A Novel Two-Level Instruction Issue Window Based on VLIW Architecture

Abstract:

Instruction compression technique overcomes the drawbacks of traditional VLIW architectures with low density in the instruction cache. However, the separated long instruction word was arranged into two cache line. It comes to be a bottleneck problem for VLIW architecture processor performance because these split long instruction word can not be fetched and issued simultaneously. A novel two-level instruction issue window mechanism is proposed in this paper. It solves the instruction fetch and issue problem in separating instruction words. It provides more effective and continuous instruction flow, and stores one iteration of the loop body to support software pipeline technique, which improves VLIW DSP processor performance effectively. Proposed machanism was synthesized to evaluate its overall costs, and the performance speedup result for DSP/IMG library bencharks using the cycle accurate simulator are presented.

• Periodical: Advanced Materials Research (Volumes 317-319)
• Pages: 146-149
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.317-319.146
• Online since: August 2011
• Authors: Hui Yang, Shu Ming Chen, Tie Bin Wu
• Keywords: Instruction Compression, Loop Buffer, Software Pipeline, Split Execute Packet, Two-Level Instruction Issue Window

References

[1] T.M. Conte, S. Banerjia, S.Y. Larin, Instruction fetch mechanisms for VLIW architectures with compressed encodings, Proceedings of the 29th Annual IEEE/ACM International Symposium on, Paris, 1996, pp.201-211.

DOI: 10.1109/micro.1996.566462

[2] T. Todd, E.S. Hahn, S. Dineel, Compilation strategies for reducing code size on a VLIW processor with variable length instructions, HiPEAC'08 Proceedings of the 3rd international conference on High performance embedded architectures and compilers, 2008, pp.147-160.

DOI: 10.1007/978-3-540-77560-7_11

[3] J.C. Chiu Y.L. Chou T.L. Yeh, Designs of the basic block reassembling Instruction Stream Buffer for X86 ISA[C], Proceedings of the 13th Computer Systems Architecture Conference, 2008, Asia-Pacific, 2008, pp.1-8.

DOI: 10.1109/apcsac.2008.4625434

[4] J.C. Chiu, K.M. Yang, A Novel instruction stream buffer for VLIW architectures, Computers & Electrical Engineering, 2010, 36(1) 190-198.

DOI: 10.1016/j.compeleceng.2009.08.006

[5] C. Panis, H. Grunbacher, J. Nurmi, A scalable instruction buffer and align unit for xDSPcore. IEEE J Solid-State Circuits, Villach, 2004,39(7) 1094-1110.

DOI: 10.1109/jssc.2004.829411

[6] A. Gordon Ross, S. Cotterell, F. Valid, Exploiting Fixed programs in Embeded Systems:A Loop Cache Example. In Computer Architecture Letters. 2002,1(1).

DOI: 10.1109/l-ca.2002.4

[7] TMS320C64x+ DSP Image/Video Processing Library (v2.0) Programmer's Reference Texas Instruments Inc (2008).