Kilo-instruction processors: overcoming the memory wall

Historically, advances in integrated circuit technology have driven improvements in processor microarchitecture and led to todays microprocessors with sophisticated pipelines operating at very high clock frequencies. However, performance improvements achievable by high-frequency microprocessors have...

Descripción completa

Detalles Bibliográficos
Autores: Cristal Kestelman, Adrián|||0000-0003-1277-9296, Santana Jaria, Oliverio J., Cazorla, Francisco, Galluzzi, Marco, Ramirez Garcia, Tanausú, Pericas, Miquel, Valero Cortés, Mateo|||0000-0003-2917-2482
Tipo de recurso: artículo
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:2117/103087
Acceso en línea:https://hdl.handle.net/2117/103087
https://dx.doi.org/10.1109/MM.2005.53
Access Level:acceso abierto
Palabra clave:Cache memory
Parallel processing (Electronic computers)
Microprocessors
Performance evaluation
Pipeline processing
Instruction sets
Cache storage
Memòria cau
Processament en paral·lel (Ordinadors)
Microprocessadors
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
Descripción
Sumario:Historically, advances in integrated circuit technology have driven improvements in processor microarchitecture and led to todays microprocessors with sophisticated pipelines operating at very high clock frequencies. However, performance improvements achievable by high-frequency microprocessors have become seriously limited by main-memory access latencies because main-memory speeds have improved at a much slower pace than microprocessor speeds. Its crucial to deal with this performance disparity, commonly known as the memory wall, to enable future high-frequency microprocessors to achieve their performance potential. To overcome the memory wall, we propose kilo-instruction processors-superscalar processors that can maintain a thousand or more simultaneous in-flight instructions. Doing so means designing key hardware structures so that the processor can satisfy the high resource requirements without significantly decreasing processor efficiency or increasing energy consumption.