paper-with-me

Papers

FPGA-Based CNN Inference Accelerator Synthesized from Multi-Threaded C Software

2018-07-27 · Jin Hee Kim, Brett Grady, Ruolong Lian, John Brothers, Jason H. Anderson

A deep-learning inference accelerator is synthesized from a C-language software program parallelized with Pthreads. The software implementation uses the well-known producer/consumer model with parallel threads interconnected by FIFO queues. The LegUp high-level synthesis (HLS) tool synthesizes threads into parallel FPGA hardware, translating software parallelism into spatial parallelism. A complete system is generated where convolution, pooling and padding are realized in the synthesized accelerator, with remaining tasks executing on an embedded ARM processor. The accelerator incorporates reduced precision, and a novel approach for zero-weight-skipping in convolution. On a mid-sized Intel Arria 10 SoC FPGA, peak performance on VGG-16 is 138 effective GOPS.

📄 PDF Abstract BibTeX arXiv:1807.10695

Code (0)

등록된 구현이 없습니다.

Tasks

High-Level Synthesis

Similar Papers 제목 키워드 기반

A Compilation Flow for the Generation of CNN Inference Accelerators on FPGAs

2022-03-08 · Seung-Hun Chung, Tarek S. Abdelrahman

We present a compilation flow for the generation of CNN inference accelerators on FPGAs. The flow translates a frozen model into OpenCL kernels with the TVM compiler and uses the Intel OpenCL SDK to compile to an FPGA bi…

CPUHigh-Level Synthesis

In-RDBMS Hardware Acceleration of Advanced Analytics

2018-01-08 · Divya Mahajan, Joon Kyung Kim, Jacob Sacks, Adel Ardalan 외

The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions …

NeuroMAX: A High Throughput, Multi-Threaded, Log-Based Accelerator for Convolutional Neural Networks

2020-07-19 · Mahmood Azhar Qureshi, Arslan Munir

Convolutional neural networks (CNNs) require high throughput hardware accelerators for real time applications owing to their huge computational cost. Most traditional CNN accelerators rely on single core, linear processi…

Unity

Scaling up HBM Efficiency of Top-K SpMV for Approximate Embedding Similarity on FPGAs

2021-03-08 · Alberto Parravicini, Luca Giuseppe Cellamare, Marco Siracusa, Marco Domenico Santambrogio

Top-K SpMV is a key component of similarity-search on sparse embeddings. This sparse workload does not perform well on general-purpose NUMA systems that employ traditional caching strategies. Instead, modern FPGA acceler…

CPUGPU

Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA

2026-06-09 · Vinamra Sharma, Xingjian Fu, Jude Haris, José Cano arxiv

Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that involves architectural parameters, data flow strategies, and memory hierarc…