Related papers: FlexMem: High-Parallel Near-Memory Architecture fo…

With the increasing awareness of privacy protection and data fragmentation problem, federated learning has been emerging as a new paradigm of machine learning. Federated learning tends to utilize various privacy preserving mechanisms to…

Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate this bottleneck by providing the memory with computing…

The Compute Express Link (CXL) technology facilitates the extension of CPU memory through byte-addressable SerDes links and cascaded switches, creating complex heterogeneous memory systems where CPU access to various endpoints differs in…

Neural Network (NN) accelerators with emerging ReRAM (resistive random access memory) technologies have been investigated as one of the promising solutions to address the \textit{memory wall} challenge, due to the unique capability of…

As the application of deep learning continues to grow, so does the amount of data used to make predictions. While traditionally, big-data deep learning was constrained by computing performance and off-chip memory bandwidth, a new constraint…

Today, there are a plethora of In-Memory Computing (IMC) devices- SRAMs, PCMs & FeFETs, that emulate convolutions on crossbar-arrays with high throughput. Each IMC device offers its own pros & cons during inference of Deep Neural Networks…

Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE…

Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns…

With the rapid advancement of AI technology, we have seen more and more concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial…

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…

Homomorphic encryption (HE) allows secure computation on encrypted data without revealing the original data, providing significant benefits for privacy-sensitive applications. Many cloud computing applications (e.g., DNA read mapping,…

Fully homomorphic encryption (FHE) allows computations over encrypted data. This technique makes privacy-preserving cloud computing a reality. Users can send their encrypted sensitive data to a cloud server, get encrypted results returned…

Fully Homomorphic Encryption (FHE) emerges one of the most promising solutions to privacy-preserving computing in an untrusted cloud. FHE can be implemented by various schemes, each of which has distinctive advantages, i.e., some are good…

It has been a long standing problem to securely outsource computation tasks to an untrusted party with integrity and confidentiality guarantees. While fully homomorphic encryption (FHE) is a promising technique that allows computations…

The Compute Express Link (CXL) interconnect makes it feasible to integrate diverse types of memory into servers via its byte-addressable SerDes links. Considering the various access latency, harnessing the full potential of CXL-based…

Homomorphic Encryption (HE) draws a significant attention as a privacy-preserving way for cloud computing because it allows computation on encrypted messages called ciphertexts. Among numerous HE schemes proposed, HE for Arithmetic of…

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM…

Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper addresses the memory capacity and bandwidth challenges of…

The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix multiplication schemes…