Commit Graph

112 Commits

Author SHA1 Message Date
Tom Stellard
a52c3acc14 Add a MachinePostDominator pass
This is used in the AMDIL and R600 backends.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164029 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-17 14:08:37 +00:00
Andrew Trick
99ab6c6035 TargetSchedModel interface. To be implemented...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163934 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-14 20:26:46 +00:00
Nadav Rotem
c05d30601c Add a new optimization pass: Stack Coloring, that merges disjoint static allocations (allocas). Allocas are known to be
disjoint if they are marked by disjoint lifetime markers (@llvm.lifetime.XXX intrinsics).



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163299 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-06 09:17:37 +00:00
Jakob Stoklund Olesen
9f63e10427 Start scaffolding for a MachineTraceMetrics analysis pass.
This is still a work in progress.

Out-of-order CPUs usually execute instructions from multiple basic
blocks simultaneously, so it is necessary to look at longer traces when
estimating the performance effects of code transformations.

The MachineTraceMetrics analysis will pick a typical trace through a
given basic block and provide performance metrics for the trace. Metrics
will include:

- Instruction count through the trace.
- Issue count per functional unit.
- Critical path length, and per-instruction 'slack'.

These metrics can be used to determine the performance limiting factor
when executing the trace, and how it will be affected by a code
transformation.

Initially, this will be used by the early if-conversion pass.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160796 91177308-0d34-0410-b5e6-96231b3b80d8
2012-07-26 18:38:11 +00:00
Jakob Stoklund Olesen
33242fd3ed Add an experimental early if-conversion pass, off by default.
This pass performs if-conversion on SSA form machine code by
speculatively executing both sides of the branch and using a cmov
instruction to select the result. This can help lower the number of
branch mispredictions on architectures like x86 that don't have
predicable instructions.

The current implementation is very aggressive, and causes regressions on
mosts tests. It needs good heuristics that have yet to be implemented.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159694 91177308-0d34-0410-b5e6-96231b3b80d8
2012-07-04 00:09:54 +00:00
NAKAMURA Takumi
d5c407d2d0 llvm/lib: [CMake] Add explicit dependency to intrinsics_gen.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159112 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-24 13:32:01 +00:00
Jakob Stoklund Olesen
312244747c Remove the RenderMachineFunction HTML output pass.
I don't think anyone has been using this functionality for a while, and
it is getting in the way of refactoring now.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158876 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-20 23:47:58 +00:00
Jakob Stoklund Olesen
8879480ed7 Sketch a LiveRegMatrix analysis pass.
The LiveRegMatrix represents the live range of assigned virtual
registers in a Live interval union per register unit. This is not
fundamentally different from the interference tracking in RegAllocBase
that both RABasic and RAGreedy use.

The important differences are:

- LiveRegMatrix tracks interference per register unit instead of per
  physical register. This makes interference checks cheaper and
  assignments slightly more expensive. For example, the ARM D7 reigster
  has 24 aliases, so we would check 24 physregs before assigning to one.
  With unit-based interference, we check 2 units before assigning to 2
  units.

- LiveRegMatrix caches regmask interference checks. That is currently
  duplicated functionality in RABasic and RAGreedy.

- LiveRegMatrix is a pass which makes it possible to insert
  target-dependent passes between register allocation and rewriting.
  Such passes could tweak the register assignments with interference
  checking support from LiveRegMatrix.

Eventually, RABasic and RAGreedy will be switched to LiveRegMatrix.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158255 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-09 02:13:10 +00:00
Andrew Trick
63bbe14e20 cmake: new file
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155460 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-24 18:06:49 +00:00
Andrew Trick
8c1161a262 Fix cmake
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152210 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-07 05:46:04 +00:00
Andrew Trick
96f678f2d7 Added the MachineSchedulerPass skeleton.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148105 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-13 06:30:30 +00:00
Jakob Stoklund Olesen
ccc9581e8b Move RegAllocBase into its own cpp file separate from RABasic.
No functional change.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147972 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-11 22:28:30 +00:00
Evan Cheng
977679d603 Added a late machine instruction copy propagation pass. This catches
opportunities that only present themselves after late optimizations
such as tail duplication .e.g.
## BB#1:
        movl    %eax, %ecx
        movl    %ecx, %eax
        ret

The register allocator also leaves some of them around (due to false
dep between copies from phi-elimination, etc.)

This required some changes in codegen passes. Post-ra scheduler and the
pseudo-instruction expansion passes have been moved after branch folding
and tail merging. They were before branch folding before because it did
not always update block livein's. That's fixed now. The pass change makes
independently since we want to properly schedule instructions after
branch folding / tail duplication.

rdar://10428165
rdar://10640363



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147716 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-07 03:02:36 +00:00
Benjamin Kramer
1031111f84 Kill ObjectCodeEmitter and BinaryObject, they were unused and superseded by MC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147618 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-05 22:31:37 +00:00
Rafael Espindola
611caf5f91 Remove the old ELF writer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147615 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-05 22:07:43 +00:00
Chandler Carruth
cfb75fba73 Fix up the CMake build for the new files added in r146960, they're
likely to stay either way that discussion ends up resolving itself.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146966 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-20 08:42:11 +00:00
Nick Lewycky
028700f544 Move parts of lib/Target that use CodeGen into lib/CodeGen.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146702 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-15 22:58:58 +00:00
NAKAMURA Takumi
d2cda5ce51 llvm/lib/CodeGen: Fix cmake build since r146542.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146550 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14 03:50:53 +00:00
Lang Hames
bae56b4c21 Kill off the LoopSplitter. It's not being used or maintained.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145897 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-06 01:57:59 +00:00
Dylan Noblesmith
fe0926d773 CodeGen: fix CMake build
Missing file from r145629.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145634 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-01 21:49:23 +00:00
Daniel Dunbar
d782bae970 build/CMake: Finish removal of add_llvm_library_dependencies.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145420 91177308-0d34-0410-b5e6-96231b3b80d8
2011-11-29 19:25:30 +00:00
Jakob Stoklund Olesen
6e49be7101 Delete VirtRegRewriter.
And there was much rejoicing.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@144480 91177308-0d34-0410-b5e6-96231b3b80d8
2011-11-13 00:16:01 +00:00
Jakob Stoklund Olesen
799c1ede71 Delete the linear scan register allocator.
RegAllocGreedy has been the default for six months now.

Deleting RegAllocLinearScan makes it possible to also delete
VirtRegRewriter and clean up the spiller code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@144475 91177308-0d34-0410-b5e6-96231b3b80d8
2011-11-12 22:39:45 +00:00
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
Jakob Stoklund Olesen
d4d4fca9c3 Rename SSEDomainFix -> lib/CodeGen/ExecutionDepsFix.
I'll clean up the source in the next commit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140663 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-28 00:01:54 +00:00
Jakob Stoklund Olesen
fb96574fca Rename LowerSubregs to ExpandPostRAPseudos.
I'll fix the file contents in the next commit.

This pass is currently expanding the COPY and SUBREG_TO_REG pseudos. I
am going to add a hook so targets can expand more pseudo-instructions
after register allocation.

Many targets have pseudo-instructions that assist the register
allocator.  They can be expanded after register allocation, before PEI
and PostRA scheduling.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140469 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-25 16:46:00 +00:00
Jakob Stoklund Olesen
b5a457c4cb Extract live range calculations from SplitKit.
SplitKit will soon need two copies of these data structures, and the
algorithms will also be useful when LiveIntervalAnalysis becomes
independent of LiveVariables.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139572 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-13 01:34:21 +00:00
Devang Patel
103b8e653c Provide utility to extract and use lexical scoping information from machine instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137237 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-10 19:04:06 +00:00
Chandler Carruth
ac03e736c7 Rewrite the CMake build to use explicit dependencies between libraries,
specified in the same file that the library itself is created. This is
more idiomatic for CMake builds, and also allows us to correctly specify
dependencies that are missed due to bugs in the GenLibDeps perl script,
or change from compiler to compiler. On Linux, this returns CMake to
a place where it can relably rebuild several targets of LLVM.

I have tried not to change the dependencies from the ones in the current
auto-generated file. The only places I've really diverged are in places
where I was seeing link failures, and added a dependency. The goal of
this patch is not to start changing the dependencies, merely to move
them into the correct location, and an explicit form that we can control
and change when necessary.

This also removes a serialization point in the build because we don't
have to scan all the libraries before we begin building various tools.
We no longer have a step of the build that regenerates a file inside the
source tree. A few other associated cleanups fall out of this.

This isn't really finished yet though. After talking to dgregor he urged
switching to a single CMake macro to construct libraries with both
sources and dependencies in the arguments. Migrating from the two macros
to that style will be a follow-up patch.

Also, llvm-config is still generated with GenLibDeps.pl, which means it
still has slightly buggy dependencies. The internal CMake
'llvm-config-like' macro uses the correct explicitly specified
dependencies however. A future patch will switch llvm-config generation
(when using CMake) to be based on these deps as well.

This may well break Windows. I'm getting a machine set up now to dig
into any failures there. If anyone can chime in with problems they see
or ideas of how to solve them for Windows, much appreciated.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136433 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-29 00:14:25 +00:00
Jakub Staszak
f55c1c8588 Rename BlockFrequency to BlockFrequencyInfo and MachineBlockFrequency to
MachineBlockFrequencyInfo.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135937 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-25 19:25:40 +00:00
Jakub Staszak
59a9dab4d8 Add MachineBlockFrequency analysis.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135352 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-16 20:23:20 +00:00
Chandler Carruth
0b3b58df1b Fix CMake build by removing this now dead file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133981 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-28 02:03:12 +00:00
Rafael Espindola
655739de7b Merge SimpleRegisterCoalescing.cpp into RegisterCoalescer.cpp.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133897 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-26 22:06:36 +00:00
Jakub Staszak
7cc2b07437 Introduce MachineBranchProbabilityInfo class, which has similar API to
BranchProbabilityInfo (expect setEdgeWeight which is not available here).
Branch Weights are kept in MachineBasicBlocks. To turn off this analysis
set -use-mbpi=false.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133184 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-16 20:22:37 +00:00
Jakob Stoklund Olesen
491a13691d Add a RegisterClassInfo class that lazily caches information about
register classes.

It provides information for each register class that cannot be
determined statically, like:

- The number of allocatable registers in a class after filtering out the
  reserved and invalid registers.

- The preferred allocation order with registers that overlap callee-saved
  registers last.

- The last callee-saved register that overlaps a given physical register.

This information usually doesn't change between functions, so it is
reused for compiling multiple functions when possible.  The many
possible combinations of reserved and callee saves registers makes it
unfeasible to compute this information statically in TableGen.

Use RegisterClassInfo to count available registers in various heuristics
in SimpleRegisterCoalescing, making the pass run 4% faster.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132450 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-02 02:19:35 +00:00
Jakob Stoklund Olesen
5907d86365 Add an InterferenceCache class for caching per-block interference ranges.
When the greedy register allocator is splitting multiple global live ranges, it
tends to look at the same interference data many times. The InterferenceCache
class caches queries for unaltered LiveIntervalUnions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128764 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-02 06:03:35 +00:00
Oscar Fuentes
6d857ca4d7 Move library stuff out of the toplevel CMakeLists.txt file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125968 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-18 22:06:14 +00:00
Chris Lattner
9dddf08eb8 sort this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123129 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-09 21:31:39 +00:00
Jakob Stoklund Olesen
8bfe50871f Add the SpillPlacement analysis pass.
This pass precomputes CFG block frequency information that can be used by the
register allocator to find optimal spill code placement.

Given an interference pattern, placeSpills() will compute which basic blocks
should have the current variable enter or exit in a register, and which blocks
prefer the stack.

The algorithm is ready to consume block frequencies from profiling data, but for
now it gets by with the static estimates used for spill weights.

This is a work in progress and still not hooked up to RegAllocGreedy.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122938 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-06 01:21:53 +00:00
Jakob Stoklund Olesen
8dd070edc2 Turn the EdgeBundles class into a stand-alone machine CFG analysis pass.
The analysis will be needed by both the greedy register allocator and the
X86FloatingPoint pass. It only needs to be computed once when the CFG doesn't
change.

This pass is very fast, usually showing up as 0.0% wall time.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122832 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-04 21:10:05 +00:00
Jakob Stoklund Olesen
ceadc01e91 Add MachineLoopRanges analysis.
A MachineLoopRange contains the intervals of slot indexes covered by the blocks
in a loop. This representation of the loop blocks is more efficient to compare
against interfering registers during register coalescing.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121917 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-15 23:41:23 +00:00
Jakob Stoklund Olesen
c9672cb8be Add an AllocationOrder class that can iterate over the allocatable physical
registers for a given virtual register.

Reserved registers are filtered from the allocation order, and any valid hint is
returned as the first suggestion.

For target dependent hints, a number of arcane target hooks are invoked.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121497 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-10 18:36:02 +00:00
Andrew Trick
6b1207267f Generalize PostRAHazardRecognizer so it can be used in any pass for
both forward and backward scheduling. Rename it to
ScoreboardHazardRecognizer (Scoreboard is one word). Remove integer
division from the scoreboard's critical path.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121274 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-08 20:04:29 +00:00
Jakob Stoklund Olesen
cba2e06d52 Stub out RegAllocGreedy.
This new register allocator is initially identical to RegAllocBasic, but it will
receive all of the tricks that RegAllocBasic won't get.

RegAllocGreedy will eventually replace linear scan.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121234 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-08 03:26:16 +00:00
Cameron Zwarich
a474685d06 Move the FindCopyInsertPoint method of PHIElimination to a new standalone
function so that it can be shared with StrongPHIElimination.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120951 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-05 19:51:05 +00:00
Jakob Stoklund Olesen
bb7b23f5b7 Stub out a new LiveDebugVariables pass.
This analysis is going to run immediately after LiveIntervals. It will stay
alive during register allocation and keep track of user variables mentioned in
DBG_VALUE instructions.

When the register allocator is moving values between registers and the stack, it
is very hard to keep track of DBG_VALUE instructions. We usually get it wrong.
This analysis maintains a data structure that makes it easy to update DBG_VALUE
instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120385 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-30 02:17:10 +00:00
Dan Gohman
8ec9d62380 Rename ExpandPseudos to ExpandISelPseudos to help clarify its role.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119716 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-18 18:45:06 +00:00
Evan Cheng
61f1a97e61 Add ExpandPseudos.cpp.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119385 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-16 21:20:36 +00:00
Andrew Trick
14e8d71cc9 This is a prototype of an experimental register allocation
framework. It's purpose is not to improve register allocation per se,
but to make it easier to develop powerful live range splitting. I call
it the basic allocator because it is as simple as a global allocator
can be but provides the building blocks for sophisticated register
allocation with live range splitting. 

A minimal implementation is provided that trivially spills whenever it
runs out of registers. I'm checking in now to get high-level design
and style feedback. I've only done minimal testing. The next step is
implementing a "greedy" allocation algorithm that does some register
reassignment and makes better splitting decisions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117174 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-22 23:09:15 +00:00
Jakob Stoklund Olesen
a17768f582 Create a new LiveRangeEdit class to keep track of the new registers created when
splitting or spillling, and to help with rematerialization.

Use LiveRangeEdit in InlineSpiller and SplitKit. This will eventually make it
possible to share remat code between InlineSpiller and SplitKit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116543 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-14 23:49:52 +00:00