aboutsummaryrefslogtreecommitdiff
path: root/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp
AgeCommit message (Collapse)Author
2009-03-23Fix canClobberPhysRegDefs to check all SDNodes grouped togetherDan Gohman
in an SUnit, instead of just the first one. This fix is needed by some upcoming scheduler changes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@67531 91177308-0d34-0410-b5e6-96231b3b80d8
2009-03-20For inline asm output operand that matches an input. Encode the input ↵Evan Cheng
operand index in the high bits. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@67387 91177308-0d34-0410-b5e6-96231b3b80d8
2009-03-12Fix a typo in a comment.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@66843 91177308-0d34-0410-b5e6-96231b3b80d8
2009-03-06Fix ScheduleDAGRRList::CopyAndMoveSuccessors' handling of nodesDan Gohman
with multiple chain operands. This can occur when the scheduler has added chain operands to a node that already has a chain operand, in order to handle physical register dependencies. This fixes an llvm-gcc bootstrap failure on x86-64 introduced in r66058. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@66240 91177308-0d34-0410-b5e6-96231b3b80d8
2009-03-04Fix PR3701. 1. X86 target renamed eflags register to flags. This matches ↵Evan Cheng
what llvm-gcc generates so codegen knows flags register is being clobbered by inline asm. 2. BURR scheduler should also check if inline asm nodes can clobber "live" physical registers. Previously it was only checking target nodes with implicit defs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@65996 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-12Oops. Last second clean up messed things up.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64373 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-12Replace one of burr scheduling heuristic with something more sensible. Now ↵Evan Cheng
calcMaxScratches simply compute the number of true data dependencies. This actually improve a couple of tests in dejagnu suite as many tests in llvm nightly test suite. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64369 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-11Fix a comment.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64328 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-11Don't use special heuristics for nodes with no data predecessorsDan Gohman
unless they actually have data successors, and likewise for nodes with no data successors unless they actually have data precessors. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64327 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-11Delete the heuristic for non-livein CopyFromReg nodes. Non-liveinnessDan Gohman
is determined by whether the node has a Flag operand. However, if the node does have a Flag operand, it will be glued to its register's def, so the heuristic would end up spuriously applying to whatever node is the def. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64319 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-11When scheduling a block in parts, keep track of the overallDan Gohman
instruction index across each part. Instruction indices are used to make live range queries, and live ranges can extend beyond scheduling region boundaries. Refactor the ScheduleDAGSDNodes class some more so that it doesn't have to worry about this additional information. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64288 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-10Factor out more code for computing register live-range informationforDan Gohman
scheduling, and generalize is so that preserves state across scheduling regions. This fixes incorrect live-range information around terminators and labels, which are effective region boundaries. In place of looking for terminators to anchor inter-block dependencies, introduce special entry and exit scheduling units for this purpose. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64254 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-10Fix PR3457: Ignore control successors when looking for closest scheduled ↵Evan Cheng
successor. A control successor doesn't read result(s) produced by the scheduling unit being evaluated. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@64210 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-06Move ScheduleDAGSDNodes.h to be a private header. Front-endsDan Gohman
that previously included this header should include SchedulerRegistry.h instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63937 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-29Make a few things const, fix some comments, and simplifyDan Gohman
some assertions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63328 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-15Move a few containers out of ScheduleDAGInstrs::BuildSchedGraphDan Gohman
and into the ScheduleDAGInstrs class, so that they don't get destructed and re-constructed for each block. This fixes a compile-time hot spot in the post-pass scheduler. To help facilitate this, tidy and do some minor reorganization in the scheduler constructor functions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62275 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-13The list-td and list-tdrr schedulers don't yet support physregDan Gohman
scheduling dependencies. Add assertion checks to help catch this. It appears the Mips target defaults to list-td, and it has a regression test that uses a physreg dependence. Such code was liable to be miscompiled, and now evokes an assertion failure. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62177 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-12Fix PR3241: Currently EmitCopyFromReg emits a copy from the physical ↵Evan Cheng
register to a virtual register unless it requires an expensive cross class copy. That means we are only treating "expensive to copy" register dependency as physical register dependency. Also future proof the scheduler to handle "normal" physical register dependencies. The code is not exercised yet. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62074 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-09Minor debug output tweak.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62005 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-07Remove redundant 'else's. No functionality change.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61891 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-06Update these argument lists for the isNormalMemoryDan Gohman
argument. This doesn't affect current functionality. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61779 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-06Use a latency value of 0 for the artificial edges inserted byDan Gohman
AddPseudoTwoAddrDeps. This lets the scheduling infrastructure avoid recalculating node heights. In very large testcases this was a major bottleneck. Thanks to Roman Levenstein for finding this! As a side effect, fold-pcmpeqd-0.ll is now scheduled better and it no longer requires spilling on x86-32. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61778 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-05Tidy up #includes, deleting a bunch of unnecessary #includes.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61715 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-03CommuteNodesToReducePressure() is now removed.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61612 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-03Remove the code from the scheduler that commuted two-addressDan Gohman
instructions to avoid copies, because TwoAddressInstructionPass also does this optimization. The scheduler's version didn't account for live-out values, which resulted in spurious commutes and missed opportunities. Now, TwoAddressInstructionPass handles all the opportunities, instead of just those that the scheduler missed. The result is usually the same, though there are occasional trivial differences resulting from the avoidance of spurious commutes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61611 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-23Rename BuildSchedUnits to BuildSchedGraph, and refactor theDan Gohman
code in ScheduleDAGSDNodes' BuildSchedGraph into separate functions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61376 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-16Fix some register-alias-related bugs in the post-RA scheduler livenessDan Gohman
computation code. Also, avoid adding output-depenency edges when both defs are dead, which frequently happens with EFLAGS defs. Compute Depth and Height lazily, and always in terms of edge latency values. For the schedulers that don't care about latency, edge latencies are set to 1. Eliminate Cycle and CycleBound, and LatencyPriorityQueue's Latencies array. These are all subsumed by the Depth and Height fields. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61073 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-16Make addPred and removePred return void, since the return value is notDan Gohman
currently used by anything. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61066 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-09Rewrite the SDep class, and simplify some of the related code.Dan Gohman
The Cost field is removed. It was only being used in a very limited way, to indicate when the scheduler should attempt to protect a live register, and it isn't really needed to do that. If we ever want the scheduler to start inserting copies in non-prohibitive situations, we'll have to rethink some things anyway. A Latency field is added. Instead of giving each node a single fixed latency, each edge can have its own latency. This will eventually be used to model various micro-architecture properties more accurately. The PointerIntPair class and an internal union are now used, which reduce the overall size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60806 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-04Make debug output more informative.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60524 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-25Initial support for anti-dependence breaking. Currently this code does notDan Gohman
introduce any new spilling; it just uses unused registers. Refactor the SUnit topological sort code out of the RRList scheduler and make use of it to help with the post-pass scheduler. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59999 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-24Check in the rest of this change. The isAntiDep flag needs to be passedDan Gohman
to removePred because an SUnit can both data-depend and anti-depend on the same SUnit. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59969 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-21Add a flag to SDep for tracking which edges are anti-dependence edges.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59785 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-21Rename SDep's isSpecial to isArtificial, to make this field a littleDan Gohman
less mysterious. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59782 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-21Remove the CycleBound computation code from the ScheduleDAGRRListDan Gohman
schedulers. This doesn't have much immediate impact because targets that use these schedulers by default don't yet provide pipeline information. This code also didn't have the benefit of register pressure information. Also, removing it will avoid problems with list-burr suddenly starting to do latency-oriented scheduling on x86 when we start providing pipeline data, which would increase spilling. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59775 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-21Change these schedulers to not emit no-ops. It turns out thatDan Gohman
the RR scheduler actually does look at latency values, but it doesn't use a hazard recognizer so it has no way to know when a no-op is needed, as opposed to just stalling and incrementing the cycle count. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59759 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-20Remove a remnant of list-burr's fast mode.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59702 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-20Factor out the SethiUllman numbering logic from the list-burr andDan Gohman
list-tdrr schedulers into a common base class. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59701 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-20Remove the "fast" form of the list-burr scheduler, and use theDan Gohman
dedicated "fast" scheduler in -fast mode instead, which is faster. This speeds up llc -fast by a few percent on some testcases -- the speedup only happens for code not handled by fast-isel. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59700 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-20Facter AddPseudoTwoAddrDeps and associated infrasructure out ofDan Gohman
the list-burr scheduler so that it can be used by the list-tdrr scheduler too. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59698 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-20Factor out the code for verifying the work of the scheduler,Dan Gohman
extend it a bit, and make use of it in all schedulers, to ensure consistent checking. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59689 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-19Experimental post-pass scheduling support. Post-pass schedulingDan Gohman
is currently off by default, and can be enabled with -disable-post-RA-scheduler=false. This doesn't have a significant impact on most code yet because it doesn't yet do anything to address anti-dependencies and it doesn't attempt to disambiguate memory references. Also, several popular targets don't have pipeline descriptions yet. The majority of the changes here are splitting the SelectionDAG-specific code out of ScheduleDAG, so that ScheduleDAG can be moved to libLLVMCodeGen.a. The interface between ScheduleDAG-using code and the rest of the scheduling code is somewhat rough and will evolve. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59676 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-19Rearrange code to reduce the nesting level. No functionality change.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59580 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-18Tidy up ScheduleNodeBottomUp methods, and make them moreDan Gohman
consistent with ScheduleNodeTopDown methods. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59550 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-18Change SUnit's dump method to take a ScheduleDAG* instead ofDan Gohman
a SelectionDAG*. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59488 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-18Avoid using a loop in ReleasePred and ReleaseSucc methods to compute theDan Gohman
new CycleBound value. Instead, just update CycleBound on each call. Also, make ReleasePred and ReleaseSucc methods more consistent accross the various schedulers. This also happens to make ScheduleDAGRRList's CycleBound computation somewhat more interesting, though it still doesn't have any noticeable effect, because no current targets that use the register-pressure reduction scheduler provide pipeline models. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59475 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-17Eliminate some trivial differences between the ScheduleNodeTopDownDan Gohman
functions in these two schedulers. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59465 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-13Remove the FlaggedNodes member from SUnit. Instead of requiring each SUnitDan Gohman
to carry a SmallVector of flagged nodes, just calculate the flagged nodes dynamically when they are needed. The local-liveness change is due to a trivial scheduling change where the scheduler arbitrary decision differently. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59273 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-13Make the Node member of SUnit private, and add accessors.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59264 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-13Change ScheduleDAG's DAG member from a reference to a pointer, to prepareDan Gohman
for the possibility of scheduling without a SelectionDAG being present. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59263 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-09-06 02:31:33 +0000