llvm-project/llvm
Chandler Carruth 1964078936 [x86] Teach the new vector shuffle lowering to aggressively form MOVSS
and MOVSD nodes for single element vector inserts.

This is particularly important because a number of patterns in the
backend detect these patterns and leverage them to simplify things. It
also fixes quite a few of the insertion bad code examples. However, it
regresses a specific area: when available, blendps and blendpd are
*dramatically* faster than movss and movsd respectively. But it doesn't
really work to form the blend logic first because the blends *aren't* as
crazy efficient when the data is coming from memory anyways, and thus
will have a movss or movsd regardless. Also, doing that would block
a bunch of the patterns that this is designed to hit.

So my plan is to go into the patterns for lowering MOVSS and MOVSD and
lower them via blends when available. However that's a pretty invasive
restructuring so it will need to be a follow-up patch.

I have already gone into the patterns to lower MOVSS and MOVSD from
memory using MOVLPD, etc. Without that, several of the test cases
I already have regress.

llvm-svn: 218985
2014-10-03 13:11:13 +00:00
..
autoconf Delete support for AuroraUX. 2014-08-14 15:15:09 +00:00
bindings Reinstate "Nuke the old JIT." 2014-09-02 22:28:02 +00:00
cmake Add LLVM_ENABLE_MODULES flag to CMake to enable building with C++ modules. 2014-09-26 22:40:15 +00:00
docs [sphinx cleanup] Fix unexpected indentation warning introduced by r218937 2014-10-03 12:28:48 +00:00
examples Add doInitialization/doFinalization to DataLayoutPass. 2014-09-10 21:27:43 +00:00
include Revert 202433 - Provide a target override for the latest regalloc heuristic 2014-10-03 12:20:53 +00:00
lib [x86] Teach the new vector shuffle lowering to aggressively form MOVSS 2014-10-03 13:11:13 +00:00
projects [cmake] Use the external project machinery for libcxxabi so that it can 2014-07-25 10:27:40 +00:00
test [x86] Teach the new vector shuffle lowering to aggressively form MOVSS 2014-10-03 13:11:13 +00:00
tools llvm-readobj: print COFF delay-load import table 2014-10-03 00:41:58 +00:00
unittests Revert "DI: Fold constant arguments into a single MDString" 2014-10-02 22:15:31 +00:00
utils PR21101: tablegen's FastISel emitter should filter out unused functions. 2014-10-01 22:44:01 +00:00
.arcconfig
.clang-format
.clang-tidy Add .clang-tidy configuration file to provide LLVM-optimized defaults for 2014-09-08 13:30:00 +00:00
.gitignore
CMakeLists.txt Add LLVM_ENABLE_MODULES flag to CMake to enable building with C++ modules. 2014-09-26 22:40:15 +00:00
CODE_OWNERS.TXT Add Tom Stellard's role as 3.5 release manager. 2014-09-12 08:07:31 +00:00
CREDITS.TXT Rise from the dead and update personal info 2014-08-25 17:51:04 +00:00
LICENSE.TXT
LLVMBuild.txt
Makefile
Makefile.common
Makefile.config.in
Makefile.rules Revert my earlier change to add "all" as a dependency to check. In 2014-09-19 18:44:27 +00:00
README.txt
configure Delete support for AuroraUX. 2014-08-14 15:15:09 +00:00
llvm.spec.in

README.txt

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.