6 papers
AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance
Seungkwan Kang, Seungjun Lee, Donghyun Gouk +9
Graph neural network (GNN) inference faces significant bottlenecks in preprocessing, which often dominate overall inference latency. We introduce AutoGNN, an FPGA-based accelerator…
MPI-over-CXL: Enhancing Communication Efficiency in Distributed HPC Systems
Miryeong Kwon, Donghyun Gouk, Hyein Woo +10
MPI implementations commonly rely on explicit memory-copy operations, incurring overhead from redundant data movement and buffer management. This overhead notably impacts HPC workl…
ScalePool: Hybrid XLink-CXL Fabric for Composable Resource Disaggregation in Unified Scale-up Domains
Hyein Woo, Miryeong Kwon, Jiseon Kim +4
This paper proposes ScalePool, a novel cluster architecture designed to interconnect numerous accelerators using unified hardware interconnects rather than traditional long-distanc…
From Block to Byte: Transforming PCIe SSDs with CXL Memory Protocol and Instruction Annotation
Miryeong Kwon, Donghyun Gouk, Junhyeok Jang +8
This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting bl…
Containerized In-Storage Processing and Computing-Enabled SSD Disaggregation
Miryeong Kwon, Donghyun Gouk, Eunjee Na +9
ISP minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model leveraging OS-level virtualization and lightweig…
CXL Topology-Aware and Expander-Driven Prefetching: Unlocking SSD Performance
Dongsuk Oh, Miryeong Kwon, Jiseon Kim +8
Integrating compute express link (CXL) with SSDs allows scalable access to large memory but has slower speeds than DRAMs. We present ExPAND, an expander-driven CXL prefetcher that…