Mirror of official llvm git repository located at http://llvm.org/git/llvm. Updated every five minutes.
Go to file
Chandler Carruth 3508e27903 Revert r223764 which taught instcombine about integer-based elment extraction
patterns.

This is causing Clang to miscompile itself for 32-bit x86 somehow, and likely
also on ARM and PPC. I really don't know how, but reverting now that I've
confirmed this is actually the culprit. I have a reproduction as well and so
should be able to restore this shortly.

This reverts commit r223764.

Original commit log follows:
Teach instcombine to canonicalize "element extraction" from a load of an
integer and "element insertion" into a store of an integer into actual
element extraction, element insertion, and vector loads and stores.

Previously various parts of LLVM (including instcombine itself) would
introduce integer loads and stores into the code as a way of opaquely
loading and storing "bits". In some cases (such as a memcpy of
std::complex<float> object) we will eventually end up using those bits
in non-integer types. In order for SROA to effectively promote the
allocas involved, it splits these "store a bag of bits" integer loads
and stores up into the constituent parts. However, for non-alloca loads
and tsores which remain, it uses integer math to recombine the values
into a large integer to load or store.

All of this would be "fine", except that it forces LLVM to go through
integer math to combine and split up values. While this makes perfect
sense for integers (and in fact is critical for bitfields to end up
lowering efficiently) it is *terrible* for non-integer types, especially
floating point types. We have a much more canonical way of representing
the act of concatenating the bits of two SSA values in LLVM: a vector
and insertelement. This patch teaching InstCombine to use this
representation.

With this patch applied, LLVM will no longer introduce integer math into
the critical path of every loop over std::complex<float> operations such
as those that make up the hot path of ... oh, most HPC code, Eigen, and
any other heavy linear algebra library.

For the record, I looked *extensively* at fixing this in other parts of
the compiler, but it just doesn't work:
- We really do want to canonicalize memcpy and other bit-motion to
  integer loads and stores. SSA values are tremendously more powerful
  than "copy" intrinsics. Not doing this regresses massive amounts of
  LLVM's scalar optimizer.
- We really do need to split up integer loads and stores of this form in
  SROA or every memcpy of a trivially copyable struct will prevent SSA
  formation of the members of that struct. It essentially turns off
  SROA.
- The closest alternative is to actually split the loads and stores when
  partitioning with SROA, but this has all of the downsides historically
  discussed of splitting up loads and stores -- the wide-store
  information is fundamentally lost. We would also see performance
  regressions for bitfield-heavy code and other places where the
  integers aren't really intended to be split without seemingly
  arbitrary logic to treat integers totally differently.
- We *can* effectively fix this in instcombine, so it isn't that hard of
  a choice to make IMO.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223813 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-09 19:21:16 +00:00
autoconf Expose LLVM version string via macro in llvm-config.h, and modify Go bindings 2014-11-19 03:34:17 +00:00
bindings IR: Split Metadata from Value 2014-12-09 18:38:53 +00:00
cmake Make GetSVN.cmake do its VCS queries with native CMake code. 2014-12-05 00:50:15 +00:00
docs Add argument variable support to the debug info tutorial 2014-12-09 00:28:24 +00:00
examples Once more on the cmake build. nativecodegen->native on the dependencies. 2014-12-08 18:24:06 +00:00
include Fix another GCC build failure from r223802 2014-12-09 18:59:09 +00:00
lib Revert r223764 which taught instcombine about integer-based elment extraction 2014-12-09 19:21:16 +00:00
projects [cmake] Use the external project machinery for libcxxabi so that it can 2014-07-25 10:27:40 +00:00
test Revert r223764 which taught instcombine about integer-based elment extraction 2014-12-09 19:21:16 +00:00
tools Adding a new option to CMake to disable C++ atexit on llvm-shlib. 2014-12-09 18:49:55 +00:00
unittests IR: Split Metadata from Value 2014-12-09 18:38:53 +00:00
utils Improve emacs coding style 2014-12-09 08:58:31 +00:00
.arcconfig Updated phabricator server. 2014-04-07 03:57:04 +00:00
.clang-format Test commit. 2014-03-02 13:08:46 +00:00
.clang-tidy Enable display of compiler diagnostics in clang-tidy by default. 2014-10-29 17:29:38 +00:00
.gitignore Initial version of Go bindings. 2014-10-16 22:48:02 +00:00
CMakeLists.txt Adding a new option to CMake to disable C++ atexit on llvm-shlib. 2014-12-09 18:49:55 +00:00
CODE_OWNERS.TXT Make myself the code owner for llgo. 2014-12-08 20:30:39 +00:00
configure Expose LLVM version string via macro in llvm-config.h, and modify Go bindings 2014-11-19 03:34:17 +00:00
CREDITS.TXT Rise from the dead and update personal info 2014-08-25 17:51:04 +00:00
LICENSE.TXT Remove projects/sample. 2014-03-12 22:40:22 +00:00
llvm.spec.in
LLVMBuild.txt Remove the very substantial, largely unmaintained legacy PGO 2013-10-02 15:42:23 +00:00
Makefile [configure/make] Propagate names of build host tools when making BuildTools 2014-03-25 21:45:41 +00:00
Makefile.common Makefile.common: Update a description, s/Source/SOURCES/ , according to MakefileGuide.html#control-variables . 2012-12-07 01:43:23 +00:00
Makefile.config.in Add a check for misbehaving -Wcomment from gcc-4.7 and add 2014-11-05 00:35:15 +00:00
Makefile.rules Add a check for misbehaving -Wcomment from gcc-4.7 and add 2014-11-05 00:35:15 +00:00
README.txt [TEST-COMMIT] As per Developer Policy, Added a blank line. 2014-12-06 00:38:39 +00:00

Low Level Virtual Machine (LLVM)
================================

This directory and its subdirectories contain source code for the Low Level
Virtual Machine, 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're writing a package for LLVM, see docs/Packaging.rst for our
suggestions.