Sciweavers

76 search results - page 7 / 16
» isca 2000
Sort
View
ISCA
2000
IEEE
92views Hardware» more  ISCA 2000»
15 years 2 months ago
Trace preconstruction
Trace caches enable high bandwidth, low latency instruction supply, but have a high miss penalty and relatively large working sets. Consequently, their performance may suffer due ...
Quinn Jacobson, James E. Smith
ISCA
2000
IEEE
78views Hardware» more  ISCA 2000»
15 years 1 months ago
Vector instruction set support for conditional operations
Vector instruction sets are receiving renewed interest because of their applicability to multimedia. Current multimedia instruction sets use short vectors with SIMD implementation...
James E. Smith, Greg Faanes, Rabin A. Sugumar
ISCA
2000
IEEE
111views Hardware» more  ISCA 2000»
15 years 2 months ago
Understanding the backward slices of performance degrading instructions
For many applications, branch mispredictions and cache misses limit a processor’s performance to a level well below its peak instruction throughput. A small fraction of static i...
Craig B. Zilles, Gurindar S. Sohi
ISCA
2000
IEEE
81views Hardware» more  ISCA 2000»
15 years 2 months ago
Clock rate versus IPC: the end of the road for conventional microarchitectures
The doubling of microprocessor performance every three years has been the result of two factors: more transistors per chip and superlinear scaling of the processor clock with tech...
Vikas Agarwal, M. S. Hrishikesh, Stephen W. Keckle...
ISCA
2000
IEEE
134views Hardware» more  ISCA 2000»
15 years 2 months ago
Architectural support for scalable speculative parallelization in shared-memory multiprocessors
Speculative parallelization aggressively executes in parallel codes that cannot be fully parallelized by the compiler. Past proposals of hardware schemes have mostly focused on si...
Marcelo H. Cintra, José F. Martínez,...