Gunjae Koo

Dr. Gunjae Koo

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 March 2022
Verified
Conference Paper
Closed access
YLYoung Seo Lee
Young Seo Lee
GKGunjae Koo
Gunjae Koo
YGYoung-Ho Gong
Young-Ho Gong
SCSung Woo Chung
Sung Woo Chung
As DRAM process technology scales down and DRAM density continues to grow, DRAM errors have become a primary concern in modern data centers. Typically, data centers have adopted memory systems with a single error correction double error detection (SECDED) code. However, the SECDED code is not sufficient to satisfy DRAM reliability demands as memory systems get more vulnerable. Though the servers in data centers employ strong ECC schemes, such ECC schemes lead to substantial performance and/or storage overhead. In this paper, we propose Stealth ECC, a cost-effective memory protection scheme providing stronger error correctability than the conventional SECDED code, with negligible performance overhead and without storage overhead. Depending on the data-width (either narrow-width or full-width), Stealth ECC adaptively selects ECC schemes. For narrow-width values, Stealth ECC provides multi-bit error correctability by storing more parity bits in MSB side, instead of zeros. Furthermore, with bitwise interleaved data placement between x4 DRAM chips, Stealth ECC is robust to a single DRAM chip error for narrow-width values. On the other hand, for full-width values, Stealth ECC adopts the SECDED code, which maintains DRAM reliability comparable to the conventional SECDED code. As a result, thanks to the reliability improvement of narrow-width values, Stealth ECC enhances overall DRAM reliability, while incurring negligible performance overhead as well as no storage overhead. Our simulation results show that Stealth ECC reduces the probability of system failure (caused by DRAM errors) by 47.9%, on average, with only 0.9% performance overhead compared to the conventional SECDED code.

25 March 2024 in IEEE Access
Verified
Journal Article
Open access
SCSangun Choi
Sangun Choi
SPSeongjun Park
Seongjun Park
JPJaeyong Park
Jaeyong Park
JKJongmin Kim
Jongmin Kim
GKGunjae Koo
Gunjae Koo
YOYunho Oh
Yunho Oh
Conventional DNN inference accelerators are designed with a few (up to four) large systolic arrays. As such a scale-up architecture often suffers from low utilization, a scale-out architecture, in which a single accelerator has tens of pods and each pod has a small systolic array, has been proposed. While the scale-out architecture is promising, it still incurs increasing off-chip memory access as the pods are supposed to access the duplicate tiles of tensors. Prior work has proposed a shared buffer structure to address the problem, but those architectures suffer from performance degradation due to shared buffer access latency. We make an observation that all the pods access the same rows of input and weights within a short time window. With the observation, we propose a new inference accelerator architecture, called Vectored Systolic Arrays (SAVector). SAVector consists of a new two-level on-chip buffer architecture and a tensor tile scheduling technique. In the new buffer architecture, global buffers are shared by all the pods and they keep the rows shared by the pods. And each pod has a tiny dedicated buffer. SAVector monitors the memory access behavior and timely determines to prefetch the data and flush it. In our evaluation, SAVector exhibits a very similar off-chip memory access count to the scale-up architecture and achieves 52% energy-delay-product (EDP) reduction. Also, SAVector achieves 27% EDP reduction over prior work by mitigating performance degradation from global buffer access latency.

26 October 2022 in IEEE Access
Verified
Journal Article
Open access
IKInje Kim
Inje Kim
JJJonghyun Jeong
Jonghyun Jeong
YOYunho Oh
Yunho Oh
MYMyung Kuk Yoon
Myung Kuk Yoon
GKGunjae Koo
Gunjae Koo
Graph convolutional neural networks (GCNs) are emerging neural networks for graph structures that include large features associated with each vertex. The operations of GCN can be divided into two phases - aggregation and combination. While the combination just performs matrix multiplications using trained weights and aggregated features, the aggregation phase requires graph traversal to collect features from adjacent vertices. Even though neural network applications rely on GPU’s massively parallel processing, GCN aggregation kernels exhibit rather low performance since graph processing using compressed graph structures provokes frequent irregular accesses in GPUs. In order to investigate the performance hurdles of GCN aggregation on GPU, we perform an in-depth analysis of the aggregation kernels using real GPU hardware and a cycle-accurate GPU simulator. We first analyze the characteristics of the popular graph datasets used for GCN studies. We reveal the fractions of non-zero elements in feature vectors are diverse among datasets. Based on the observation, we build two types of aggregation kernels that handle uncompressed and compressed feature vectors. Our evaluation exhibits the performance of aggregation can be significantly influenced by kernel design approaches and feature density. We also analyze the individual loads that access the data arrays of the aggregation kernels to specify critical loads. Our analysis reveals the performance of GPU memory hierarchy is influenced by access patterns and feature size of graph datasets. Based on our observations we discuss possible kernel design approaches and architectural ideas that can improve the performance of GCN aggregation.


25 February 2022 in IEEE Transactions on Computers
Verified
Journal Article
Open access
GKGunjae Koo
Gunjae Koo
YOYunho Oh
Yunho Oh
HTHung-Wei Tseng
Hung-Wei Tseng
WRWon Ro
Won Ro
MAMurali Annavaram
Murali Annavaram
Flash memory technologies rely on flash translation layer (FTL) to manage no in-place update and garbage collection. Current FTL management schemes do not exploit the semantics of the accessed data. In this paper, we explore how semantic knowledge can be exploited to build and maintain indexes for stored data automatically. Data indexing is a critical enabler to accelerate many database applications and big data analytics. Unlike traditional per-table or per-file indexes that are managed separately from the data, we propose to maintain indexes on a per-flash page basis. Our approach, called FLash IndeXeR (FLIXR), builds and maintains page-level indexes whenever a page is written into the flash. FLIXR updates the indexes alongside any data updates at page granularity. The cost of the index update is hidden in the page write delays. FLIXR stores index data for each page within the FTL entry associated with that page, thereby piggybacking index access on a page access request. FLIXR accesses the index data in each FTL entry to determine whether the associated page stores data with a given key. FLIXR achieves 52.6% performance improvement for TPC-C and TPC-H benchmarks, compared to the conventional host-side indexing mechanism.

17 June 2025 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
JKJunsu Kim
Junsu Kim
JJJaebeom Jeon
Jaebeom Jeon
JPJaeyong Park
Jaeyong Park
SCSangun Choi
Sangun Choi
MGMinseong Gil
Minseong Gil
YOYunho Oh
Yunho Oh
Deep Neural Network (DNN) training demands large memory capacities that exceed the limits of current GPU onboard memory. Expanding GPU memory with SSDs is a cost-effective approach. However, the low bandwidth of SSDs introduces severe performance bottlenecks in data management, particularly for Unified Virtual Memory (UVM)-based systems. The default on-demand migration mechanism in UVM causes frequent page faults and stalls, exacerbated by memory oversubscription and eviction processes along the critical path. To address these challenges, this paper proposes Memory Oversubscription-aware Scheduling for Tensor Migration (MOST), a software framework designed to improve data migration in UVM environments. MOST profiles memory access behavior and quantifies the impact of memory oversubscription stalls and schedules tensor migrations to minimize overall training time. With the profiling results, MOST executes newly designed pre-eviction and prefetching instructions within DNN kernel code. MOST effectively selects and migrates tensors that can mitigate memory oversubscription stalls, thus reducing training time. Our evaluation shows that MOST achieves an average speedup of 22.9% and 12.8% over state-of-the-art techniques, DeepUM and G10, respectively.