Predicting multiple streams per cycle
The next stream predictor is an accurate branch predictor that provides stream level sequencing. Every stream prediction contains a full stream of instructions, that is, a sequence of instructions from the target of a taken branch to the next taken branch, potentially containing multiple basic block...
| Autores: | , , |
|---|---|
| Tipo de recurso: | informe técnico |
| Fecha de publicación: | 2005 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/106641 |
| Acceso en línea: | https://hdl.handle.net/2117/106641 |
| Access Level: | acceso abierto |
| Palabra clave: | Microprocessors Parallel processing (Electronic computers) Microprocessadors Processament en paral·lel (Ordinadors) Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors |
| Sumario: | The next stream predictor is an accurate branch predictor that provides stream level sequencing. Every stream prediction contains a full stream of instructions, that is, a sequence of instructions from the target of a taken branch to the next taken branch, potentially containing multiple basic blocks. The long size of instruction streams makes it possible for the stream predictor to provide high fetch bandwidth and to tolerate the prediction table access latency. Therefore, an excellent way for improving the behavior of the next stream predictor is to enlarge instruction streams. In this paper, we provide a comprehensive analysis of dynamic instruction streams, showing that focusing on particular kinds of stream is not a good strategy due to Amdahl's law. Consequently, we propose the multiple stream predictor, a novel mechanism that deals with all kinds of streams by combining single streams into long virtual streams. We show that our multiple stream predictor is able to tolerate the prediction table access latency without requiring the complexity caused by additional hardware mechanisms like prediction overriding, also reducing the overall branch predictor energy consumption. |
|---|