150% while generating a median code size and compile-time increase of not more than 25%. Our results indicate that fast-path unrolling of non-counted loops can be used in practice to increase the performance of Java applications.
150% of non-counted loop speed or 150% of total application speed? i suspect the first. i wonder how prevalent those kind of loops are ...
> We evaluated our implementation on top of the GraalVM by running and analyzing a set of industry-standard benchmarks.
for the Java DaCapo suite it looks like it didn't do much except making the variability of the jython runtime more unpredictable.