- 4ee451d Remove attribution from file headers, per discussion on llvmdev. by Chris Lattner · 17 years ago
- b253a8b make sure not to zap volatile stores, thanks a lot to Dale for noticing this! by Chris Lattner · 17 years ago
- 5938bef don't fold fp_round(fp_extend(load)) -> fp_round(extload) by Chris Lattner · 17 years ago
- 3c87285 Delete a store whose input is a load from the same pointer: by Chris Lattner · 17 years ago
- b16f55f Tell TargetLoweringOpt whether it is running before or after legalize. by Chris Lattner · 17 years ago
- 02132d6 Don't leave newly created nodes around if it turns out they are not needed. by Evan Cheng · 17 years ago
- e0e6fac Redo previous patch so optimization only done for i1. Simpler and safer. by Dale Johannesen · 17 years ago
- d3fd6d2 third time around: instead of disabling this completely, by Chris Lattner · 17 years ago
- e00cbad Actually, disable this code for now. More analysis and improvements to by Chris Lattner · 17 years ago
- e70da20 implement a readme entry, compiling the code into: by Chris Lattner · 17 years ago
- 59f1e97 Fix PR1842. by Dale Johannesen · 17 years ago
- 7700304 Don't lower srem/urem X%C to X-X/C*C unless the division is actually by Dan Gohman · 17 years ago
- fd617d0 Move MinAlign to MathExtras.h. by Duncan Sands · 17 years ago
- c6fa170 Fix some load/store logic that would be wrong for by Duncan Sands · 17 years ago
- 4471194 If both parts of smul_lohi, etc. are used, don't simplify. If only one part is used, try simplify it. by Evan Cheng · 17 years ago
- de1631b Typo. by Evan Cheng · 17 years ago
- 090b38a Fix a DAGCombiner abort on a bitcast from a scalar to a vector. by Dan Gohman · 17 years ago
- 3c3ddb3 Enable more fold (sext (load x)) -> (sext (truncate (sextload x))) by Evan Cheng · 17 years ago
- dc84650 The guaranteed alignment of ptr+offset is only the minimum of by Duncan Sands · 17 years ago
- b6210fc Redo "last ppc long double fix" as Chris wants. by Dale Johannesen · 17 years ago
- fabd32d More ppcf128 issues (maybe the last)? by Dale Johannesen · 17 years ago
- db44bf8 Disable attempts to constant fold PPC f128. by Dale Johannesen · 17 years ago
- 01d029b One mundane change: Change ReplaceAllUsesOfValueWith to *optionally* by Chris Lattner · 17 years ago
- e33544c Enhance the truncstore optimization code to handle shifted by Chris Lattner · 17 years ago
- 2b4c279 Add a simple optimization to simplify the input to by Chris Lattner · 17 years ago
- 272dce0 Correct swapped arguments to getConstant. by Duncan Sands · 17 years ago
- 389079b DAGCombiner support for UDIVREM/SDIVREM and UMUL_LOHI/SMUL_LOHI. by Dan Gohman · 17 years ago
- 513da43 Reapply 42677. by Evan Cheng · 17 years ago
- 5349de1 revert evan's patch until the header is committed by Chris Lattner · 17 years ago
- c231e8c Added DAG xforms. e.g. by Evan Cheng · 17 years ago
- e0480d2 Fix a bogus splat xform: by Evan Cheng · 17 years ago
- c7b21d5 Prevent crash on long double. by Dale Johannesen · 17 years ago
- 9d5f456 Revise previous patch per review comments. by Dale Johannesen · 17 years ago
- 3f6eb74 Add APInt interfaces to APFloat (allows directly by Dale Johannesen · 17 years ago
- 61c5ff4 Emit: by Chris Lattner · 17 years ago
- c4dd3c3 Add mod, copysign, abs operations to APFloat. by Dale Johannesen · 17 years ago
- e9c8fa0 Make DAGCombiner's global alias analysis query more precise in the case by Dan Gohman · 17 years ago
- e6c1742 Revise per review comments. by Dale Johannesen · 17 years ago
- 87503a6 Add APFloat interface to ConstantFPSDNode. Change by Dale Johannesen · 17 years ago
- 571c478 Fold C ? 0 : 1 to ~C or zext(~C) or trunc(~C) depending the types. by Evan Cheng · 17 years ago
- 559742c Fix the alias analysis query in DAGCombiner to not add in two by Dan Gohman · 17 years ago
- 05d92fe Don't call SimplifyVBinOp for non-vector operations, following earlier review by Dan Gohman · 17 years ago
- 70fb1ae Fix a bug in the folding of binary operators to undef. by Dan Gohman · 17 years ago
- d595b5f Fix the folding of undef in several binary operators to recognize by Dan Gohman · 17 years ago
- d6fd1bc Preserve volatililty and alignment information when lowering or by Dan Gohman · 17 years ago
- e094f54 Fix this warning: by Chris Lattner · 17 years ago
- 613e0d8 Fix several over-aggressive folds for undef nodes in dagcombine, to by Dan Gohman · 17 years ago
- 23ff182 Teach GetNegatedExpression to negate 0-B to B in UnsafeFPMath mode, and by Dan Gohman · 17 years ago
- 7f32156 Generalize MVT::ValueType and associated functions to be able to represent by Dan Gohman · 17 years ago
- ea859be Move ComputeMaskedBits, MaskedValueIsZero, and ComputeNumSignBits from by Dan Gohman · 17 years ago
- b13cdbd Xforms: by Evan Cheng · 17 years ago
- b5bec2b Pass a SelectionDAG into SDNode::dump everywhere it's used, in prepration by Dan Gohman · 17 years ago
- 51eaa86 Rename MVT::getVectorBaseType to MVT::getVectorElementType. by Dan Gohman · 17 years ago
- 3adf951 tighten up recursion depth again by Chris Lattner · 17 years ago
- c843abe Fix a typo that caused combiner to create mal-formed pre-indexed store where value store is the same as the base pointer. by Evan Cheng · 17 years ago
- 501fee7 prevent exponential recursion in isNegatibleForFree by Chris Lattner · 17 years ago
- fcc4dd9 Qualify calls to getTypeForValueType with MVT:: too. by Dan Gohman · 17 years ago
- 98a6c62 Don't fold bitconvert(load) for preinc/postdec loads. Likewise stores. by Dale Johannesen · 17 years ago
- c76d441 Use a ptr set instead of a linear search to unique TokenFactor operands. by Chris Lattner · 17 years ago
- 93003b8 Bug fix: should check ABI alignment, not pref. alignment. by Evan Cheng · 17 years ago
- b5bb7ff Fix an infinite recursion in GetNegatedExpression. by Lauro Ramos Venancio · 17 years ago
- 2944652 implement a simple fneg optimization/propagation thing. This compiles: by Chris Lattner · 17 years ago
- 2c4f943 Can't fold the bit_convert is the store is a truncating store. by Evan Cheng · 17 years ago
- c2cd2b2 Forgot a check. by Evan Cheng · 17 years ago
- 59d5b68 Enable a couple of xforms: by Evan Cheng · 17 years ago
- a7d4a04 Don't create indexed load / store with zero offset! by Evan Cheng · 17 years ago
- 498f559 Forgot about chain result; also UNDEF cannot have multiple values. by Evan Cheng · 17 years ago
- 45a7ca9 * Only turn a load to UNDEF if all of its outputs have no uses (indexed loads by Evan Cheng · 17 years ago
- 95c218a PR400 phase 2. Propagate attributed load/store information through DAGs. by Christopher Lamb · 17 years ago
- c67bdc2 Revert Christopher Lamb's load/store alignment changes. by Reid Spencer · 17 years ago
- 2330e4d by Christopher Lamb · 17 years ago
- 61a4c07 allow SRL to simplify its operands, as it doesn't demand all bits as input. by Chris Lattner · 17 years ago
- ec06e9a When replacing a node in SimplifyDemandedBits, if the old node used any by Chris Lattner · 17 years ago
- 95a5e05 SIGN_EXTEND_INREG does not demand its top bits. Give SimplifyDemandedBits by Chris Lattner · 17 years ago
- c24bbad fix an infinite loop compiling ldecod, notice by JeffC. by Chris Lattner · 17 years ago
- 1eba01e Fix this harder. by Chris Lattner · 17 years ago
- c56a81d don't create shifts by zero, fix some problems with my previous patch by Chris Lattner · 17 years ago
- 20a35c3 Teach the codegen to turn [aez]ext (setcc) -> selectcc of 1/0, which often by Chris Lattner · 17 years ago
- 1982ef2 Codegen integer abs more efficiently using the trick from the PPC CWG. This by Chris Lattner · 17 years ago
- c9dc114 1. Insert custom lowering hooks for ISD::ROTR and ISD::ROTL. by Scott Michel · 17 years ago
- 2041a0e Fix incorrect combination of different loads. Reenable zext-over-truncate by Dale Johannesen · 17 years ago
- b0b6c76 Disable load width reduction xform of variant (zext (truncate load x)) for by Evan Cheng · 17 years ago
- 15213b7 SIGN_EXTEND_INREG requires one extra operand, a ValueType node. by Evan Cheng · 17 years ago
- dae54ce Adjust offset to compensate for big endian machines. by Evan Cheng · 17 years ago
- e177e30 Make sure SEXTLOAD of the specific type is supported on the target. by Evan Cheng · 17 years ago
- b37b80c Also replace uses of SRL if that's also folded during ReduceLoadWidth(). by Evan Cheng · 17 years ago
- 0b063de A couple of bug fixes for reducing load width xform: by Evan Cheng · 17 years ago
- c88138f More opportunities to reduce load size. by Evan Cheng · 17 years ago
- 007b69e fold (truncate (srl (load x), c)) -> (smaller load (x+c/vt bits)) by Evan Cheng · 17 years ago
- 83060c5 Avoid combining indexed load further. by Evan Cheng · 17 years ago
- b654176 fold away addc nodes when we know there cannot be a carry-out. by Chris Lattner · 17 years ago
- bcf2484 generalize by Chris Lattner · 17 years ago
- 9115368 canonicalize constants to the RHS of addc/adde. If nothing uses the carry out of by Chris Lattner · 17 years ago
- 2255887 Fold (sext (truncate x)) more aggressively, by avoiding creation of a by Chris Lattner · 17 years ago
- fa1eb27 Move SimplifySetCC to TargetLowering and allow it to be shared with legalizer. by Evan Cheng · 18 years ago
- 597a3bd Fix for PR1108: type of insert_vector_elt index operand is PtrVT, not MVT::i32. by Evan Cheng · 18 years ago
- 42d7ccf Remove this xform: by Evan Cheng · 18 years ago
- c4e664b Fix PR1114 and CodeGen/Generic/2007-01-15-LoadSelectCycle.ll by being by Chris Lattner · 18 years ago
- 938ab02 add options to view the dags before the first or second pass of dag combine. by Chris Lattner · 18 years ago
- ddae4bd Implement some trivial FP foldings when -enable-unsafe-fp-math is specified. by Chris Lattner · 18 years ago