Most significant changes this week came in response to regressions discussed in last week's triage report. Curious readers may be interested in #77058, in which the removal of a single field from a struct caused a 25% decrease in wall-times for one seemingly unrelated benchmark, or #76986, an ABI change that should be a pretty clear win but seems to have mixed results.
Triage done by @ecstaticmorse. Revision range: b01326ab033e41986d4a5c8b96ce4f40f3b38e30..6369a98ebdee8ce01510f5d4307ddb771c8cb0e5
0 Regressions, 1 Improvements, 3 Mixed
0 of them in rollups
#77041 perf: move cold path of process_obligations
into a separate function
full
builds of inflate-check
)#77006 Cache eval_to_allocation_raw
on disk
incr-unchanged
builds of ctfe-stress-4-check
)incr-full
builds of ctfe-stress-4-check
),incr-full
builds of ctfe-stress-4
also have significantly increased max-rss
.#76913 Fixing the performance regression of #76244
full
builds of unicode_normalization-check
)incr-unchanged
builds of ctfe-stress-4-check
)unicode-normalization
.#76986 Return values up to 128 bits in registers
full
builds of deeply-nested-debug
)full
builds of piston-image-opt
)task-clock
measurements.