment (DUNE) is a next-generation long-baseline neutrino oscillation experiment. Its primary goal is the determination of the neutrino mass hierarchy and the CP-violating phase. The DUNE physics program…
Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…
DNA-based storage is an emerging technology that enables digital information to be archived in DNA molecules. This method enjoys major advantages over magnetic and optical storage solutions such as exceptional information density, enhanced…
Resilience is a major design goal for HPC. Checkpoint is the most common method to enable resilient HPC. Checkpoint periodically saves critical data objects to non-volatile storage to enable data persistence. However, using checkpoint, we…
Recent advancements in deep learning have led to the widespread adoption of artificial intelligence (AI) in applications such as computer vision and natural language processing. As neural networks become deeper and larger, AI modeling…
Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…
Compute-in-memory (PIM) mitigates the memory wall by performing computation within memory, reducing data movement and improving energy efficiency. DRAM-based PIM is particularly attractive due to its high density, mature manufacturing…
I/O latency and throughput is one of the major performance bottlenecks for disk-based database systems. Upcoming persistent memory (PMem) technologies, like Intel's Optane DC Persistent Memory Modules, promise to bridge the gap between…
The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time.…
Quantum memory is an important component in the long-distance quantum communication system based on the quantum repeater protocol. To outperform the direct transmission of photons with quantum repeaters, it is crucial to develop quantum…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
The data processing model for the CDF experiment is described. Data processing reconstructs events from parallel data streams taken with different combinations of physics event triggers and further splits the events into datasets of…