[notnullorvoid]

Something I see many JS benchmarks struggle with is GC. Benchmarks run in tight loops with no GC in between, leading to results not representative of real world use. Rarely do they even run GC between the different test cases, so earlier cases build up GC pressure negatively impacting the later cases and invalidating all results.

[leeoniya]

yep, also thermal throttling.

had this discussion about GC pressure a bit ago: https://github.com/leeoniya/uDSV/issues/2