Browse > Article
http://dx.doi.org/10.7471/ikeee.2015.19.3.455

Design of a Dispatch Unit & Operand Selection Unit for Improving the SIMT Based GP-GPU Instruction Performance  

Kwak, Jae Chang (Dept. of Computer Science, Seokyeong University)
Publication Information
Journal of IKEEE / v.19, no.3, 2015 , pp. 455-459 More about this Journal
Abstract
This paper proposes a dispatch unit of GP-GPU with SIMT architecture to support the acceleration of general-purpose operation as well as graphics processing. If all the information of an operand used instructions issued from the warp scheduler is decoded, an unnecessary operand load occurs, resulting in register loads. To resolve this problem, this paper proposes a method that can reduce the operand load and the load on the resister by decoding only the information of the operand using a pre-decoding method. The operand information from the dispatch unit is passed to the operand selection unit with preventing register bank collisions. Thus the overall performance are improved. In the simulation test, the total clock cycles required by processing 10,000 arbitrary instructions issued from the wrap scheduler using ModelSim SE 10.0b are measured. It shows that the application of the dispatch unit equipped with the pre-decoding function proposed in this paper can make an improvement of about 12% in processing performance compared to the conventional method.
Keywords
dispatch unit; pre-decoding; operand; register; operand sselection unit;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Lashgar. A, Baniasadi. A, Khonsari. A, "Dynamic warp resizing: Analysis and benefits in high-performance simt," Computer Design, ICCD, 2012 IEEE 30th International Conference, pp. 502-503, 2012.
2 Xue Yang, Lixin Yu, Wei Zhuang, Yingpan Wu, Li Hao, "Design of instruction decode logic for dual-issue superscalar processor based on leon2," Consumer Electronics, Berlin (ICCE-Berlin), 2013. ICCEBerlin 2013. IEEE Third International Conference, pp. 1-4, September 2013.
3 Sohl, J., Jian Wang Karlsson, A., Liu, D., "Conflict-free data access for multi-bank memory architectures using padding," High Performance Computing (HiPC), 2013 20th International Conference, pp. 425-432, 2013.
4 Qi Zhang, Li, Qing, Yunyang Dai, Kuo, C.-C.J., "Reducing memory bank conflict for embedded multimedia systems," Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference, pp. 471-474 Vol.1, June 2004.
5 Xilinx, "VC707 User Guide," http://www.xilinx.com