Odd results for mutator retired instructions for `biojava`

[k-sareen]

During performance evaluation, I've noticed that biojava has a very odd result for the number of retired instructions for the mutator. Every plan in the current MMTk (so GenImmix, Immix, MarkCompact, NoGC, and SemiSpace) retires 40% more instructions than GenCopy. This makes no sense as the fastpath and allocator for GenCopy is identical to the rest of the GCs (specially SemiSpace and GenImmix). If anything, we expect that the generational plans retire more instructions than other plans owing to the presence of a barrier.

biojava is also the only benchmark this occurs in. The odd results for the number of (mutator) retired instructions also translates into a decrease in mutator time for GenCopy.

Results

Note the ~40% increase in number of retired instructions for the rest of the plans in comparison to GenCopy.

Revisions used

mmtk-core: 3dbdd7ae + feature perf_counter mmtk-openjdk: 3cc0d71 openjdk: ca90b43f0f5

DaCapo Chopin: f480064

Benchmark results were gathered on an i9-9900K Coffee Lake machine.

[k-sareen]

Plotty link

https://squirrel.anu.edu.au/plotty/kunals/bench-test/#0|2022-05-11-gc-microarch-effects-shrew-2022-05-11-Wed-232638^2022-05-13-gc-microarch-effects-nogc-shrew-2022-05-13-Fri-161908^2022-05-13-gc-microarch-effects-gen-shrew-2022-05-13-Fri-234650&benchmark^build^invocation^iteration^mmtk_gc&LLC_MISSES.other^PERF_COUNT_HW_BRANCH_MISSES.other^PERF_COUNT_HW_CACHE_DTLB.MISS.other^PERF_COUNT_HW_CACHE_L1D.MISS.other^PERF_COUNT_HW_CPU_CYCLES.other^PERF_COUNT_HW_INSTRUCTIONS.other^time^time.other^time.stw&time.other+time.stw^1000*PERF_COUNT_HW_BRANCH_MISSES.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*LLC_MISSES.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*PERF_COUNT_HW_CACHE_L1D.MISS.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*PERF_COUNT_HW_CACHE_DTLB.MISS.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other|10&iteration^1^4&benchmark^2^xalan&benchmark^2^graphchi&benchmark^2^batik&benchmark^2^h2|20&1^invocation|70&mmtk_gc^mmtk_gc-microarch-effects|30&2&benchmark|41&Histogram%20(with%20CI)^mmtk_gc^benchmark&1000*LLC_MISSES.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*PERF_COUNT_HW_BRANCH_MISSES.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*PERF_COUNT_HW_CACHE_DTLB.MISS.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^1000*PERF_COUNT_HW_CACHE_L1D.MISS.other%20/%20PERF_COUNT_HW_INSTRUCTIONS.other^PERF_COUNT_HW_CPU_CYCLES.other^PERF_COUNT_HW_INSTRUCTIONS.other^time.other^time^time.stw