Citations and the h-index are parameters to evaluate a researcher’s performance.Several platforms are used to analyse these parameters.However,all of them differ in their methods.As a consequence,an author can appear...Citations and the h-index are parameters to evaluate a researcher’s performance.Several platforms are used to analyse these parameters.However,all of them differ in their methods.As a consequence,an author can appear with several different h-index values and with a varying number of publications and citations,which can differ by more than a hundred per cent from one platform to another.This work investigates the differences in values obtained using the publication data of the author of this paper.展开更多
Data value prediction has been widely accepted as an effective mechanism to break data hazards for high performance processor design. Several works have reported promising performance potential. However, there is hard...Data value prediction has been widely accepted as an effective mechanism to break data hazards for high performance processor design. Several works have reported promising performance potential. However, there is hardly enough information that is presented in a clear way about performance comparison of these prediction mechanisms. This paper investigates the performance impact of four previously proposed value predictors, namely last value predictor, stride value predictor, two-level value predictor and hybrid （stride-t-two-level） predictor. The impact of misprediction penalty, which has been frequently ignored, is discussed in detail. Several other implementation issues, including instruction window size, issue width and branch predictor are also addressed and simulated. Simulation results indicate that data value predictors act differently under different configurations. In some cases, simpler schemes may be more beneficial than complicated ones. In some particular cases, value prediction may have negative impact on performance.展开更多
文摘Citations and the h-index are parameters to evaluate a researcher’s performance.Several platforms are used to analyse these parameters.However,all of them differ in their methods.As a consequence,an author can appear with several different h-index values and with a varying number of publications and citations,which can differ by more than a hundred per cent from one platform to another.This work investigates the differences in values obtained using the publication data of the author of this paper.
文摘Data value prediction has been widely accepted as an effective mechanism to break data hazards for high performance processor design. Several works have reported promising performance potential. However, there is hardly enough information that is presented in a clear way about performance comparison of these prediction mechanisms. This paper investigates the performance impact of four previously proposed value predictors, namely last value predictor, stride value predictor, two-level value predictor and hybrid （stride-t-two-level） predictor. The impact of misprediction penalty, which has been frequently ignored, is discussed in detail. Several other implementation issues, including instruction window size, issue width and branch predictor are also addressed and simulated. Simulation results indicate that data value predictors act differently under different configurations. In some cases, simpler schemes may be more beneficial than complicated ones. In some particular cases, value prediction may have negative impact on performance.
