aboutsummaryrefslogtreecommitdiff
path: root/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
AgeCommit message (Collapse)Author
2013-05-06Fix slightly too aggressive conact_vector optimization.Michael Kuperstein
(Would sometimes optimize away conacts used to extend a vector with undef values) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181186 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-01Optimize away nop CONCAT_VECTOR nodes.Nadav Rotem
Optimize CONCAT_VECTOR nodes that merge EXTRACT_SUBVECTOR values that extract from the same vector. rdar://13402653 PR15866 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180871 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-26Re-write the address propagation code for pre-indexed loads/stores to take ↵Silviu Baranga
into account some previously misssed cases (PRE_DEC addressing mode, the offset and base address are swapped, etc). This should fix PR15581. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180609 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-26DAGCombiner: Canonicalize vector integer abs in the same way we do it for ↵Benjamin Kramer
scalars. This already helps SSE2 x86 a lot because it lacks an efficient way to represent a vector select. The long term goal is to enable the backend to match a canonicalized pattern into a single instruction (e.g. vabs or pabs). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180597 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-23DAGCombine should not aggressively fold SEXT(VSETCC(...)) into a wider ↵Owen Anderson
VSETCC without first checking the target's vector boolean contents. This exposed an issue with PowerPC AltiVec where it appears it was setting the wrong vector boolean contents. The included change fixes the PowerPC tests, and was OK'd by Hal. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180129 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-20Remove unused MEMBARRIER DAG node; it's been replaced by ATOMIC_FENCE.Tim Northover
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179939 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09DAGCombiner: Fold a shuffle on CONCAT_VECTORS into a new CONCAT_VECTORS if ↵Benjamin Kramer
possible. This pattern occurs in SROA output due to the way vector arguments are lowered on ARM. The testcase from PR15525 now compiles into this, which is better than the code we got with the old scalarrepl: _Store: ldr.w r9, [sp] vmov d17, r3, r9 vmov d16, r1, r2 vst1.8 {d16, d17}, [r0] bx lr Differential Revision: http://llvm-reviews.chandlerc.com/D647 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179106 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-02DAGCombiner: Merge store/loads when we have extload/truncstoresArnold Schwaighofer
This is helps on architectures where i8,i16 are not legal but we have byte, and short loads/stores. Allowing us to merge copies like the one below on ARM. copy(char *a, char *b, int n) { do { int t0 = a[0]; int t1 = a[1]; b[0] = t0; b[1] = t1; radar://13536387 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178546 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-01Merge load/store sequences with adresses: base + index + offsetArnold Schwaighofer
We would also like to merge sequences that involve a variable index like in the example below. int index = *idx++ int i0 = c[index+0]; int i1 = c[index+1]; b[0] = i0; b[1] = i1; By extending the parsing of the base pointer to handle dags that contain a base, index, and offset we can handle examples like the one above. The dag for the code above will look something like: (load (i64 add (i64 copyfromreg %c) (i64 signextend (i8 load %index)))) (load (i64 add (i64 copyfromreg %c) (i64 signextend (i32 add (i32 signextend (i8 load %index)) (i32 1))))) The code that parses the tree ignores the intermediate sign extensions. However, if there is a sign extension it needs to be on all indexes. (load (i64 add (i64 copyfromreg %c) (i64 signextend (add (i8 load %index) (i8 1)))) vs (load (i64 add (i64 copyfromreg %c) (i64 signextend (i32 add (i32 signextend (i8 load %index)) (i32 1))))) radar://13536387 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178483 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-30DAGCombine: visitXOR can replace a node without returning it, bail out in ↵Benjamin Kramer
that case. Fixes the crash reported in PR15608. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178429 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-25Enhance folding of (extract_subvec (insert_subvec V1, V2, IIdx), EIdx)Michael Liao
- Handle the case where the result of 'insert_subvect' is bitcasted before 'extract_subvec'. This removes the redundant insertf128/extractf128 pair on unaligned 256-bit vector load/store on vectors of non 64-bit integer. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177945 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-25Disable some unsafe-fp-math DAG-combine transformation after legalization.Shuxin Yang
For instance, following transformation will be disabled: x + x + x => 3.0f * x; The problem of these transformations is that it introduces a FP constant, which following Instruction-Selection pass cannot handle. Reviewed by Nadav, thanks a lot! rdar://13445387 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177933 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-12Avoid generating ISD::SELECT for vector operands to SIGN_EXTENDRichard Relph
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176881 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-08DAGCombiner: Use correct value type for checking legality of BR_CC v3Tom Stellard
LegalizeDAG.cpp uses the value of the comparison operands when checking the legality of BR_CC, so DAGCombiner should do the same. v2: - Expand more BR_CC value types for NVPTX v3: - Expand correct BR_CC value types for Hexagon, Mips, and XCore. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176694 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21DAGCombiner: Make the post-legalize vector op optimization more aggressive.Benjamin Kramer
A legal BUILD_VECTOR goes in and gets constant folded into another legal BUILD_VECTOR so we don't lose any legality here. The problematic PPC optimization that made this check necessary was fixed recently. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175759 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-20DAGCombiner: Fold pointless truncate, bitcast, buildvector seriesArnold Schwaighofer
(2xi32) (truncate ((2xi64) bitcast (buildvector i32 a, i32 x, i32 b, i32 y))) can be folded into a (2xi32) (buildvector i32 a, i32 b). Such a DAG would cause uneccessary vdup instructions followed by vmovn instructions. We generate this code on ARM NEON for a setcc olt, 2xf64, 2xf64. For example, in the vectorized version of the code below. double A[N]; double B[N]; void test_double_compare_to_double() { int i; for(i=0;i<N;i++) A[i] = (double)(A[i] < B[i]); } radar://13191881 Fixes bug 15283. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175670 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-14Dont merge consecutive loads/stores into vectors when noimplicitfloat is used.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175190 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-14Add some legality checks for SETCC before introducing it in the DAG combiner ↵Owen Anderson
post-operand legalization. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175149 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-12PR14562 - Truncation of left shift became undefPaul Redmond
DAGCombiner::ReduceLoadWidth was converting (trunc i32 (shl i64 v, 32)) into (shl i32 v, 32) into undef. To prevent this, check the shift count against the final result size. Patch by: Kevin Schoedel Reviewed by: Nadav Rotem git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174972 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-12Check type for legality before forming a select from loads.Pete Cooper
Sorry for the lack of a test case. I tried writing one for i386 as i know selects are illegal on this target, but they are actually considered legal by isel and expanded later. I can't see any targets to trigger this, but checking for the legality of a node before forming it is general goodness. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174934 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-08DAGCombiner: Constant folding around pre-increment loads/storesHal Finkel
Previously, even when a pre-increment load or store was generated, we often needed to keep a copy of the original base register for use with other offsets. If all of these offsets are constants (including the offset which was combined into the addressing mode), then this is clearly unnecessary. This change adjusts these other offsets to use the new incremented address. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174746 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-05Reapply r174343, with a fix for a scary DAG combine bug where it failed to ↵Owen Anderson
differentiate between the alignment of the base point of a load, and the overall alignment of the load. This caused infinite loops in DAG combine with the original application of this patch. ORIGINAL COMMIT LOG: When the target-independent DAGCombiner inferred a higher alignment for a load, it would replace the load with one with the higher alignment. However, it did not place the new load in the worklist, which prevented later DAG combines in the same phase (for example, target-specific combines) from ever seeing it. This patch corrects that oversight, and updates some tests whose output changed due to slightly different DAGCombine outputs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174431 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-05Revert r174343, "When the target-independent DAGCombiner inferred a higher ↵NAKAMURA Takumi
alignment for a load," It caused hangups in compiling clang/lib/Parse/ParseDecl.cpp and clang/lib/Driver/Tools.cpp in stage2 on some hosts. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174374 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-05When the target-independent DAGCombiner inferred a higher alignment for a load,Owen Anderson
it would replace the load with one with the higher alignment. However, it did not place the new load in the worklist, which prevented later DAG combines in the same phase (for example, target-specific combines) from ever seeing it. This patch corrects that oversight, and updates some tests whose output changed due to slightly different DAGCombine outputs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174343 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-02rdar://13126763Shuxin Yang
Fix a bug in DAGCombine. The symptom is mistakenly optimizing expression "x + x*x" into "x * 3.0". git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174239 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-20Revert 172708.Nadav Rotem
The optimization handles esoteric cases but adds a lot of complexity both to the X86 backend and to other backends. This optimization disables an important canonicalization of chains of SEXT nodes and makes SEXT and ZEXT asymmetrical. Disabling the canonicalization of consecutive SEXT nodes into a single node disables other DAG optimizations that assume that there is only one SEXT node. The AVX mask optimizations is one example. Additionally this optimization does not update the cost model. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172968 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-17Optimization for the following SIGN_EXTEND pairs:Elena Demikhovsky
v8i8 -> v8i64, v8i8 -> v8i32, v4i8 -> v4i64, v4i16 -> v4i64 for AVX and AVX2. Bug 14865. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172708 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-14This patch addresses an incorrect transformation in the DAG combiner.Bill Schmidt
The included test case is derived from one of the GCC compatibility tests. The problem arises after the selection DAG has been converted to type-legalized form. The combiner first sees a 64-bit load that can be converted into a pre-increment form. The original load feeds into a SRL that isolates the upper 32 bits of the loaded doubleword. This looks like an opportunity for DAGCombiner::ReduceLoadWidth() to replace the 64-bit load with a 32-bit load. However, this transformation is not valid, as the replacement load is not a pre-increment load. The pre-increment load produces an extra result, which feeds a subsequent add instruction. The replacement load only has one result value, and this value is propagated to all uses of the pre- increment load, including the add. Because the add is looking for the second result value as its operand, it ends up attempting to add a constant to a token chain, resulting in a crash. So the patch simply disables this transformation for any load with more than two result values. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172480 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-09Fix a DAG combine bug visitBRCOND() is transforming br(xor(x, y)) to br(x != y).Evan Cheng
It cahced XOR's operands before calling visitXOR() but failed to update the operands when visitXOR changed the XOR node. rdar://12968664 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171999 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-07Sink AddrMode back into TargetLowering, removing one of the mostChandler Carruth
peculiar headers under include/llvm. This struct still doesn't make a lot of sense, but it makes more sense down in TargetLowering than it did before. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171739 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-02DAGCombiner: Avoid generating illegal vector INT_TO_FP nodesTom Stellard
DAGCombiner::reduceBuildVecConvertToConvertBuildVec() was making two mistakes: 1. It was checking the legality of scalar INT_TO_FP nodes and then generating vector nodes. 2. It was passing the result value type to TargetLoweringInfo::getOperationAction() when it should have been passing the value type of the first operand. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171420 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-02Move all of the header files which are involved in modelling the LLVM IRChandler Carruth
into their new header subdirectory: include/llvm/IR. This matches the directory structure of lib, and begins to correct a long standing point of file layout clutter in LLVM. There are still more header files to move here, but I wanted to handle them in separate commits to make tracking what files make sense at each layer easier. The only really questionable files here are the target intrinsic tablegen files. But that's a battle I'd rather not fight today. I've updated both CMake and Makefile build systems (I think, and my tests think, but I may have missed something). I've also re-sorted the includes throughout the project. I'll be committing updates to Clang, DragonEgg, and Polly momentarily. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171366 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-30Remove the Function::getFnAttributes method in favor of using the AttributeSetBill Wendling
directly. This is in preparation for removing the use of the 'Attribute' class as a collection of attributes. That will shift to the AttributeSet class instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171253 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-27Refactor DAGCombinerInfo. Change the different booleans that indicate if we ↵Nadav Rotem
are before or after different runs of DAGCo, with the CombineLevel enum. Also, added a new API for checking if we are running before or after the LegalizeVectorOps phase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171142 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20Do not introduce vector operations in functions marked with noimplicitfloat.Bob Wilson
<rdar://problem/12879313> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170630 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19Change TargetLowering::isCondCodeLegal to take an MVT, instead of EVT.Patrik Hagglund
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170524 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19Optimized load + SIGN_EXTEND patterns in the X86 backend.Elena Demikhovsky
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170506 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-13Fix a bug in DAGCombiner::MatchBSwapHWord. Make sure the node has operands ↵Evan Cheng
before referencing them. rdar://12868039 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170078 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12DAGCombine: clamp hi bit in APInt::getBitsSet to avoid assertionManman Ren
rdar://12838504 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169951 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-11Revert EVT->MVT changes, r169836-169851, due to buildbot failures.Patrik Hagglund
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169854 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-11Change TargetLowering::isCondCodeLegal to take an MVT, instead of EVT.Patrik Hagglund
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169843 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-11Fix a miscompile in the DAG combiner. Previously, we would incorrectlyChandler Carruth
try to reduce the width of this load, and would end up transforming: (truncate (lshr (sextload i48 <ptr> as i64), 32) to i32) to (truncate (zextload i32 <ptr+4> as i64) to i32) We lost the sext attached to the load while building the narrower i32 load, and replaced it with a zext because lshr always zext's the results. Instead, bail out of this combine when there is a conflict between a sextload and a zext narrowing. The rest of the DAG combiner still optimize the code down to the proper single instruction: movswl 6(...),%eax Which is exactly what we wanted. Previously we read past the end *and* missed the sign extension: movl 6(...), %eax git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169802 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-10Teach DAG combine to handle vector add/sub with vectors of all 0s.Craig Topper
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169727 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-09Remove extra blank line.Craig Topper
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169692 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-08Teach DAG combine to handle vector logical operations with vectors of all 1s ↵Craig Topper
or all 0s. These cases can show up when vectors are split for legalizing. Fix some tests that were dependent on these cases not being combined. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169684 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-06Fix a bug in the code that merges consecutive stores. Previously we did notNadav Rotem
check if loads that happen in between stores alias with the first store in the chain, only with the second store onwards. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169516 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-03Use the new script to sort the includes of every file under lib.Chandler Carruth
Sooooo many of these had incorrect or strange main module includes. I have manually inspected all of these, and fixed the main module include to be the nearest plausible thing I could find. If you own or care about any of these source files, I encourage you to take some time and check that these edits were sensible. I can't have broken anything (I strictly added headers, and reordered them, never removed), but they may not be the headers you'd really like to identify as containing the API being implemented. Many forward declarations and missing includes were added to a header files to allow them to parse cleanly when included first. The main module rule does in fact have its merits. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169131 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-02Allow merging multiple store sequences on the same chain.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169111 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-29When combining consecutive stores allow loads in between the stores, if the ↵Nadav Rotem
loads do not alias. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168832 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14Handle DAG CSE adding new uses during ReplaceAllUsesWith. Fixes PR14333.Rafael Espindola
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167912 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-04-26 20:44:04 +0000