The process of empirical autotuning results in the generation of many code variants which are tested, found to be suboptimal, and discarded. By retaining annotated performance profiles of each variant tested over the course of many autotuning runs of the same code across different hardware environments and different input datasets, we can apply machine learning algorithms to generate classifier...

Automatic vectorization is critical to enhancing performance of compute-intensive programs on modern processors. However, there is much room for improvement over the auto-vectorization capabilities of current production compilers, through careful vector-code synthesis that utilizes a variety of loop transformations (e.g. unroll-and-jam, interchange, etc.). As the set of transformations consider...

In response to questions about the relative importance of different types capital flow for international competitiveness, we develop a structural vector auto-regressive model real exchange rate and flows. We reveal that innovations speculative sentiment cause changes in competitiveness. report speculation replaces effect equity, bond most interest effect. The results show is an important contri...

In the literature, there are few studies analyzing impacts of foreign direct investment and portfolio investments on house prices. We employed quarterly data for 20 EU countries over 2007-2013 period in order to examine separate prices post-financial crisis. The results Panel Vector Auto Regression indicate that negatively affects prices, positively Also, increase lead decrease both investment....

Centralized fiscal transfers to the provinces are principal means of reducing income inequalities in China. The coastal main transfer donors poorer provinces. We evaluate if equity objective sacrifices aggregate growth using four panel vector auto-regressions (PVARs) for geographical regions Chinese PVARs estimated centralized transfers, government spending, taxes and output from 1994 2018, whe...