Sciweavers

ICPP
2002
IEEE

Out-of-Order Instruction Fetch Using Multiple Sequencers

13 years 8 months ago
Out-of-Order Instruction Fetch Using Multiple Sequencers
Conventional instruction fetch mechanisms fetch contiguous blocks of instructions in each cycle. They are difficult to scale since taken branches make it hard to increase the size of these blocks beyond eight instructions. Trace caches have been proposed as a solution to this problem, but they use cache space inefficiently. We show that fetching large blocks of contiguous instructions, or wide fetch, is inefficient for modern out-oforder processors. Instead of the usual approach of fetching large blocks of instructions from a single point in the program, we propose a high-bandwidth fetch mechanism that fetches small blocks of instructions from multiple points in a program. In this paper, we demonstrate that it is possible to achieve high-bandwidth fetch by using multiple narrow fetch units operating in parallel. Our mechanism performs as well as a trace cache, does not waste cache space, is more resilient to instruction cache misses, and is a natural fit for techniques that requir...
Paramjit S. Oberoi, Gurindar S. Sohi
Added 14 Jul 2010
Updated 14 Jul 2010
Type Conference
Year 2002
Where ICPP
Authors Paramjit S. Oberoi, Gurindar S. Sohi
Comments (0)