Jim, >> Fixed but I kept the local variable as it has a measurable impact (760ms >> vs 800ms) with a medium complex map (135 000 shapes). > > > Please confirm that I am reading this correctly. > > You reverted the 2 variable loads at lines 1258,1259 in Renderer.java and made no other changes and saw a 5% performance drop on the total runtime of a benchmark that renders 135,000 shapes?
I only run the benchmark once on each variant and results have some variability even MapBench has several warmup phases... However, each map is rendered by 4 threads for 25 iterations on this test = 3 minutes at 100% cpu on my laptop. I have the impression it is a bit slower; I will take time to perform 3 runs per variant and compare the best of 3 to have a better estimate. Laurent
