SEWD:A Cache Architecture to Speed up the Misaligned Instruction Prefetch
スポンサーリンク
概要
- 論文の詳細を見る
In microprocessors, reducing the cache access delay and the number of pipeline stall is critical to improve the system performance. In this paper, we propose a Separated Word-line Decoding (SEWD) cache to overcome the pipeline stall caused by the misaligned multi-words data or instruction prefetches which are placed over two cache lines. SEWD cache makes it possible to perform misaligned prefetch as well as aligned prefetch in one clock cycle. This feature is invaluable because the branch target addresses are very often misaligned (Percentage of misalignment in the cache is 8 to 13% for 16-byte caches). 8 K byte SEWD cache chip was implemented in 0.8 μm DLM CMOS process. It consists of 489,000 transistors on a die size of 0.853×0.827 cm^2.
- 社団法人電子情報通信学会の論文
- 1997-07-25
著者
-
Park In-cheol
Department Of Eecs Kaist
-
Kyung Chong-min
Department Of Eecs Kaist Taejon
-
Yim Joon-seo
Department Of Electrical Engineering Korea Advanced Institute Of Science And Technology
関連論文
- An Area-Efficient and Fully Synthesizable Bluetooth Baseband Module for Wireless Communication(Integrated Electronics)
- Improving Dictionary-Based Code Compression in VLIW Architectures (Special Section on VLSI Design and CAD Algorithms)
- Parallel Decoding of Context-Based Adaptive Binary Arithmetic Codes Based on Most Probable Symbol Prediction(Image Processing and Video Processing)
- Loop and Address Code Optimization for Digital Signal Processors
- A Hierarchical Circuit Clustering Algorithm with Stable Performance
- CLASSIC:An O(n^2)-Heuristic Algorithm for Microcode Bit Optimization Based on Incompleteness Relations
- Issues on the Interface Synthesis between Intellectual Properties Operating at Different Clock Frequencies
- A New Single-Clock Flip-Flop for Half-Swing Clocking (Special Section on VLSI Design and CAD Algorithms)
- Path-Classified Trace Cache for Improving Hit Ratio in Wide-Issue Processors
- SEWD:A Cache Architecture to Speed up the Misaligned Instruction Prefetch
- An Efficient Routing Algorithm for Symmetrical FPGAs Using Reliable Cost Metrics(VLSI Design Technology and CAD)(Regular Section)
- A Supplementary Scheme for Reducing Cache Access Time