| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Add skeletal code to increase the alignment of loads and stores when | Chris Lattner | 2008-01-25 | 1 | -0/+38 |
| * | clarify a comment, thanks Duncan. | Chris Lattner | 2008-01-24 | 1 | -2/+3 |
| * | Fix this buggy transformation. Two observations: | Chris Lattner | 2008-01-24 | 1 | -17/+8 |
| * | The dag combiner is missing revisiting nodes that it really should, and thus ... | Chris Lattner | 2008-01-24 | 1 | -0/+5 |
| * | fold fp_round(fp_round(x)) -> fp_round(x). | Chris Lattner | 2008-01-24 | 1 | -0/+9 |
| * | This commit changes: | Chris Lattner | 2008-01-17 | 1 | -10/+20 |
| * | code cleanups, no functionality change. | Chris Lattner | 2008-01-17 | 1 | -7/+9 |
| * | * Introduce a new SelectionDAG::getIntPtrConstant method | Chris Lattner | 2008-01-17 | 1 | -11/+25 |
| * | Fixes a nasty dag combiner bug that causes a bunch of tests to fail at -O0. | Evan Cheng | 2008-01-16 | 1 | -6/+44 |
| * | Factor the ReachesChainWithoutSideEffects out of dag combiner into | Chris Lattner | 2008-01-16 | 1 | -28/+1 |
| * | Make load->store deletion a bit smarter. This allows us to compile this: | Chris Lattner | 2008-01-08 | 1 | -3/+33 |
| * | Remove attribution from file headers, per discussion on llvmdev. | Chris Lattner | 2007-12-29 | 1 | -2/+2 |
| * | make sure not to zap volatile stores, thanks a lot to Dale for noticing this! | Chris Lattner | 2007-12-29 | 1 | -1/+2 |
| * | don't fold fp_round(fp_extend(load)) -> fp_round(extload) | Chris Lattner | 2007-12-29 | 1 | -0/+4 |
| * | Delete a store whose input is a load from the same pointer: | Chris Lattner | 2007-12-29 | 1 | -1/+12 |
| * | Tell TargetLoweringOpt whether it is running before | Chris Lattner | 2007-12-22 | 1 | -1/+1 |
| * | Don't leave newly created nodes around if it turns out they are not needed. | Evan Cheng | 2007-12-19 | 1 | -2/+4 |
| * | Redo previous patch so optimization only done for i1. | Dale Johannesen | 2007-12-06 | 1 | -16/+4 |
| * | third time around: instead of disabling this completely, | Chris Lattner | 2007-12-06 | 1 | -6/+13 |
| * | Actually, disable this code for now. More analysis and improvements to | Chris Lattner | 2007-12-06 | 1 | -0/+6 |
| * | implement a readme entry, compiling the code into: | Chris Lattner | 2007-12-06 | 1 | -19/+65 |
| * | Fix PR1842. | Dale Johannesen | 2007-12-06 | 1 | -4/+16 |
| * | Don't lower srem/urem X%C to X-X/C*C unless the division is actually | Dan Gohman | 2007-11-26 | 1 | -14/+18 |
| * | Move MinAlign to MathExtras.h. | Duncan Sands | 2007-11-09 | 1 | -1/+0 |
| * | Fix some load/store logic that would be wrong for | Duncan Sands | 2007-11-09 | 1 | -4/+8 |
| * | If both parts of smul_lohi, etc. are used, don't simplify. If only one part i... | Evan Cheng | 2007-11-08 | 1 | -30/+31 |
| * | Typo. | Evan Cheng | 2007-10-30 | 1 | -1/+1 |
| * | Fix a DAGCombiner abort on a bitcast from a scalar to a vector. | Dan Gohman | 2007-10-29 | 1 | -1/+2 |
| * | Enable more fold (sext (load x)) -> (sext (truncate (sextload x))) | Evan Cheng | 2007-10-29 | 1 | -24/+134 |
| * | The guaranteed alignment of ptr+offset is only the minimum of | Duncan Sands | 2007-10-28 | 1 | -9/+13 |
| * | Redo "last ppc long double fix" as Chris wants. | Dale Johannesen | 2007-10-19 | 1 | -1/+1 |
| * | More ppcf128 issues (maybe the last)? | Dale Johannesen | 2007-10-19 | 1 | -1/+1 |
| * | Disable attempts to constant fold PPC f128. | Dale Johannesen | 2007-10-16 | 1 | -12/+16 |
| * | One mundane change: Change ReplaceAllUsesOfValueWith to *optionally* | Chris Lattner | 2007-10-15 | 1 | -19/+14 |
| * | Enhance the truncstore optimization code to handle shifted | Chris Lattner | 2007-10-13 | 1 | -2/+21 |
| * | Add a simple optimization to simplify the input to | Chris Lattner | 2007-10-13 | 1 | -0/+42 |
| * | Correct swapped arguments to getConstant. | Duncan Sands | 2007-10-10 | 1 | -1/+1 |
| * | DAGCombiner support for UDIVREM/SDIVREM and UMUL_LOHI/SMUL_LOHI. | Dan Gohman | 2007-10-08 | 1 | -17/+137 |
| * | Reapply 42677. | Evan Cheng | 2007-10-06 | 1 | -3/+52 |
| * | revert evan's patch until the header is committed | Chris Lattner | 2007-10-06 | 1 | -52/+3 |
| * | Added DAG xforms. e.g. | Evan Cheng | 2007-10-06 | 1 | -3/+52 |
| * | Fix a bogus splat xform: | Evan Cheng | 2007-09-18 | 1 | -2/+1 |
| * | Prevent crash on long double. | Dale Johannesen | 2007-09-18 | 1 | -0/+4 |
| * | Revise previous patch per review comments. | Dale Johannesen | 2007-09-12 | 1 | -5/+5 |
| * | Add APInt interfaces to APFloat (allows directly | Dale Johannesen | 2007-09-11 | 1 | -3/+5 |
| * | Emit: | Chris Lattner | 2007-09-10 | 1 | -0/+10 |
| * | Add mod, copysign, abs operations to APFloat. | Dale Johannesen | 2007-08-31 | 1 | -7/+9 |
| * | Make DAGCombiner's global alias analysis query more precise in the case | Dan Gohman | 2007-08-27 | 1 | -2/+3 |
| * | Revise per review comments. | Dale Johannesen | 2007-08-26 | 1 | -1/+1 |
| * | Add APFloat interface to ConstantFPSDNode. Change | Dale Johannesen | 2007-08-25 | 1 | -10/+6 |
