Haejin Nam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haejin Nam has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Soontae Kim
School of Computing, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
3 shared publications - Jinkwon Kim
School of Computing, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
2 shared publications - Myeongjae Jang
Korea Advanced Institute of Science & Technology (KAIST), Republic of Korea
2 shared publications D.J. Kim
Korea Electrotechnology Research Institute, 665 Euiwang Gyungido, 437-808, Korea
1 shared publicationJ. B. Choo
Power System Laboratory, Korea Electric Power Research Institute, 103-16 Munji-dong, Yusung-gu, Daejon 305-380, Korea
1 shared publicationJ. W. Lee
Power System Laboratory, Korea Electric Power Research Institute, 103-16 Munji-dong, Yusung-gu, Daejon 305-380, Korea
1 shared publication
Latest Publications
- Open Access
- 28 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1148-1162
HARP: Hardware-Based Pseudo-Tiling for Sparse Matrix Multiplication Accelerator
General sparse matrix-matrix multiplication (SpGEMM) is a memory-bound workload, due to the compression format used. To minimize data movements for input matrices, outer product accelerators have been proposed. Since these accelerators access input matrices only once and then generate numerous partial products, managing the generated partial products is the key optimization factor. To reduce the number of partial products handled, the state-of-the-art accelerator uses software to tile an input matrix. However, the software-based tiling has three limitations. First, a user manually executes the tiling software and manages the tiles. Second, generating a compression format for each tile incurs memory-intensive operations. Third, an accelerator that uses the compression format cannot skip ineffectual accesses for input matrices. To overcome these limitations, this paper proposes hardware-based pseudo-tiling (HARP), which enables logical tiling of the original compressed matrix without generating a compression format for each tile. To this end, HARP utilizes our proposed Runtime Operand Descriptor to point to an effectual column-row pair in a pseudo-tile. Consequently, HARP enables a user to use the accelerator as a normal SpGEMM operation does without tiling. Furthermore, HARP does not require a compression format for each tile and can skip ineffectual accesses for input matrices. To further improve the efficiency of pseudo-tiling, HARP performs super-tiling to combine pseudo-tiles and sub-tiling to further tile a pseudo-tile. Experiment results show that HARP achieves 4 ×, 35 ×, and 33 × speedup and 5 ×, 664 ×, and 233 × energy efficiency on average compared to the state-of-the-art outer product accelerator, CPU (MKL), and GPU (cuSPARSE), respectively.
- 28 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1148-1162
Open AccessHARP: Hardware-Based Pseudo-Tiling for Sparse Matrix Multiplication Accelerator
General sparse matrix-matrix multiplication (SpGEMM) is a memory-bound workload, due to the compression format used. To minimize data movements for input matrices, outer product accelerators have been proposed. Since these accelerators access input matrices only once and then generate numerous partial products, managing the generated partial products is the key optimization factor. To reduce the number of partial products handled, the state-of-the-art accelerator uses software to tile an input matrix. However, the software-based tiling has three limitations. First, a user manually executes the tiling software and manages the tiles. Second, generating a compression format for each tile incurs memory-intensive operations. Third, an accelerator that uses the compression format cannot skip ineffectual accesses for input matrices. To overcome these limitations, this paper proposes hardware-based pseudo-tiling (HARP), which enables logical tiling of the original compressed matrix without generating a compression format for each tile. To this end, HARP utilizes our proposed Runtime Operand Descriptor to point to an effectual column-row pair in a pseudo-tile. Consequently, HARP enables a user to use the accelerator as a normal SpGEMM operation does without tiling. Furthermore, HARP does not require a compression format for each tile and can skip ineffectual accesses for input matrices. To further improve the efficiency of pseudo-tiling, HARP performs super-tiling to combine pseudo-tiles and sub-tiling to further tile a pseudo-tile. Experiment results show that HARP achieves 4 ×, 35 ×, and 33 × speedup and 5 ×, 664 ×, and 233 × energy efficiency on average compared to the state-of-the-art outer product accelerator, CPU (MKL), and GPU (cuSPARSE), respectively.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 73 (1) , 249-262
Zero and Narrow-Width Value-Aware Compression for Quantized Convolutional Neural Networks
Convolutional neural networks are normally used in systems with dedicated neural processing units for CNN-related computations. For high performance and low hardware overheads, CNN datatype quantization is applied. As an additional optimization, to further reduce DRAM accesses, compression algorithms have been used for CNN data. However, conventional zero value-aware compression algorithms suffer from a reduction in compression ratio with the latest quantized CNNs, owing to the small number of zero values. Moreover, the appropriate zero run-length code width can be changed dynamically based on the CNNs, layers, and quantization datatypes. As another compressible data value for increasing the compression ratio, the latest quantized CNNs have many narrow-width values. Because low-precision quantization reduces the data bit width, CNN data are gathered into a few discrete values and incur a biased data distribution. These discrete values become narrow-width values, and constitute a large proportion of the biased distribution. In this article, we propose an efficient compression algorithm for quantized CNNs, ENCORE, which utilizes variable zero run-length encoding and compresses narrow-width values. With the latest quantized CNNs, ENCORE shows higher compression ratios, 93.55% and 50.85% in Mobilenet v1 and Tiny YOLO v3, respectively, than conventional zero value-aware CNN data compression algorithms.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 73 (1) , 249-262
Zero and Narrow-Width Value-Aware Compression for Quantized Convolutional Neural Networks
Convolutional neural networks are normally used in systems with dedicated neural processing units for CNN-related computations. For high performance and low hardware overheads, CNN datatype quantization is applied. As an additional optimization, to further reduce DRAM accesses, compression algorithms have been used for CNN data. However, conventional zero value-aware compression algorithms suffer from a reduction in compression ratio with the latest quantized CNNs, owing to the small number of zero values. Moreover, the appropriate zero run-length code width can be changed dynamically based on the CNNs, layers, and quantization datatypes. As another compressible data value for increasing the compression ratio, the latest quantized CNNs have many narrow-width values. Because low-precision quantization reduces the data bit width, CNN data are gathered into a few discrete values and incur a biased data distribution. These discrete values become narrow-width values, and constitute a large proportion of the biased distribution. In this article, we propose an efficient compression algorithm for quantized CNNs, ENCORE, which utilizes variable zero run-length encoding and compresses narrow-width values. With the latest quantized CNNs, ENCORE shows higher compression ratios, 93.55% and 50.85% in Mobilenet v1 and Tiny YOLO v3, respectively, than conventional zero value-aware CNN data compression algorithms.
- 27 October 2005
- Published by Wiley in European Transactions on Electrical Power
- Vol. 16 (1) , 79-91
Construction of largest equivalent systems for power system simulator
This paper presents the dynamic reduction algorithm including network reduction for large‐scale power systems to develop the largest equivalent systems. In particular, the proposed reduction algorithm is suitable for the real time digital simulator. The load angle of the synchronous machine is used as a state variable to identify or aggregate the coherent synchronous machine groups. In this paper, the equivalent systems that preserve the desired property of the original systems are evaluated to verify the algorithm with dynamic simulation for given power system faults. The results of comparison between the original systems and equivalent systems are described to provide the accuracy and reliability. Copyright © 2005 John Wiley & Sons, Ltd.
- 27 October 2005
- Published by Wiley in European Transactions on Electrical Power
- Vol. 16 (1) , 79-91
Construction of largest equivalent systems for power system simulator
This paper presents the dynamic reduction algorithm including network reduction for large‐scale power systems to develop the largest equivalent systems. In particular, the proposed reduction algorithm is suitable for the real time digital simulator. The load angle of the synchronous machine is used as a state variable to identify or aggregate the coherent synchronous machine groups. In this paper, the equivalent systems that preserve the desired property of the original systems are evaluated to verify the algorithm with dynamic simulation for given power system faults. The results of comparison between the original systems and equivalent systems are described to provide the accuracy and reliability. Copyright © 2005 John Wiley & Sons, Ltd.
- 1 September 2003
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 36 (20) , 709-715
Eigenvalue Analysis Program of Small-Signal Stability of Power System Including Network Dynamics for the Subsynchronous Resonance Study
- 1 September 2003
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 36 (20) , 709-715
Eigenvalue Analysis Program of Small-Signal Stability of Power System Including Network Dynamics for the Subsynchronous Resonance Study