Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Hardware-level data layout approach to mitigate the memory row conflicts on FPGA-based CNN accelerators

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 4 (2026) · hlm. 3280–3290

DOI
10.11591/eei.v15i4.11386
ISSN
2089-3191, 2302-9285
Terbit
2026-08-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Memory row conflicts (MRCs) continue to be a major bottleneck that results in higher latency, ineffective double data rate (DDR) usage, and decreased effective bandwidth in field-programmable gate array (FPGA-based) convolutional neural network (CNN) accelerators. The majority of current effort focuses on computational optimization, frequently ignoring inefficient memory access. In order to reduce memory reference codes (MRCs), this research suggests a hardware-level data layout technique using a memory-centric accelerator architecture. In order to improve hit rates and row buffer locality, the architecture incorporates a dynamic cursor-based address mapping method that adjusts to different feature map sizes across CNN layers and a dual-DDR setup for concurrent data access. The experimental results on VGG16, YOLOv2, and AlexNet show an 18% reduction in MRCs, a 40% increase in throughput, and a 23% decrease in latency compared to state-of-the-art techniques. The design uses a Xilinx Kintex-7 FPGA with low power usage of 1.52 W. The suggested method improves memory performance in FPGA-based CNN accelerators in a scalable and hardware-efficient manner without requiring a large computational burden.

Kata kunci

Jaringan kolaborasi para penulis

18 penulis · 46 tautan kepenulisan bersama · 21 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Visvesvaraya Technological University
  • Dayananda Sagar College of Engineering
  • B.M.S. College of Engineering
  • Don Bosco Institute of Technology
  • RV University
  • R.V. College of Engineering
  • PES University
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Karanam Sunil KumarR.V. College of Engineering2
Vijayashree R. BudyalAfiliasi tidak diketahui1
Ambuja KrishnappaB.M.S. College of Engineering1
Gauri Sameer RapatePES University1
Sarala Duggonahalli VeereshB.M.S. College of Engineering1
Lakshminarayana MunirathnamRamaiah Institute of Technology1
Suraksha PrakashAfiliasi tidak diketahui1
Reshma ShafiDayananda Sagar College of Engineering1
M. LakshminarayanaVisvesvaraya Technological University1
Somu ParandeAfiliasi tidak diketahui1
Vani Bengaluru PurushothamaVisvesvaraya Technological University1
Yogeesh Ambalagere ChandrashekaraiahVisvesvaraya Technological University1
Ramya Mullur VaradhanayakaAfiliasi tidak diketahui1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Hardware-level data layout approach to mitigate the memory row conflicts on FPGA-based CNN accelerators</dc:title><dc:creator>S. Prasad</dc:creator><dc:creator>Suman Jayakumar</dc:creator><dc:creator>Bellary Kursheed</dc:creator><dc:creator>Aruna Mogarala Guruvaya</dc:creator><dc:creator>S Rashmi</dc:creator><dc:subject>data layout</dc:subject><dc:subject>memory-centric architecture</dc:subject><dc:subject>memory access efficiency</dc:subject><dc:subject>VGG16</dc:subject><dc:subject>YOLOv2</dc:subject><dc:subject>AlexNet</dc:subject><dc:description xml:lang="en">Memory row conflicts (MRCs) continue to be a major bottleneck that results in higher latency, ineffective double data rate (DDR) usage, and decreased effective bandwidth in field-programmable gate array (FPGA-based) convolutional neural network (CNN) accelerators. The majority of current effort focuses on computational optimization, frequently ignoring inefficient memory access. In order to reduce memory reference codes (MRCs), this research suggests a hardware-level data layout technique using a memory-centric accelerator architecture. In order to improve hit rates and row buffer locality, the architecture incorporates a dynamic cursor-based address mapping method that adjusts to different feature map sizes across CNN layers and a dual-DDR setup for concurrent data access. The experimental results on VGG16, YOLOv2, and AlexNet show an 18% reduction in MRCs, a 40% increase in throughput, and a 23% decrease in latency compared to state-of-the-art techniques. The design uses a Xilinx Kintex-7 FPGA with low power usage of 1.52 W. The suggested method improves memory performance in FPGA-based CNN accelerators in a scalable and hardware-efficient manner without requiring a large computational burden.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-08-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i4.11386</dc:identifier><dc:identifier>10.11591/eei.v15i4.11386</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 4 (2026); 3280-3290</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/11386/4890</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>