multilevel cache
Recently Published Documents


TOTAL DOCUMENTS

24
(FIVE YEARS 1)

H-INDEX

3
(FIVE YEARS 0)

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Changpei Qiu ◽  
Xin’an Wang ◽  
Tianxia Zhao ◽  
Qiuping Li ◽  
Bo Wang ◽  
...  

In this paper, an FPGA-based convolutional neural network coprocessor is proposed. The coprocessor has a 1D convolutional computation unit PE in row stationary (RS) streaming mode and a 3D convolutional computation unit PE chain in pulsating array structure. The coprocessor can flexibly control the number of PE array openings according to the number of output channels of the convolutional layer. In this paper, we design a storage system with multilevel cache, and the global cache uses multiple broadcasts to distribute data to local caches and propose an image segmentation method that is compatible with the hardware architecture. The proposed coprocessor implements the convolutional and pooling layers of the VGG16 neural network model, in which the activation value, weight value, and bias value are quantized using 16-bit fixed-point quantization, with a peak computational performance of 316.0 GOP/s and an average computational performance of 62.54 GOP/s at a clock frequency of 200 MHz and a power consumption of about 9.25 W.





2019 ◽  
Vol 9 (1) ◽  
pp. 22
Author(s):  
Bakhtiar Kasi ◽  
Mumraiz Kasi ◽  
Riaz UlAmin


Author(s):  
Muhammad Putra Pamungkas ◽  
Septi Andi Ekawibowo ◽  
Nana Rachmana Syambas


2019 ◽  
Vol 4 (1) ◽  
pp. 109
Author(s):  
Andri Ulus Rahayu

Performa komputer dari generasi ke generasi mengalami peningkatan yang cukup pesat, terutama dalam hal kecepatan pemrosesan data. Jika kita amati, kecepatan komputer dalam melakukan pemrosesan data merupakan arah dari  perkembangan generasi komputer. Kecepatan pemrosesan data ini sangat dipengaruhi oleh average access time pada cache prosesor. Tujuan penelitian ini adalah untuk membandingkan performa dan memberikan gambaran average access time pada multilevel cache proseesor komputer. Untuk mendapatkan perbandingan dan gambaran mengenai cara menghitung average access time ini, digunakan dua buah prosesor sebagai sampel yaitu Intel Core I7 2600K dan Phenom II X6 1100T. Untuk membandingkan average access time dari kedua prosesor tersebut, diperlukan dua indikator yaitu access time dan hit rate. Dari  hasil  analisis  yang  dilakukan,  dapat disimpulkan  bahwa dari segi average access time, prosesor Phenom X6 1100T memiliki performa lebih baik jika dibandingkan dengan prosesor  Intel Core I7 2600K.



2019 ◽  
Vol 13 (4) ◽  
pp. 850-863 ◽  
Author(s):  
Xiaodong Meng ◽  
Chentao Wu ◽  
Minyi Guo ◽  
Long Zheng ◽  
Jingyu Zhang




2017 ◽  
Vol 32 (2) ◽  
pp. 312-328
Author(s):  
Xiao-Dong Meng ◽  
Chen-Tao Wu ◽  
Min-Yi Guo ◽  
Jie Li ◽  
Xiao-Yao Liang ◽  
...  


2016 ◽  
Vol 3 (2) ◽  
pp. 11-22
Author(s):  
Shenchen Ruan ◽  
Haixia Wang ◽  
Dongsheng Wang


Sign in / Sign up

Export Citation Format

Share Document