Michael Niemier
YOU?
Author Swipe
View article: COSMOS: RL-Enhanced Locality-Aware Counter Cache Optimization for Secure Memory
COSMOS: RL-Enhanced Locality-Aware Counter Cache Optimization for Secure Memory Open
View article: Design and Evaluation of Monolithic 3D Content Addressable Memories
Design and Evaluation of Monolithic 3D Content Addressable Memories Open
View article: TAP-CAM: A Tunable Approximate Matching Engine based on Ferroelectric Content Addressable Memory
TAP-CAM: A Tunable Approximate Matching Engine based on Ferroelectric Content Addressable Memory Open
Pattern search is crucial in numerous analytic applications for retrieving data entries akin to the query. Content Addressable Memories (CAMs), an in-memory computing fabric, directly compare input queries with stored entries through embed…
View article: A 65 nm Bayesian Neural Network Accelerator with 360 fJ/Sample In-Word GRNG for AI Uncertainty Estimation
A 65 nm Bayesian Neural Network Accelerator with 360 fJ/Sample In-Word GRNG for AI Uncertainty Estimation Open
Uncertainty estimation is an indispensable capability for AI-enabled, safety-critical applications, e.g. autonomous vehicles or medical diagnosis. Bayesian neural networks (BNNs) use Bayesian statistics to provide both classification predi…
View article: A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI
A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI Open
Neuro-symbolic artificial intelligence (AI) excels at learning from noisy and generalized patterns, conducting logical inferences, and providing interpretable reasoning. Comprising a 'neuro' component for feature extraction and a 'symbolic…
View article: Shared-PIM: Enabling Concurrent Computation and Data Flow for Faster Processing-in-DRAM
Shared-PIM: Enabling Concurrent Computation and Data Flow for Faster Processing-in-DRAM Open
Processing-in-Memory (PIM) enhances memory with computational capabilities, potentially solving energy and latency issues associated with data transfer between memory and processors. However, managing concurrent computation and data flow w…
View article: Deep random forest with ferroelectric analog content addressable memory
Deep random forest with ferroelectric analog content addressable memory Open
Deep random forest (DRF), which combines deep learning and random forest, exhibits comparable accuracy, interpretability, low memory and computational overhead to deep neural networks (DNNs) in edge intelligence tasks. However, efficient D…
View article: Smoothing Disruption Across the Stack: Tales of Memory, Heterogeneity, & Compilers
Smoothing Disruption Across the Stack: Tales of Memory, Heterogeneity, & Compilers Open
International audience
View article: A New Secure Memory System for Efficient Data Protection and Access Pattern Obfuscation
A New Secure Memory System for Efficient Data Protection and Access Pattern Obfuscation Open
As the reliance on secure memory environments permeates across applications, memory encryption is used to ensure memory security. However, most effective encryption schemes, such as the widely used AES-CTR, inherently introduce extra overh…
View article: Efficient approximation of Earth Mover's Distance Based on Nearest Neighbor Search
Efficient approximation of Earth Mover's Distance Based on Nearest Neighbor Search Open
Earth Mover's Distance (EMD) is an important similarity measure between two distributions, used in computer vision and many other application domains. However, its exact calculation is computationally and memory intensive, which hinders it…
View article: Privacy Preserving In-memory Computing Engine
Privacy Preserving In-memory Computing Engine Open
Privacy has rapidly become a major concern/design consideration. Homomorphic Encryption (HE) and Garbled Circuits (GC) are privacy-preserving techniques that support computations on encrypted data. HE and GC can complement each other, as H…
View article: Accelerating Polynomial Modular Multiplication with Crossbar-Based Compute-in-Memory
Accelerating Polynomial Modular Multiplication with Crossbar-Based Compute-in-Memory Open
Lattice-based cryptographic algorithms built on ring learning with error theory are gaining importance due to their potential for providing post-quantum security. However, these algorithms involve complex polynomial operations, such as pol…
View article: Cross Layer Design for the Predictive Assessment of Technology-Enabled Architectures
Cross Layer Design for the Predictive Assessment of Technology-Enabled Architectures Open
There is great interest in "end-to-end" analysis that captures how innovation at the materials, device, and/or architectural levels will impact figures of merit at the application-level. However, there are numerous combinations of devices …
View article: Achieving software-equivalent accuracy for hyperdimensional computing with ferroelectric-based in-memory computing
Achieving software-equivalent accuracy for hyperdimensional computing with ferroelectric-based in-memory computing Open
View article: Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search
Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search Open
View article: COSIME: FeFET based Associative Memory for In-Memory Cosine Similarity Search
COSIME: FeFET based Associative Memory for In-Memory Cosine Similarity Search Open
In a number of machine learning models, an input query is searched across the trained class vectors to find the closest feature class vector in cosine similarity metric. However, performing the cosine similarities between the vectors in Vo…
View article: Experimentally realized memristive memory augmented neural network
Experimentally realized memristive memory augmented neural network Open
Lifelong on-device learning is a key challenge for machine intelligence, and this requires learning from few, often single, samples. Memory augmented neural network has been proposed to achieve the goal, but the memory module has to be sto…
View article: Modeling and Design for Magnetoelectric Ternary Content Addressable Memory (TCAM)
Modeling and Design for Magnetoelectric Ternary Content Addressable Memory (TCAM) Open
This article proposes a novel magnetoelectric (ME) effect-based ternary content addressable memory (TCAM). The potential array-level write and search performances of the proposed ME-TCAM are studied using experimentally calibrated compact …
View article: Hardware-Software Co-Design of an In-Memory Transformer Network Accelerator
Hardware-Software Co-Design of an In-Memory Transformer Network Accelerator Open
Transformer networks have outperformed recurrent and convolutional neural networks in terms of accuracy in various sequential tasks. However, memory and compute bottlenecks prevent transformer networks from scaling to long sequences due to…
View article: iMARS: An In-Memory-Computing Architecture for Recommendation Systems
iMARS: An In-Memory-Computing Architecture for Recommendation Systems Open
Recommendation systems (RecSys) suggest items to users by predicting their preferences based on historical data. Typical RecSys handle large embedding tables and many embedding table related operations. The memory size and bandwidth of the…
View article: CoursePathVis: Course path visualization using flexible grouping and funnel-augmented Sankey diagram
CoursePathVis: Course path visualization using flexible grouping and funnel-augmented Sankey diagram Open
We present CoursePathVis, a visual analytics tool for exploring and analyzing students’ progress through a college curriculum using a Sankey diagram. Focusing on four student cohorts in a department, we group students in multiple ways (b…
View article: IMCRYPTO: An In-Memory Computing Fabric for AES Encryption and Decryption
IMCRYPTO: An In-Memory Computing Fabric for AES Encryption and Decryption Open
This paper proposes IMCRYPTO, an in-memory computing (IMC) fabric for accelerating AES encryption and decryption. IMCRYPTO employs a unified structure to implement encryption and decryption in a single hardware architecture, with combined …
View article: Deep Random Forest with Ferroelectric Analog Content Addressable Memory
Deep Random Forest with Ferroelectric Analog Content Addressable Memory Open
Deep random forest (DRF), which incorporates the core features of deep learning and random forest (RF), exhibits comparable classification accuracy, interpretability, and low memory and computational overhead when compared with deep neural…
View article: MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing
MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing Open
Hyperdimensional Computing (HDC) is an emerging computational framework that mimics important brain functions by operating over high-dimensional vectors, called hypervectors (HVs). In-memory computing implementations of HDC are desirable s…
View article: Application-driven Design Exploration for Dense Ferroelectric Embedded Non-volatile Memories
Application-driven Design Exploration for Dense Ferroelectric Embedded Non-volatile Memories Open
The memory wall bottleneck is a key challenge across many data-intensive applications. Multi-level FeFET-based embedded non-volatile memories are a promising solution for denser and more energy-efficient on-chip memory. However, reliable m…
View article: MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit\n In-Memory Computing
MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit\n In-Memory Computing Open
Hyperdimensional Computing (HDC) is an emerging computational framework that\nmimics important brain functions by operating over high-dimensional vectors,\ncalled hypervectors (HVs). In-memory computing implementations of HDC are\ndesirabl…
View article: Application-driven Design Exploration for Dense Ferroelectric Embedded\n Non-volatile Memories
Application-driven Design Exploration for Dense Ferroelectric Embedded\n Non-volatile Memories Open
The memory wall bottleneck is a key challenge across many data-intensive\napplications. Multi-level FeFET-based embedded non-volatile memories are a\npromising solution for denser and more energy-efficient on-chip memory.\nHowever, reliabl…
View article: The Implications of Ferroelectric FET Device Models to the Design of Computing-in-Memory Architectures
The Implications of Ferroelectric FET Device Models to the Design of Computing-in-Memory Architectures Open
Data transfer between a processor and memory frequently represents a bottleneck with respect to improving application-level performance. Computing-in-memory (CiM), where logic and arithmetic operations are performed in memory, could …
View article: In-Memory Nearest Neighbor Search with FeFET Multi-Bit Content-Addressable Memories
In-Memory Nearest Neighbor Search with FeFET Multi-Bit Content-Addressable Memories Open
Nearest neighbor (NN) search is an essential operation in many applications, such as one/few-shot learning and image classification. As such, fast and low-energy hardware support for accurate NN search is highly desirable. Ternary content-…
View article: In-Memory Nearest Neighbor Search with FeFET Multi-Bit\n Content-Addressable Memories
In-Memory Nearest Neighbor Search with FeFET Multi-Bit\n Content-Addressable Memories Open
Nearest neighbor (NN) search is an essential operation in many applications,\nsuch as one/few-shot learning and image classification. As such, fast and\nlow-energy hardware support for accurate NN search is highly desirable. Ternary\nconte…