llvm-project/llvm
Kazu Hirata 9895c7012d [InlineCost] Implement cost-benefit-based inliner
This patch adds an alternative cost metric for the inliner to take
into account both the cost (i.e. size) and cycle count savings into
account.

Without this patch, we decide to inline a given call site if the size
of inlining the call site is below the threshold that is computed
according to the hotness of the call site.

This patch adds a new cost metric, turned off by default, to take over
the handling of hot call sites.  Specifically, with the new cost
metric, we decide to inline a given call site if the ratio of cycle
savings to size exceeds a threshold.  The cycle savings are computed
from call site costs, parameter propagation, folded conditional
branches, etc, all weighted by their respective profile counts.  The
size is primarily the callee size, but we subtract call site costs and
the size of basic blocks that are never executed.

The new cost metric implicitly takes advantage of the machine function
splitter recently introduced by Snehasish Kumar, which dramatically
reduces the cost of duplicating (e.g. inlining) cold basic blocks by
placing cold basic blocks of hot functions in the .text.split
section.

We evaluated the new cost metric on clang bootstrap and SPECInt 2017.

For clang bootstrap, we observe 0.69% runtime improvement.

For SPECInt we report the change in IntRate the C/C++ benchmarks.  All
benchmarks apart from perlbench and omnetpp improve, on average by
0.21% with the max for mcf at 1.96%.

Benchmark               % Change
500.perlbench_r         -0.45
502.gcc_r                0.13
505.mcf_r                1.96
520.omnetpp_r           -0.28
523.xalancbmk_r          0.49
525.x264_r               0.00
531.deepsjeng_r          0.00
541.leela_r              0.35
557.xz_r                 0.21

Differential Revision: https://reviews.llvm.org/D92780
2020-12-18 00:37:24 -08:00
..
benchmarks
bindings [Go] Fix bindings/go/llvm/IRBindings.cpp 2020-12-16 10:09:58 -08:00
cmake [CMake] Avoid __FakeVCSRevision.h with no git repository 2020-12-16 17:33:20 +01:00
docs [IR][PGO] Add hot func attribute and use hot/cold attribute in func section 2020-12-17 18:41:12 -08:00
examples [NFC] Reduce include files dependency and AA header cleanup (part 2). 2020-12-17 14:04:48 +03:00
include [clang][cli] Convert Analyzer option string based options to new option parsing system 2020-12-18 08:56:06 +01:00
lib [InlineCost] Implement cost-benefit-based inliner 2020-12-18 00:37:24 -08:00
projects
resources
runtimes
test [PowerPC] Select the D-Form load if we know its offset meets the requirement 2020-12-18 07:27:26 +00:00
tools [llvm-readobj/elf] - AArch64: Handle AARCH64_VARIANT_PCS for GNUStyle 2020-12-17 11:09:53 -03:00
unittests Revert "Ensure SplitEdge to return the new block between the two given blocks" 2020-12-17 21:00:37 +00:00
utils [NFC][utils] Factor remaining APIs under FunctionTestBuilder 2020-12-17 22:13:14 -08:00
.clang-format
.clang-tidy
.gitattributes
.gitignore
CMakeLists.txt Remove Python2 fallback and only advertise Python3 in the doc 2020-12-17 15:40:16 +01:00
CODE_OWNERS.TXT
CREDITS.TXT
LICENSE.TXT
README.txt
RELEASE_TESTERS.TXT
configure
llvm.spec.in

README.txt

The LLVM Compiler Infrastructure
================================

This directory and its subdirectories contain source code for LLVM,
a toolkit for the construction of highly optimized compilers,
optimizers, and runtime environments.

LLVM is open source software. You may freely distribute it under the terms of
the license agreement found in LICENSE.txt.

Please see the documentation provided in docs/ for further
assistance with LLVM, and in particular docs/GettingStarted.rst for getting
started with LLVM and docs/README.txt for an overview of LLVM's
documentation setup.

If you are writing a package for LLVM, see docs/Packaging.rst for our
suggestions.