• Title/Summary/Keyword: 소프트웨어-하드웨어 공동최적화

Search Result 3, Processing Time 0.016 seconds

A Software-Hardware Co-Optimized Sense Amplifier for 2T1C Cell-based DRAM In-Memory-Computing (2T1C 셀 기반 DRAM 인메모리 컴퓨팅을 위한 소프트웨어-하드웨어 공동 체적화 센스 증폭기)

  • Hoi-Jun Yoo;Sunjoo Whang;Soyeon Um;Sangwoo Ha
    • Transactions on Semiconductor Engineering
    • /
    • v.2 no.4
    • /
    • pp.8-12
    • /
    • 2024
  • This paper presents a software-hardware (SW-HW) co-optimization approach for DRAM inmemory computing, significantly reducing sense amplifier read power in 2T1C cell systems. By transitioning from 2's complement to signed magnitude representation, data '0' prevalence increased from 52% to 73%, achieving a 13% reduction in read power. A novel sense amplifier design incorporating a variable reference voltage contributed a further 15% power reduction. This co-optimization strategy resulted in a total read power decrease of 26% compared to the baseline, demonstrating substantial improvements in energy efficiency for memory-intensive computing environments.

Hardware and Software Co-Design Platform for Energy-Efficient FPGA Accelerator Design (에너지 효율적인 FPGA 가속기 설계를 위한 하드웨어 및 소프트웨어 공동 설계 플랫폼)

  • Lee, Dongkyu;Park, Daejin
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.25 no.1
    • /
    • pp.20-26
    • /
    • 2021
  • Recent systems contain hardware and software components together for faster execution speed and less power consumption. In conventional hardware and software co-design, the ratio of software and hardware was divided by the designer's empirical knowledge. To find optimal results, designers iteratively reconfigure accelerators and applications and simulate it. Simulating iteratively while making design change is time-consuming. In this paper, we propose a hardware and software co-design platform for energy-efficient FPGA accelerator design. The proposed platform makes it easy for designers to find an appropriate hardware ratio by automatically generating application program code and hardware code by parameterizing the components of the accelerator. The co-design platform based on the Vitis unified software platform runs on a server with Xilinx Alveo U200 FPGA card. As a result of optimizing the multiplication accelerator for two matrices with 1000 rows, execution time was reduced by 90.7% and power consumption was reduced by 56.3%.

An HEVC intra encoder sharing DCT with RDO for a low complex hardware (하드웨어 복잡도를 줄이기 위한 RDO내 DCT 공유구조의 HEVC 화면내 예측부호화기)

  • Lee, Sukho;Jang, Juneyoung;Byun, Kyungjun;Eum, Nakwoong
    • Smart Media Journal
    • /
    • v.3 no.4
    • /
    • pp.16-21
    • /
    • 2014
  • HEVC is the latest joint video coding standard with ITU-T SG16 WP and ISO/IEC JTC1/SC29/WG11. Its coding efficiency is about two times compared to H.264 high profile. Intra prediction has 35 directional modes including dc and planer. However an accurate mode decision on lots of modes with SSE is too costly to implement it with hardware. The key idea of this paper is a DCT shared architecture to reduce the complexity of HEVC intra encoder. It is to use same DCT block to quantize as well as to calculate SSE in RDO. The proposed intra encoder uses two step mode decision to lighten complexity with simplified RDO blocks and shares the transform resources. Its BD-rate increase is negligible at 20% on hardware aspect and the operating clock frequency is 300MHz@60fps on FHD ($1920{\times}1080$) image.