Paper #10 Authors: Spadini et al. (Francesco Spadini, Brian Fahs, Sanjay Patel, Steven S. Lumetta) Title:Improving Quasi-Dynamic Schedules through Region Slip Reviewer name Adrian Pop, adrpo@ida.liu.se Short summary The paper is addressing the generation of improved dynamically generated static schedules through a new hardware improvement that they call region slip. Region slip consists of an hardware mechanism that dispatches parallel instructions in one region to migrate a previous region. In this way the available parallelism does not become lower towards the end of a region. The main contributions Simple quasi-dynamic hardware mechanism as opposed to much more hardware for a fully dynamic scheduler. Merits and weaknesses Their technique is simulated within a hardware framework and they provide performance analysis using some standard benchmarks. Numerical rating in the interval from 0 (very bad) to 10 (excellent) * Significance: 7 * Originality: 9 * Interest to a journal on programming languages and compiler technology: 3 * Quality of experimental evaluation: 7 * Overall organization: 8 * Presentation (language and style): 7 * Length appropriate: 8 * References appropriate: 8 * Overall evaluation (0..10): 8 * Recommendation: Accept * Your confidence in your review (1=novice, 10=leading expert): 6 Comments to the authors In Conclusions, please explain that IPL is not Integer Linear Programming but Instruction Level Parallelism Suggestions for improvement (for the authors) None.