From 24bf6ff4e08f88df0b6c01ef87aa384276636901 Mon Sep 17 00:00:00 2001 From: Snehasish Kumar Date: Thu, 8 Oct 2020 17:36:13 -0700 Subject: [llvm] Update default cutoff threshold for machine function splitter. Based on internal testing at Google we found that setting the profile summary cutoff threshold to 999950 yields the best results in terms of itlb and icache metrics (as observed on Intel CPUs). *default* = Split out code if no profile count available for block *size-%* = The fraction of bytes split out of .text and .text.hot *itlb* = Misses per kilo instructions (MPKI) for itlb *icache* = Misses per kilo instructions (MPKI) for L1 icache Search1 | cutoff | size-% | itlb | icache | |---------|---------|-----------|---------| | default | 42.5861 | 0.0822151 | 2.46363 | | 999999 | 44.9350 | 0.0767194 | 2.44416 | | 999950 | 50.0660 | 0.075744 | 2.4091 | | 999500 | 56.9158 | 0.082564 | 2.4188 | | 995000 | 63.8625 | 0.0814927 | 2.42832 | | 990000 | 71.7314 | 0.106906 | 2.57785 | Search2 | cutoff | size-% | itlb | icache | |---------|--------|----------|---------| | default | 2.8845 | 0.626712 | 4.73245 | | 999999 | 3.3291 | 0.602309 | 4.70045 | | 999950 | 3.8577 | 0.587842 | 4.71632 | | 999500 | 4.4170 | 0.63577 | 4.68351 | | 995000 | 5.1020 | 0.657969 | 4.82272 | | 990000 | 5.7153 | 0.719122 | 5.39496 | Differential Revision: https://reviews.llvm.org/D89085 --- llvm/lib/CodeGen/MachineFunctionSplitter.cpp | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'llvm/lib/CodeGen/MachineFunctionSplitter.cpp') diff --git a/llvm/lib/CodeGen/MachineFunctionSplitter.cpp b/llvm/lib/CodeGen/MachineFunctionSplitter.cpp index 1a1bd901c92d..b2f474afea99 100644 --- a/llvm/lib/CodeGen/MachineFunctionSplitter.cpp +++ b/llvm/lib/CodeGen/MachineFunctionSplitter.cpp @@ -39,11 +39,18 @@ using namespace llvm; +// FIXME: This cutoff value is CPU dependent and should be moved to +// TargetTransformInfo once we consider enabling this on other platforms. +// The value is expressed as a ProfileSummaryInfo integer percentile cutoff. +// Defaults to 999950, i.e. all blocks colder than 99.995 percentile are split. +// The default was empirically determined to be optimal when considering cutoff +// values between 99%-ile to 100%-ile with respect to iTLB and icache metrics on +// Intel CPUs. static cl::opt PercentileCutoff("mfs-psi-cutoff", cl::desc("Percentile profile summary cutoff used to " "determine cold blocks. Unused if set to zero."), - cl::init(0), cl::Hidden); + cl::init(999950), cl::Hidden); static cl::opt ColdCountThreshold( "mfs-count-threshold", -- cgit v1.2.3