Learning to Superoptimize real-world programs

Re:Learning to Superoptimize real-world programs by mach1ne on Thursday September 30, 2021 @03:14PM (#28710118)

I don't understand the wording: "Our method, SILO, superoptimizes programs an expected 6.2% of our test set when compared with the gcc version 10.3 compiler's aggressive optimization level -O3."

Does that mean that the runtime is only 6.2% of the runtime after gcc optimization, or that there was a 6.2% reduction in runtime compared to gcc optimization?

[ Parent | on HN ]

Re:Learning to Superoptimize real-world programs by O_nlogn on Thursday September 30, 2021 @05:47PM (#28711745)

Neither, they found that 6.2% of the programs that SILO generated performed better on their benchmarks (based on a sum of the expected and actual execution latency of the assembly on some test data) than the gcc -O3 baseline (i.e. 93.8% of the programs SILO generated did not perform better, or were not correct). AFAIK they don't state how much better the super optimized programs were.

[ Parent | on HN ]