1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Go to file
Benjamin Kramer 0463564612 CodeGenPrepare: Add a transform to turn selects into branches in some cases.
This came up when a change in block placement formed a cmov and slowed down a
hot loop by 50%:

	ucomisd	(%rdi), %xmm0
	cmovbel	%edx, %esi

cmov is a really bad choice in this context because it doesn't get branch
prediction. If we emit it as a branch, an out-of-order CPU can do a better job
(if the branch is predicted right) and avoid waiting for the slow load+compare
instruction to finish. Of course it won't help if the branch is unpredictable,
but those are really rare in practice.

This patch uses a dumb conservative heuristic, it turns all cmovs that have one
use and a direct memory operand into branches. cmovs usually save some code
size, so we disable the transform in -Os mode. In-Order architectures are
unlikely to benefit as well, those are included in the
"predictableSelectIsExpensive" flag.

It would be better to reuse branch probability info here, but BPI doesn't
support select instructions currently. It would make sense to use the same
heuristics as the if-converter pass, which does the opposite direction of this
transform.


Test suite shows a small improvement here and there on corei7-level machines,
but the actual results depend a lot on the used microarchitecture. The
transformation is currently disabled by default and available by passing the
-enable-cgp-select2branch flag to the code generator.

Thanks to Chandler for the initial test case to him and Evan Cheng for providing
me with comments and test-suite numbers that were more stable than mine :)

llvm-svn: 156234
2012-05-05 12:49:22 +00:00
autoconf This patch adds a new NVPTX back-end to LLVM which supports code generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the current PTX back-end, while maintaining compatibility with it. 2012-05-04 20:18:50 +00:00
bindings [python] Add negative MemoryBuffer testcase 2012-03-22 11:23:52 +00:00
cmake Pass -fcolor-diagnostics when it is supported. This makes a difference when 2012-05-04 03:23:36 +00:00
docs Use correct variable in this example. Pointed out by waynix on IRC. 2012-05-03 15:25:19 +00:00
examples Remove llvm-ld and llvm-stub (which is only used by llvm-ld). 2012-04-19 19:27:54 +00:00
include Add a new target hook "predictableSelectIsExpensive". 2012-05-05 12:49:14 +00:00
lib CodeGenPrepare: Add a transform to turn selects into branches in some cases. 2012-05-05 12:49:22 +00:00
projects This patch adds a new NVPTX back-end to LLVM which supports code generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the current PTX back-end, while maintaining compatibility with it. 2012-05-04 20:18:50 +00:00
runtime Switch to c-style comments in a C file. 2012-04-27 19:30:29 +00:00
test CodeGenPrepare: Add a transform to turn selects into branches in some cases. 2012-05-05 12:49:22 +00:00
tools Move the CodeExtractor utility to a dedicated header file / source file, 2012-05-04 10:18:49 +00:00
unittests SmallVector: Don't rely on having an assignment operator around in push_back for POD-like types. 2012-04-29 10:53:29 +00:00
utils Order register classes by spill size first, members last. 2012-05-04 23:12:22 +00:00
.gitignore Add tools/lld to .gitignore. 2012-05-02 21:25:32 +00:00
CMakeLists.txt This patch adds a new NVPTX back-end to LLVM which supports code generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the current PTX back-end, while maintaining compatibility with it. 2012-05-04 20:18:50 +00:00
configure This patch adds a new NVPTX back-end to LLVM which supports code generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the current PTX back-end, while maintaining compatibility with it. 2012-05-04 20:18:50 +00:00
CREDITS.TXT Update the documentation of CellSPU, in case it gets removed in 3.1. 2012-04-29 20:00:55 +00:00
LICENSE.TXT Add YAML parser to Support. 2012-04-03 23:09:22 +00:00
llvm.spec.in Tidy up. s/Low Level Virtual Machine/LLVM/. 2012-01-25 22:00:23 +00:00
LLVMBuild.txt LLVMBuild: Introduce a common section which currently has a list of the 2011-12-12 22:45:54 +00:00
Makefile When cross compiling, install a host version of llvm-config. <rdar://11187889> 2012-04-19 23:19:55 +00:00
Makefile.common Removed trailing whitespace from Makefiles. 2009-01-09 16:44:42 +00:00
Makefile.config.in Add profiling support for Intel Parallel Amplifier XE (VTune) for JITted code in LLVM. 2012-03-13 08:33:15 +00:00
Makefile.rules Remove llvm-ld and llvm-stub (which is only used by llvm-ld). 2012-04-19 19:27:54 +00:00
README.txt test commit 2012-03-20 13:12:38 +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 HTML documentation provided in docs/index.html for further
assistance with LLVM.

If you're writing a package for LLVM, see docs/Packaging.html for our
suggestions.