Chandler Carruth db35087d21 Implement a block placement pass based on the branch probability and ... block frequency analyses. This differs substantially from the existing block-placement pass in LLVM: 1) It operates on the Machine-IR in the CodeGen layer. This exposes much more (and more precise) information and opportunities. Also, the results are more stable due to fewer transforms ocurring after the pass runs. 2) It uses the generalized probability and frequency analyses. These can model static heuristics, code annotation derived heuristics as well as eventual profile loading. By basing the optimization on the analysis interface it can work from any (or a combination) of these inputs. 3) It uses a more aggressive algorithm, both building chains from tho bottom up to maximize benefit, and using an SCC-based walk to layout chains of blocks in a profitable ordering without O(N^2) iterations which the old pass involves. The pass is currently gated behind a flag, and not enabled by default because it still needs to grow some important features. Most notably, it needs to support loop aligning and careful layout of loop structures much as done by hand currently in CodePlacementOpt. Once it supports these, and has sufficient testing and quality tuning, it should replace both of these passes. Thanks to Nick Lewycky and Richard Smith for help authoring & debugging this, and to Jakob, Andy, Eric, Jim, and probably a few others I'm forgetting for reviewing and answering all my questions. Writing a backend pass is *sooo* much better now than it used to be. =D git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142641 91177308-0d34-0410-b5e6-96231b3b80d8		2011-10-21 06:46:38 +00:00
..
Analysis	A FIXME about block addresses and indirectbr.	2011-10-20 04:05:33 +00:00
Archive	Rewrite the CMake build to use explicit dependencies between libraries,	2011-07-29 00:14:25 +00:00
AsmParser	Backing out patch. Will refactor to remove the AsmParser dependency on Target.	2011-10-18 00:23:49 +00:00
Bitcode	Also update the EH with bitcode. I missed this earlier. Thanks to Duncan for pointing it out.	2011-10-05 07:04:14 +00:00
CodeGen	Implement a block placement pass based on the branch probability and	2011-10-21 06:46:38 +00:00
DebugInfo	lib/DebugInfo/DWARFDebugLine.cpp: De-Unicode-ify.	2011-10-08 11:22:47 +00:00
ExecutionEngine	Adding dependencies to allow -DBUILD_SHARED_LIBS=true to complete.	2011-10-19 00:13:13 +00:00
Linker	Allow the source module to be materialized during the linking process.	2011-10-14 22:17:46 +00:00
MC	Fix parsing of a line with only a # in it.	2011-10-19 18:48:52 +00:00
Object	Object/COFF: Remove useless test.	2011-10-18 19:51:36 +00:00
Support	Remove unused include of sys/uio.h in MemoryBuffer.cpp. It was not correctly protected by ifdef either.	2011-10-20 21:57:46 +00:00
TableGen	Implement Paste	2011-10-19 13:04:43 +00:00
Target	Fix unused variable warning.	2011-10-21 01:22:04 +00:00
Transforms	Refactor code from inlining and globalopt that checks whether a function definition is unused, and enhance it so it can tell that functions which are only used by a blockaddress are in fact dead. This probably doesn't happen much on most code, but the Linux kernel's _THIS_IP_ can trigger this issue with blockaddress. (GlobalDCE can also handle the given tescase, but we only run that at -O3.) Found while looking at PR11180.	2011-10-20 05:23:42 +00:00
VMCore	Refactor code from inlining and globalopt that checks whether a function definition is unused, and enhance it so it can tell that functions which are only used by a blockaddress are in fact dead. This probably doesn't happen much on most code, but the Linux kernel's _THIS_IP_ can trigger this issue with blockaddress. (GlobalDCE can also handle the given tescase, but we only run that at -O3.) Found while looking at PR11180.	2011-10-20 05:23:42 +00:00
CMakeLists.txt	Move TableGen's parser and entry point into a library	2011-10-01 16:41:13 +00:00
Makefile	Remove more of llvmc and dependencies.	2011-09-20 00:34:27 +00:00