Tae Jun Ham

Tae Jun Ham

Auto-generated profile, based on publicly available information

Tae Jun Ham

Seoul National University, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 April 2022
Verified
Conference Paper
Closed access
YLYejin Lee
Yejin Lee
HCHyunji Choi
Hyunji Choi
SMSunhong Min
Sunhong Min
HLHyunseung Lee
Hyunseung Lee
SBSangwon Beak
Sangwon Beak
THTae Jun Ham
Tae Jun Ham
Similarity search or nearest neighbor search is a task of retrieving a set of vectors in the (vector) database that are most similar to the provided query vector. It has been a key kernel for many applications for a long time. However, it is becoming especially more important in recent days as modern neural networks and machine learning models represent the semantics of images, videos, and documents as high-dimensional vectors called embeddings. Finding a set of similar embeddings for the provided query embedding is now the critical operation for modern recommender systems and semantic search engines. Since exhaustively searching for the most similar vectors out of billion vectors is such a prohibitive task, approximate nearest neighbor search (ANNS) is often utilized in many real-world use cases. Unfortunately, we find that utilizing the server-class CPUs and GPUs for the ANNS task leads to suboptimal performance and energy efficiency. To address such limitations, we propose a specialized architecture named ANNA (Approximate Nearest Neighbor search Accelerator), which is compatible with state-of-the-art ANNS algorithms such as Google ScaNN and Facebook Faiss. By combining the benefits of a specialized dataflow pipeline and efficient data reuse, ANNA achieves multiple orders of magnitude higher energy efficiency, 2.3-61.6× higher throughput, and 4.3-82.1× lower latency than the conventional CPU or GPU for both million- and billion-scale datasets.

17 April 2021
Verified
Conference Paper
Open access
YLYejin Lee
Yejin Lee
SSSeong Hoon Seo
Seong Hoon Seo
HCHyunji Choi
Hyunji Choi
HSHyoung Uk Sul
Hyoung Uk Sul
SKSoosung Kim
Soosung Kim
THTae Jun Ham
Tae Jun Ham
Deep neural networks (DNNs) with embedding layers are widely adopted to capture complex relationships among entities within a dataset. Embedding layers aggregate multiple embeddings — a dense vector used to represent the complicated nature of a data feature— into a single embedding; such operation is called embedding reduction. Embedding reduction spends a significant portion of its runtime on reading embeddings from memory and thus is known to be heavily memory-bandwidth-bound. Recent works attempt to accelerate this critical operation, but they often require either hardware modifications or emerging memory technologies, which makes it hardly deployable on commodity hardware. Thus, we propose MERCI, Memoization for Embedding Reduction with ClusterIng, a novel memoization framework for efficient embedding reduction. MERCI provides a mechanism for memoizing partial aggregation of correlated embeddings and retrieving the memoized partial result at a low cost. MERCI substantially reduces the number of memory accesses by 44% (29%), leading to 102% (74%) throughput improvement on real machines and 40.2% (28.6%) energy savings at the expense of 8×(1×) additional memory usage.

22 June 2021
Verified
Conference Paper
Open access
DODeok-Jae Oh
Deok-Jae Oh
YMYaebin Moon
Yaebin Moon
ELEojin Lee
Eojin Lee
THTae Jun Ham
Tae Jun Ham
YPYongjun Park
Yongjun Park
JAJung Ho Ahn
Jung Ho Ahn
Hardware performance monitoring units (PMUs) are a standard feature in modern microprocessors for high-performance computing (HPC) and embedded systems, by providing a rich set of microarchitectural event samplers. Recently, many profile-guided optimization (PGO) frameworks have exploited them to feature much lower profiling overhead than conventional instrumentation-based frameworks. However, existing PGO frameworks mostly focus on optimizing the layout of binaries and do not utilize rich information provided by the PMU about data access behaviors over the memory hierarchy. Thus, we propose MaPHeA, a lightweight Memory hierarchy-aware Profile-guided Heap Allocation framework applicable to both HPC and embedded systems. MaPHeA improves application performance by guiding and applying the optimized allocation of dynamically allocated heap objects with very low profiling overhead and without additional user intervention. To demonstrate the effectiveness of MaPHeA, we apply it to optimizing heap object allocation in an emerging DRAM-NVM heterogeneous memory system (HMS), and to selective huge-page utilization. In an HMS, by identifying and placing frequently accessed heap objects to the fast DRAM region, MaPHeA improves the performance of memory-intensive graph-processing and Redis workloads by 56.0% on average over the default configuration that uses DRAM as a hardware-managed cache of slow NVM. Also, by identifying large heap objects that cause frequent TLB misses and allocating them to huge pages, MaPHeA increases the performance of read and update operations of Redis by 10.6% over the transparent huge-page implementation of Linux.

28 June 2017 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
PDF file
THTae Jun Ham
Tae Jun Ham
JAJuan L. Aragón
Juan L. Aragón
MMMargaret Martonosi
Margaret Martonosi
In today’s computers, heterogeneous processing is used to meet performance targets at manageable power. In adopting increased compute specialization, however, the relative amount of time spent on communication increases. System and software optimizations for communication often come at the costs of increased complexity and reduced portability. The Decoupled Supply-Compute (DeSC) approach offers a way to attack communication latency bottlenecks automatically, while maintaining good portability and low complexity. Our work expands prior Decoupled Access Execute techniques with hardware/software specialization. For a range of workloads, DeSC offers roughly 2 × speedup, and additional specialized compression optimizations reduce traffic between decoupled units by 40%.

12 April 2021 in IEEE Micro
Verified
Journal Article
Closed access
THTae Jun Ham
Tae Jun Ham
YLYejin Lee
Yejin Lee
SSSeong Hoon Seo
Seong Hoon Seo
USU Gyeong Song
U Gyeong Song
JLJae W. Lee
Jae W. Lee
LWLisa Wu Wills
Lisa Wu Wills
This article presents a framework, Genesis (genome analysis), to efficiently and flexibly accelerate generic data manipulation operations that have become performance bottlenecks in the genomic data processing pipeline utilizing FPGAs-as-a-service. Genesis conceptualizes genomic data as a very large relational database and uses extended SQL as a domain-specific language to construct data manipulation queries. To accelerate the queries, we designed a Genesis hardware library of efficient coarse-grained primitives that can be composed into a specialized dataflow architecture. This approach explores a systematic and scalable methodology to expedite domain-specific end-to-end accelerated system development and deployment.

30 January 2024 in ACM Transactions on Storage
Verified
Journal Article
Open access
DKDonguk Kim
Donguk Kim
JLJongsung Lee
Jongsung Lee
KLKeun Soo Lim
Keun Soo Lim
JHJun Heo
Jun Heo
THTae Jun Ham
Tae Jun Ham
JLJae W. Lee
Jae W. Lee
Modern log-structured merge (LSM) tree-based key-value stores are widely used to process update-heavy workloads effectively as the LSM tree sequentializes write requests to a storage device to maximize storage performance. However, this append-only approach leaves many outdated copies of frequently updated key-value pairs, which need to be routinely cleaned up through the operation called compaction . When the system load is modest, compaction happens in background. However, at a high system load, it can quickly become the major performance bottleneck. To address this compaction bottleneck and further improve the write throughput of LSM tree-based key-value stores, we propose LAB-DB, which augments the existing LSM tree with a pair of B + trees on byte-addressable nonvolatile memory (NVM). The auxiliary B + trees on NVM reduce both compaction frequency and compaction time, hence leading to lower compaction overhead for writes and fewer storage accesses for reads. According to our evaluation of LAB-DB on RocksDB with YCSB benchmarks, LAB-DB achieves 94% and 67% speedups on two write-intensive workloads (Workload A and F), and also a 43% geomean speedup on read-intensive YCSB Workload B, C, D, and E. This performance gain comes with a low cost of NVM whose size is just 0.6% of the entire dataset to demonstrate the scalability of LAB-DB with an ever increasing volume of future datasets.