Related papers: Buddy-RAM: Improving the Performance and Efficienc…
Dynamic Random Access Memory (DRAM) is the de-facto choice for main memory devices due to its cost-effectiveness. It offers a larger capacity and higher bandwidth compared to SRAM but is slower than the latter. With each passing generation,…
Emerging computing applications such as Artificial Intelligence (AI) are facing a memory wall with existing on-package memory solutions that are unable to meet the power-efficient bandwidth demands. We propose to enhance UCIe with memory…
Digital processing-in-memory (PIM) architectures are rapidly emerging to overcome the memory-wall bottleneck by integrating logic within memory elements. Such architectures provide vast computational power within the memory itself in the…
As a core component in modern data centers, key-value cache provides high-throughput and low-latency services for high-speed data processing. The effectiveness of a key-value cache relies on its ability of accommodating the needed data.…
Cross-attention transformers and other multimodal vision-language models excel at grounding and generation; however, their extensive, full-precision backbones make it challenging to deploy them on edge devices. Memory-augmented…
This article summarizes key results of our work on experimental characterization and analysis of latency variation and latency-reliability trade-offs in modern DRAM chips, which was published in SIGMETRICS 2016, and examines the work's…
Applications of Binary Neural Networks (BNNs) are promising for embedded systems with hard constraints on computing power. Contrary to conventional neural networks with the floating-point datatype, BNNs use binarized weights and activations…
Bit-level sparsity in quantized deep neural networks (DNNs) offers significant potential for optimizing Multiply-Accumulate (MAC) operations. However, two key challenges still limit its practical exploitation. First, conventional bit-serial…
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…
Deep neural network (DNN) inference using reduced integer precision has been shown to achieve significant improvements in memory utilization and compute throughput with little or no accuracy loss compared to full-precision floating-point.…
High-performance branch target buffers (BTBs) and the L1I cache are key to high-performance front-end. Modern branch predictors are highly accurate, but with an increase in code footprint in modern-day server workloads, BTB and L1I misses…
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…
The BDD package Adiar manipulates Binary Decision Diagrams (BDDs) in external memory. This enables handling big BDDs, but the performance suffers when dealing with moderate-sized BDDs. This is mostly due to initializing expensive external…
Many modern workloads such as neural network inference and graph processing are fundamentally memory-bound. For such workloads, data movement between memory and CPU cores imposes a significant overhead in terms of both latency and energy. A…
A theoretical memory with limited processing power and internal connectivity at each element is proposed. This memory carries out parallel processing within itself to solve generic array problems. The applicability of this in-memory…
Increasing storage density exacerbates DRAM read disturbance, a circuit-level vulnerability exploited by system-level attacks. Unfortunately, existing defenses are either ineffective or prohibitively expensive. Efficient mitigation is…
3D point cloud neural networks have significantly enhanced the perceptual capabilities of resource-limited mobile intelligent systems. However, despite the transformative impact, the point cloud algorithm suffers from substantial memory…
The evolution of the Internet and computer applications have generated colossal amount of data. They are referred to as Big Data and they consist of huge volume, high velocity, and variable datasets that need to be managed at the right…
By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with…
Combining discovery and augmentation is important in the era of data usage when it comes to predicting the outcome of tasks. However, having to ask the user the utility function to discover the goal to achieve the optimal small rightful…