Organization
Institute of Integrated Research AI Computing Research Unit Associate Professor
Title
Associate Professor
External link
FUJIKI DAICHI
Education
-
University of Michigan, Ann Arbor
2016.9 - 2022.2
Country： United States
-
Keio University Faculty of Science and Technology Department of Information and Computer Science
2012.4 - 2016.3
Country： Japan
Research History
-
Institute of Science Tokyo Institute of Integrated Research Associate Professor
2023.11
-
Tokyo Institute of Technology Institute of Innovative Research Associate Professor
2023.11 - 2024.10
-
Keio University Graduate School of Science and Technology Assistant Professor
2022.4 - 2023.10
Committee Memberships
-
MICRO 2025 TPC member
2025
-
HPCA 2025 TPC member
2025
-
ISCA 2025 TPC member
2025
-
ISCA 2024 TPC member
2024
-
HPCA 2024 TPC member
2024
-
IISWC 2023 TPC member
2023
-
HPCA 2023 light-load TPC member
2023
-
IISWC 2022 TPC member
2022
-
MICRO 2019 submission co-chair
2019
Papers
-
AQPIM: Breaking the PIM Capacity Wall for LLMs with in-Memory Activation Quantization
Kosuke Matsushima, Yasuyuki Okoshi, Masato Motomura, Daichi Fujiki
2026 IEEE International Symposium on High Performance Computer Architecture (HPCA) 2026.1
-
Memory-Efficient and Trustworthy Neural Networks via Random Seed-Based Design
Hiroaki Ito, Hikari Otsuka, Ryota Yasudo, Zhiqiang Que, Jose G. F. Coutinho, Daichi Fujiki, Masato Motomura, Ce Guo, Wayne Luk
IEEE Access 2026
-
BingoGCN: Towards Scalable and Efficient GNN Acceleration with Fine-Grained Partitioning and SLT
Jiale Yan, Hiroaki Ito, Yuta Nagahara, Kazushi Kawamura, Masato Motomura, Thiem Van Chu, Daichi Fujiki
Proceedings of the 52nd Annual International Symposium on Computer Architecture 1910 - 1924 2025.6
-
DX100: Programmable Data Access Accelerator for Indirection
Alireza Khadem, Kamalavasan Kamalakkannan, Zhenyan Zhu, Akash Poptani, Yufeng Gu, Jered Benjamin Dominguez-Trujillo, Nishil Talati, Daichi Fujiki, Scott Mahlke, Galen Shipman, Reetuparna Das
Proceedings of the 52nd Annual International Symposium on Computer Architecture 1641 - 1658 2025.6
-
Multi-Dimensional Vector ISA Extension for Mobile In-Cache Computing
Alireza Khadem, Daichi Fujiki, Hilbert Chen, Yufeng Gu, Nishil Talati, Scott Mahlke, Reetuparna Das
2025 IEEE International Symposium on High Performance Computer Architecture (HPCA) 487 - 503 2025.3
-
WhiteDwarf: A Holistic Co-Design Approach to Ultra-Compact Neural Inference Acceleration
Ángel López García-Arias, Yasuyuki Okoshi, Jaehoon Yu, Junnnosuke Suzuki, Hikari Otsuka, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Masato Motomura
IEEE Access 2025
-
DMSA: An Efficient Architecture for Sparse–Sparse Matrix Multiplication Based on Distribute-Merge Product Dataflow
Yuta Nagahara, Jiale Yan, Kazushi Kawamura, Daichi Fujiki, Masato Motomura, Thiem Van Chu
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 2025
-
SharK: Enabling High-Performance Range Queries in Key-Value Store Through Vlog Resharding
Naoto Sugiura, Daichi Fujiki
IEEE Access 2025
-
The Case for Coherence Directories in Memory Cubes
Yuki Kameyama, Naoya Niwa, Daichi Fujiki, Hiroki Matsutani, Michihiro Koibuchi, Hideharu Amano
2024 IEEE 17th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) 187 - 193 2024.12
-
Akihiro Shioda, Ángel López García-Arias, Hikari Otsuka, Yuki Ichikawa, Yasuyuki Okoshi, Kazushi Kawamura, Thiem Van Chu, Daichi Fujiki, Masato Motomura
2024 Twelfth International Symposium on Computing and Networking (CANDAR) 224 - 230 2024.11
-
Yasuyuki Okoshi, Ángel López García-Arias, Jaehoon Yu, Junnnosuke Suzuki, Hikari Otsuka, Thiem Van Chu, Kazushi Kawamura, Daichi Fujiki, Masato Motomura
2024 IEEE Asian Solid-State Circuits Conference (A-SSCC) 1 - 3 2024.11
-
MVC: Enabling Fully Coherent Multi-Data-Views through the Memory Hierarchy with Processing in Memory
Daichi Fujiki
2023 56th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) 2023.10
-
Vector-Processing for Mobile Devices: Benchmark and Analysis
Alireza Khadem, Daichi Fujiki, Nishil Talati, Scott Mahlke, Reetuparna Das
2023 IEEE International Symposium on Workload Characterization (IISWC) 2023.10
-
Multi-Layer In-Memory Processing
Daichi Fujiki, Alireza Khadem, Scott Mahlke, Reetuparna Das
2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO) 2022.10
-
In-/Near-Memory Computing
Daichi Fujiki, Xiaowei Wang, Arun Subramaniyan 0001, Reetuparna Das
1 - 140 2021
-
Zhehong Wang, Tianjun Zhang, Daichi Fujiki, Arun Subramaniyan 0001, Xiao Wu 0002, Makoto Yasuda, Satoru Miyoshi, Masaru Kawaminami, Reetuparna Das, Satish Narayanasamy, David T. Blaauw
IEEE Journal of Solid-State Circuits 56 ( 3 ) 824 - 833 2021
-
SeedEx: A Genome Sequencing Accelerator for Optimal Alignments in Subminimal Space.
Daichi Fujiki, Shunhao Wu, Nathan Ozog, Kush Goliya, David T. Blaauw, Satish Narayanasamy, Reetuparna Das
53rd Annual IEEE/ACM International Symposium on Microarchitecture(MICRO) 937 - 950 2020
-
A 2.46M reads/s Genome Sequencing Accelerator using a 625 Processing-Element Array.
Zhehong Wang, Tianjun Zhang, Daichi Fujiki, Arun Subramaniyan 0001, Xiao Wu 0002, Makoto Yasuda, Satoru Miyoshi, Masaru Kawaminami, Reetuparna Das, Satish Narayanasamy, David T. Blaauw
2020 IEEE Custom Integrated Circuits Conference(CICC) 1 - 4 2020
-
Near-memory data transformation for efficient sparse matrix multi-vector multiplication.
Daichi Fujiki, Niladrish Chatterjee, Donghyuk Lee, Mike O'Connor
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis(SC) 55 - 17 2019
-
Duality cache for data parallel acceleration.
Daichi Fujiki, Scott A. Mahlke, Reetuparna Das
Proceedings of the 46th International Symposium on Computer Architecture(ISCA) 397 - 410 2019
-
In-Memory Data Parallel Processor.
Daichi Fujiki, Scott A. Mahlke, Reetuparna Das
Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems(ASPLOS) 1 - 14 2018
-
AxNoC: Low-power Approximate Network-on-Chips using Critical-Path Isolation.
Akram Ben Ahmed, Daichi Fujiki, Hiroki Matsutani, Michihiro Koibuchi, Hideharu Amano
Twelfth IEEE/ACM International Symposium on Networks-on-Chip(NOCS) 6 - 8 2018
-
GenAx: A Genome Sequencing Accelerator.
Daichi Fujiki, Arun Subramaniyan 0001, Tianjun Zhang, Yu Zeng, Reetuparna Das, David T. Blaauw, Satish Narayanasamy
45th ACM/IEEE Annual International Symposium on Computer Architecture(ISCA) 69 - 82 2018
-
High-Bandwidth Low-Latency Approximate Interconnection Networks.
Daichi Fujiki, Kiyo Ishii, Ikki Fujiwara, Hiroki Matsutani, Hideharu Amano, Henri Casanova, Michihiro Koibuchi
2017 IEEE International Symposium on High Performance Computer Architecture(HPCA) 469 - 480 2017
-
In-memory Data Flow Processor.
Daichi Fujiki, Scott A. Mahlke, Reetuparna Das
26th International Conference on Parallel Architectures and Compilation Techniques(PACT) 375 - 375 2017
-
Randomizing Packet Memory Networks for Low-Latency Processor-Memory Communication.
Daichi Fujiki, Hiroki Matsutani, Michihiro Koibuchi, Hideharu Amano
24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing(PDP) 168 - 175 2016
Books
-
In-/Near-memory computing
Daichi Fujiki, Xiaowei Wang, Arun Subramaniyan, Reetuparna Das
Morgan & Claypool 2021 （ ISBN:9781636391885 ）
Research Projects
-
動的特徴量縮約可能な大規模モデル向けテンソル連想メモリアーキテクチャ
Grant number：24036702 2025 - 2030
科学技術振興機構 戦略的な研究開発の推進/国家戦略分野の若手研究者及び博士後期課程学生の育成事業（BOOST）/次世代AI人材育成プログラム(若手研究者支援)
藤木 大地
大量のデータを処理するAIは電力を多く消費します。本研究では、主な電力消費がメモリアクセスにあるという事実に注目し、特殊なメモリTAMによりAI内部のデータをコンパクト化することで、電力と処理速度を改善します。TAMは活性値を局所性・類似性に基づいて縮約し、要約します。本技術により、AIの性能を維持したまま大幅な省エネ化を実現し、様々なAIモデルやハードウェアに適用できる汎用性の高い最適化技術の開発を目指します。
-
メモリ駆動形DBシステムによるデータ処理基盤強化
Grant number：JPMJPR22P7 2022.10 - 2026.3
JST さきがけ
Authorship：Principal investigator
-
Multi-Layer In-Memory Computing and Its Application for GNNs
Grant number：22K21284 2022.8 - 2024.3
Japan Society for the Promotion of Science Grants-in-Aid for Scientific Research Grant-in-Aid for Research Activity Start-up
Grant amount：\2860000 （ Direct Cost: \2200000 、 Indirect Cost：\660000 ）
-
メモリ駆動形DBシステムによるデータ処理基盤強化
Grant number：22704088 2022 - 2025
科学技術振興機構 戦略的な研究開発の推進/戦略的創造研究推進事業/さきがけ
藤木 大地
本研究では、広く関連DBで使用されているB木の読み取り性能と、NoSQL/NewSQL等で使用されているLSM木の更新性能の両立をインメモリ計算IMCにより達成します。さらに、全エントリに対する準同型暗号演算が前提となっている完全秘匿型データベースについて、IMCにより静的データ近傍のメモリ資源を計算に転用し、データ移動を抑えながら超並列演算を行うことで、計算時間を低減させます。