aboutsummaryrefslogtreecommitdiff
path: root/lib/Transforms
AgeCommit message (Collapse)Author
2012-10-27Update BBVectorize to use the new VTTI instr. cost interfaces.Hal Finkel
The monolithic interface for instruction costs has been split into several functions. This is the corresponding change. No functionality change is intended. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166865 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-271. Fix a bug in getTypeConversion. When a *simple* type is split, we need to ↵Nadav Rotem
return the type of the split result. 2. Change the maximum vectorization width from 4 to 8. 3. A test for both. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166864 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26Refactor the VectorTargetTransformInfo interface.Nadav Rotem
Add getCostXXX calls for different families of opcodes, such as casts, arithmetic, cmp, etc. Port the LoopVectorizer to the new API. The LoopVectorizer now finds instructions which will remain uniform after vectorization. It uses this information when calculating the cost of these instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166836 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26Change the internalize pass to internalize all symbols when given an emptyRafael Espindola
list of externals. This makes sense since a shared library with no symbols can still be useful if it has static constructors. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166795 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26LoopSimplify: Preserve DependenceAnalysis.Benjamin Kramer
This is currently true, but may change when DA grows more aggressive caching. Without this setting it's impossible to use DA from a LoopPass because DA is a function pass and cannot be properly scheduled in between LoopPasses. The LoopManager reacts to this with an infinite loop which made this really annoying to debug. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166788 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26Fix SCEV cache invalidation in LCSSA and LoopSimplify.Benjamin Kramer
The LoopSimplify bug is pretty harmless because the loop goes from unanalyzable to analyzable but the LCSSA bug is very nasty. It only comes into play with a specific order of the LoopPassManager worklist and can cause actual miscompilations, when a SCEV refers to a value that has been replaced with PHI node. SCEVExpander may then insert code into the wrong place, either violating domination or randomly miscompiling stuff. Comes with an extensive test case reduced from the test-suite with bugpoint+SCEVValidator. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166787 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26Use VTTI->getNumberOfParts in BBVectorize.Hal Finkel
This change reflects VTTI refactoring; no functionality change intended. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166752 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-26Disable generation of pointer vectors by BBVectorize.Hal Finkel
Once vector-of-pointer support works, then this can be reverted. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166741 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25BBVectorize, when using VTTI, should not form types that will be split.Hal Finkel
This is needed so that perl's SHA can be compiled (otherwise BBVectorize takes far too long to find its fixed point). I'll try to come up with a reduced test case. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166738 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25Begin incorporating target information into BBVectorize.Hal Finkel
This is the first of several steps to incorporate information from the new TargetTransformInfo infrastructure into BBVectorize. Two things are done here: 1. Target information is used to determine if it is profitable to fuse two instructions. This means that the cost of the vector operation must not be more expensive than the cost of the two original operations. Pairs that are not profitable are no longer considered (because current cost information is incomplete, for intrinsics for example, equal-cost pairs are still considered). 2. The 'cost savings' computed for the profitability check are also used to rank the DAGs that represent the potential vectorization plans. Specifically, for nodes of non-trivial depth, the cost savings is used as the node weight. The next step will be to incorporate the shuffle costs into the DAG weighting; this will give the edges of the DAG weights as well. Once that is done, when target information is available, we should be able to dispense with the depth heuristic. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166716 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25LoopVectorize: Teach the cost model to query scalar costs as scalar types ↵Nadav Rotem
and not vectors of 1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166715 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25Also optimize large switch statements.Jakob Stoklund Olesen
The isValueEqualityComparison() guard at the top of SimplifySwitch() only applies to some of the possible transformations. The newer transformations work just fine on large switches, and the check on predecessor count is nonsensical. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166710 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25Merge commit 'a8a0a155de16830b8fcab539ba2ec21de3145532'Derek Schuff
Conflicts: lib/Target/X86/X86FrameLowering.cpp lib/Target/X86/X86ISelLowering.cpp The Intel folks switched some of the FrameLowering code to use X86RegisterInfo::getSlotSize isntead of pointer size, thus reducing our localmods in that file.
2012-10-25Teach SROA how to split whole-alloca integer loads and stores intoChandler Carruth
smaller integer loads and stores. The high-level motivation is that the frontend sometimes generates a single whole-alloca integer load or store during ABI lowering of splittable allocas. We need to be able to break this apart in order to see the underlying elements and properly promote them to SSA values. The hope is that this fixes some performance regressions on x86-32 with the new SROA pass. Unfortunately, this causes quite a bit of churn in the test cases, and bloats some IR that comes out. When we see an alloca that consists soley of bits and bytes being extracted and re-inserted, we now do some splitting first, before building widened integer "bucket of bits" representations. These are always well folded by instcombine however, so this shouldn't actually result in missed opportunities. If this splitting of all-integer allocas does cause problems (perhaps due to smaller SSA values going into the RA), we could potentially go to some extreme measures to only do this integer splitting trick when there are non-integer component accesses of an alloca, but discovering this is quite expensive: it adds yet another complete walk of the recursive use tree of the alloca. Either way, I will be watching build bots and LNT bots to see what fallout there is here. If anyone gets x86-32 numbers before & after this change, I would be very interested. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166662 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25Add support for additional reduction variables: AND, OR, XOR.Nadav Rotem
Patch by Paul Redmond <paul.redmond@intel.com>. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166649 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24revert accidental changeNadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166643 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Implement a basic cost model for vector and scalar instructions. Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166642 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Fix a compiler warning with an unused variable.Micah Villmow
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166634 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Update GVN to support vectors of pointers.Hal Finkel
GVN will now generate ptrtoint instructions for vectors of pointers. Fixes PR14166. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166624 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24whitespaceNadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166622 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24LoopVectorizer: Add a basic cost model which uses the VTTI interface.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166620 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Add some cleanup to the DataLayout changes requested by Chandler.Micah Villmow
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166607 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Back out r166591, not sure why this made it through since I cancelled the ↵Micah Villmow
command. Bleh, sorry about this! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166596 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Delete a directory that wasn't supposed to be checked in yet.Micah Villmow
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166591 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24Add in support for getIntPtrType to get the pointer type based on the ↵Micah Villmow
address space. This checkin also adds in some tests that utilize these paths and updates some of the clients. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166578 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Merge commit '92b0d8cf2c51debc7f4fb30a417ae839077a8ed0'Derek Schuff
Conflicts: lib/Target/ARM/ARMISelLowering.cpp lib/Target/Mips/MipsISelLowering.h lib/Target/X86/X86ISelLowering.h lib/Target/X86/X86TargetMachine.h tools/llc/llc.cpp The only interesting conflict was ARMISelLowering, caused by http://llvm.org/viewvc/llvm-project?view=rev&revision=166273 which actually removes a LOCALMOD for ARM byval lowering.
2012-10-23Use the AliasAnalysis isIdentifiedObj because it also understands mallocs ↵Nadav Rotem
and c++ news. PR14158. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166491 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Fix typo that somehow escaped both testing and code inspection.Duncan Sands
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166475 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Transform code like thisDuncan Sands
%V = mul i64 %N, 4 %t = getelementptr i8* bitcast (i32* %arr to i8*), i32 %V into %t1 = getelementptr i32* %arr, i32 %N %t = bitcast i32* %t1 to i8* incorporating the multiplication into the getelementptr. This happens all the time in dragonegg, for example for int foo(int *A, int N) { return A[N]; } because gcc turns this into byte pointer arithmetic before it hits the plugin: D.1590_2 = (long unsigned int) N_1(D); D.1591_3 = D.1590_2 * 4; D.1592_5 = A_4(D) + D.1591_3; D.1589_6 = *D.1592_5; return D.1589_6; The D.1592_5 line is a POINTER_PLUS_EXPR, which is turned into a getelementptr on a bitcast of A_4 to i8*, so this becomes exactly the kind of IR that the transform fires on. An analogous transform (with no testcases!) already existed for bitcasts of arrays, so I rewrote it to share code with this one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166474 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Per the C++ standard, we need to include the definition of llvm::Calculate inRichard Smith
every TU where it's implicitly instantiated, even if there's an implicit instantiation for the same types available in another TU. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166470 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Fix typo.Julien Lerouge
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166456 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23Explain why DenseMap is still used here instead of MapVector.Julien Lerouge
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166454 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Iterating over a DenseMap<std::pair<BasicBlock*, unsigned>, PHINode*> is notJulien Lerouge
deterministic, replace it with a DenseMap<std::pair<unsigned, unsigned>, PHINode*> (we already have a map from BasicBlock to unsigned). <rdar://problem/12541389> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166435 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Don't crash if the load/store pointer is not a GEP.Nadav Rotem
Fix by Shivarama Rao <Shivarama.Rao@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166427 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Revert r166407 because it caused analyzer tests to crash and broke self-host ↵Argyrios Kyrtzidis
bots. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166424 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22BBVectorize should ignore unreachable blocks.Hal Finkel
Unreachable blocks can have invalid instructions. For example, jump threading can produce self-referential instructions in unreachable blocks. Also, we should not be spending time optimizing unreachable code. Fixes PR14133. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166423 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Rename a variable.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166410 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Vectorizer: optimize the generation of selects. If the condition is uniform, ↵Nadav Rotem
generate a scalar-cond select (i1 as selector). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166409 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Update the loop vectorizer docs.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166408 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Reapply r166405, teaching tailcallelim to be smarter about nocapture, with aNick Lewycky
very small but very important bugfix: bool shouldExplore(Use *U) { Value *V = U->get(); if (isa<CallInst>(V) || isa<InvokeInst>(V)) [...] should have read: bool shouldExplore(Use *U) { Value *V = U->getUser(); if (isa<CallInst>(V) || isa<InvokeInst>(V)) Fixes PR14143! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166407 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-22Revert r166405, "Teach TailRecursionElimination to consider 'nocapture' when ↵NAKAMURA Takumi
deciding whether" It broke selfhosting stage2 in several builders. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166406 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Teach TailRecursionElimination to consider 'nocapture' when deciding whetherNick Lewycky
calls can be marked tail. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166405 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Revert r166390 "LoopIdiom: Replace custom dependence analysis with ↵Benjamin Kramer
LoopDependenceAnalysis." It passes all tests, produces better results than the old code but uses the wrong pass, LoopDependenceAnalysis, which is old and unmaintained. "Why is it still in tree?", you might ask. The answer is obviously: "To confuse developers." Just swapping in the new dependency pass sends the pass manager into an infinte loop, I'll try to figure out why tomorrow. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166399 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Avoid an extra hash lookup when inserting a value into the widen map.Anders Carlsson
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166395 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Simplify code. No functionality change.Jakub Staszak
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166393 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Simplify code. No functionality change.Jakub Staszak
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166392 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21LoopIdiom: Replace custom dependence analysis with LoopDependenceAnalysis.Benjamin Kramer
Requires a lot less code and complexity on loop-idiom's side and the more precise analysis can catch more cases, like the one I included as a test case. This also fixes the edge-case miscompilation from PR9481. I'm not entirely sure that all cases are handled that the old checks handled but LDA will certainly become smarter in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166390 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Fix a bug in the vectorization of wide load/store operations.Nadav Rotem
We used a SCEV to detect that A[X] is consecutive. We assumed that X was the induction variable. But X can be any expression that uses the induction for example: X = i + 2; git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166388 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Add support for reduction variables that do not start at zero.Nadav Rotem
This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166387 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-21Document change. Describe the pass and some papers that inspired the design ↵Nadav Rotem
of the pass. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166386 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-07-13 06:30:51 +0000