Related papers: DUMBO: Making durable read-only transactions fly o…

This paper evaluates the efficacy of recent commercial processing-in-memory (PIM) solutions to accelerate fast Fourier transform (FFT), an important primitive across several domains. Specifically, we observe that efficient implementations…

Poor DRAM technology scaling over the course of many years has caused DRAM-based main memory to increasingly become a larger system bottleneck. A major reason for the bottleneck is that data stored within DRAM must be moved across a…

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Emerging hybrid memory systems that comprise technologies such as Intel's Optane DC Persistent Memory, exhibit disparities in the access speeds and capacity ratios of their heterogeneous memory components. This breaks many assumptions and…

The ever-increasing computation complexity of fastgrowing Deep Neural Networks (DNNs) has requested new computing paradigms to overcome the memory wall in conventional Von Neumann computing architectures. The emerging Computing-In-Memory…

In current microarchitectures, due to the complex memory hierarchies and different latencies on memory accesses, thread and data mapping are important issues to improve application performance. Software transactional memory (STM) is an…

Hybrid memory systems, comprised of emerging non-volatile memory (NVM) and DRAM, have been proposed to address the growing memory demand of applications. Emerging NVM technologies, such as phase-change memories (PCM), memristor, and 3D…

Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM…

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods…

In machine learning (ML), Python serves as a convenient abstraction for working with key libraries such as PyTorch, scikit-learn, and others. Unlike DBMS, however, Python applications may lose important data, such as trained models and…

Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…

With Dynamic Resource Management (DRM) the resources assigned to a job can be changed dynamically during its execution. From the system's perspective, DRM opens a new level of flexibility in resource allocation and job scheduling and…

Conventional wisdom holds that an efficient interface between an OS running on a CPU and a high-bandwidth I/O device should use Direct Memory Access (DMA) to offload data transfer, descriptor rings for buffering and queuing, and interrupts…

Scaling deep neural network (DNN) training to more devices can reduce time-to-solution. However, it is impractical for users with limited computing resources. FOSI, as a hybrid order optimizer, converges faster than conventional optimizers…

Persistent memory (PMEM) devices present an opportunity to retain the flexibility of main memory data structures and algorithms, but augment them with reliability and persistence. The challenge in doing this is to combine replication (for…

A new device structure for spin transfer torque based magnetic random access memory is proposed for on-chip memory applications. Our device structure exploits spin Hall effect to create a differential memory cell that exhibits fast and…

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…

Real-world reinforcement learning systems must operate under distributional drift in their observation streams, yet most policy architectures implicitly assume fully observed and noise-free states. We study robustness of Proximal Policy…

Synchronous Mirroring (SM) is a standard approach to building highly-available and fault-tolerant enterprise storage systems. SM ensures strong data consistency by maintaining multiple exact data replicas and synchronously propagating every…

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…