Previous timing analysis methods have assumed that the worst-case instruction execution time necessarily corresponds to the worst-case behavior. We show that this assumption is wr...
We introduce techniques to support efficient non-atomic execution of very long traces on a new binary translation based, x86-64 compatible VLIW microprocessor. Incrementally comm...
An asynchronous superscalar architecture is presented based on a novel architectural feature called instruction compounding. This enables efficient dynamic scheduling and forwardi...
The energy usage of computer systems is becoming important, especially for portablebattery-operated applications and embedded systems. A significant reduction in the energy consum...
Gangadhar Konduri, James Goodman, Anantha Chandrak...
Existing schemes for cache energy optimization incorporate a limited degree of dynamic associativity: either direct mapped or full available associativity (say 4-way). In this pap...