完整後設資料紀錄
DC 欄位語言
dc.contributor.authorCheng, SKen_US
dc.contributor.authorShiu, RMen_US
dc.contributor.authorShann, JJJen_US
dc.date.accessioned2014-12-08T15:27:20Z-
dc.date.available2014-12-08T15:27:20Z-
dc.date.issued1998en_US
dc.identifier.isbn0-8186-8603-0en_US
dc.identifier.urihttp://hdl.handle.net/11536/19596-
dc.description.abstractIn the new generation of x86 microprocessors, superscalar techniques are used to achieve higher performance by executing multiple instructions in parallel. For compatibility and higher execution parallelism, the decoding units of these microprocessors translate the x86 instructions into primitive operations. These microprocessors translate x86 instructions by the similar rca? of merging address generating into load/store operations. In this paper, we develop a nerv translating strategy of translating isolated address generation operations. Simulation results show that, in high issue rate decoding units, translating isolated address generation operations improves the performance for 20% to 25%. Besides, we find that enhancing the store buffer with the ability of snooping result buses is important for high issue rate decoding units. Furthermore, considering the tradeoff of the hardware cast and performance, we examine the decoding rules to design a decoding unit. According to the simulation results,,ve suggest a good decoding rule suitable for current commercial programs.en_US
dc.language.isoen_USen_US
dc.subjectsuperscalar processoren_US
dc.subjectinstruction decodingen_US
dc.subjectx86 microprocessoren_US
dc.subjectload/store operationen_US
dc.titleDecoding unit with high issue rate for X86 superscalar microprocessorsen_US
dc.typeProceedings Paperen_US
dc.identifier.journal1998 INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGSen_US
dc.citation.spage488en_US
dc.citation.epage495en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000078318400060-
顯示於類別:會議論文