Modern processors rely on memory dependence prediction to execute load instructions as early as possible, speculating that they are not dependent on an earlier, unissued store. To...
Franziska Roesner, Doug Burger, Stephen W. Keckler
Current data cache organizations fail to deliver high performance in scalar processors for many vector applications. There are two main reasons for this loss of performance: the u...
Traditional vector architectures have shown to be very effective for regular codes where the compiler can detect data-level parallelism. However, this SIMD parallelism is also pre...
In order to achieve high performance, contemporary microprocessors must effectively process the four major instruction types: ALU, branch, load, and store instructions. This paper...
Bryan Black, Brian Mueller, Stephanie Postal, Ryan...
In this paper, we propose a fully automatic dynamic scratchpad memory (SPM) management technique for instructions. Our technique loads required code segments into the SPM on deman...
Bernhard Egger, Chihun Kim, Choonki Jang, Yoonsung...