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

Non-volatile memory (NVM) technologies such as PCM, ReRAM and STT-RAM allow processors to directly write values to persistent storage at speeds that are significantly faster than previous durable media such as hard drives or SSDs. Many…

Persistent memory provides high-performance data persistence at main memory. Memory writes need to be performed in strict order to satisfy storage consistency requirements and enable correct recovery from system crashes. Unfortunately,…

Recent deep learning workloads increasingly push computational demand beyond what current memory systems can sustain, with many kernels stalling on data movement rather than computation. While modern dataflow accelerators incorporate…

Oblivious RAM (ORAM) hides the memory access patterns, enhancing data privacy by preventing attackers from discovering sensitive information based on the sequence of memory accesses. The performance of ORAM is often limited by its inherent…

This brief introduces a read bias circuit to improve readout yield of magnetic random access memories (MRAMs). A dynamic bias optimization (DBO) circuit is proposed to enable the real-time tracking of the optimal read voltage across…

Fine-tuning is a critical step for adapting large language models (LLMs) to domain-specific downstream tasks. To mitigate the substantial computational and memory costs of full-model fine-tuning, Parameter-Efficient Fine-Tuning (PEFT)…

We propose Hybrid Transactional Replication (HTR), a novel replication scheme for highly dependable services. It combines two schemes: a transaction is executed either optimistically by only one service replica in the deferred update mode…

We can use a hybrid memory system consisting of DRAM and Intel Optane DC Persistent Memory (We call it DCPM in this paper) as DCPM is now commercially available since April 2019. Even if the latency for DCPM is several times higher than…

Memory-centric computing aims to enable computation capability in and near all places where data is generated and stored. As such, it can greatly reduce the large negative performance and energy impact of data access and data movement, by…

Following the design of more efficient blockchain consensus algorithms, the execution layer has emerged as the new performance bottleneck of blockchains, especially under high contention. Current parallel execution frameworks either rely on…

Automated machine learning aims to automate the whole process of machine learning, including model configuration. In this paper, we focus on automated hyperparameter optimization (HPO) based on sequential model-based optimization (SMBO).…

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this…

Data processing units (DPUs, SoC-based SmartNICs) are emerging data center hardware that provide opportunities to address cloud data processing challenges. Their onboard compute, memory, network, and auxiliary storage can be leveraged to…

Byte-addressable persistent memory (B-APM) presents a new opportunity to bridge the performance gap between main memory and storage. In this paper, we present the usage scenarios for this new technology, based on the capabilities of Intel's…

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process theory in cognitive…

Direct Preference Optimization (DPO) has been widely adopted for large language model alignment due to its simple training procedure and lack of an explicit reward model. However, in iterative DPO, when the policy model from the previous…

Most STM systems are poorly equipped to support libraries of concurrent data structures. One reason is that they typically detect conflicts by tracking transactions' read sets and write sets, an approach that often leads to false conflicts.…

Data copy is a widely-used memory operation in many programs and operating system services. In conventional computers, data copy is often carried out by two separate read and write transactions that pass data back and forth between the DRAM…

Recent dual in-line memory modules (DIMMs) are starting to support processing-in-memory (PIM) by associating their memory banks with processing elements (PEs), allowing applications to overcome the data movement bottleneck by offloading…