JISE

[1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12]

Journal of Information Science and Engineering, Vol. 18 No. 6, pp. 1027-1036

Evaluating Influence of Compiler Optimizations on Data Speculation

Toshinori Sato, Kiichi Sugitani, Akihiko Hamano
and Itsujiro Arita^*
^*Department of Artificial Intelligence
⁺Center for Microelectronic Systems
Kyushu Institute of Technology
680-4 Kawazu, Iizuka, 820-8502 Japan
⁺⁺Fujitsu Kyushu Digital Technology Ltd.
Fukuoka, Japan
^**HAW International Inc.
Iizuka, Japan

The practice of using speculation in resolving data dependences based on value prediction has been studied as a means of extracting more instruction level parallelism. There are many studies on value prediction mechanisms with high predictabilities. However, to the best of our knowledge, the influence of compiler optimizations on value prediction has not been investigated. In this paper, we evaluate the efficiency of value prediction on several binaries, which are compiled with different optimization levels. Detailed simulations reveal that value prediction is still effective for highly optimized binaries.

Keywords: instruction level parallelism, data speculation, value prediction, optimization levels, high-performance compilers

Retrieve PDF document (JISE_200206_10.pdf)