2009-12-18 |
Evan Cheng | Increase opportunities to optimize (brcond (srl (and... |
tree | commitdiff |
2009-12-18 |
Evan Cheng | On recent Intel u-arch's, folding loads into some unary... |
tree | commitdiff |
2009-12-18 |
Dan Gohman | Tidy up this testcase and add test for tailcall optimiz... |
tree | commitdiff |
2009-12-18 |
Dan Gohman | Remove "tail" keywords. These calls are not intended... |
tree | commitdiff |
2009-12-18 |
Sean Callanan | Instruction fixes, added instructions, and AsmString... |
tree | commitdiff |
2009-12-16 |
Evan Cheng | Re-enable 91381 with fixes. |
tree | commitdiff |
2009-12-16 |
Dale Johannesen | Do better with physical reg operands (typically, from... |
tree | commitdiff |
2009-12-15 |
Kenneth Uildriks | For fastcc on x86, let ECX be used as a return register... |
tree | commitdiff |
2009-12-15 |
Evan Cheng | Disable 91381 for now. It's miscompiling ARMISelDAG2DAG... |
tree | commitdiff |
2009-12-15 |
Evan Cheng | Make 91378 more conservative. |
tree | commitdiff |
2009-12-15 |
Evan Cheng | Use sbb x, x to materialize carry bit in a GPR. The... |
tree | commitdiff |
2009-12-15 |
Evan Cheng | Propagate zest through logical shift. |
tree | commitdiff |
2009-12-14 |
Dan Gohman | Fix integer cast code to handle vector types. |
tree | commitdiff |
2009-12-12 |
Evan Cheng | Disable r91104 for x86. It causes partial register... |
tree | commitdiff |
2009-12-11 |
Dan Gohman | Implement vector widening, splitting, and scalarizing... |
tree | commitdiff |
2009-12-11 |
Dan Gohman | Change this to the correct PR number. |
tree | commitdiff |
2009-12-11 |
Dan Gohman | Fix the result type of SELECT nodes lowered from Select... |
tree | commitdiff |
2009-12-11 |
Anton Korobeynikov | Honour setHasCalls() set from isel. |
tree | commitdiff |
2009-12-11 |
Evan Cheng | Tests for 91103 and 91104. |
tree | commitdiff |
2009-12-10 |
Evan Cheng | It's not safe to coalesce a move where src and dst... |
tree | commitdiff |
2009-12-09 |
Evan Cheng | Fix test. |
tree | commitdiff |
2009-12-09 |
Evan Cheng | Optimize splat of a scalar load into a shuffle of a... |
tree | commitdiff |
2009-12-07 |
David Greene | Use FileCheck and set nounwind on calls. |
tree | commitdiff |
2009-12-07 |
Dan Gohman | Don't enable the post-RA scheduler on x86 except at... |
tree | commitdiff |
2009-12-05 |
Bill Wendling | Temporarily revert r90502. It was causing the llvm... |
tree | commitdiff |
2009-12-04 |
Jakob Stoklund Olesen | Also attempt trivial coalescing for live intervals... |
tree | commitdiff |
2009-12-03 |
Nate Begeman | Don't pull vector sext through both hands of a logical... |
tree | commitdiff |
2009-12-02 |
Bill Wendling | Remove unnecessary check. |
tree | commitdiff |
2009-12-01 |
Evan Cheng | Fix PR5391: support early clobber physical register... |
tree | commitdiff |
2009-12-01 |
Jakob Stoklund Olesen | Use CFG connectedness as a secondary sort key when... |
tree | commitdiff |
2009-11-30 |
Jakob Stoklund Olesen | New virtual registers created for spill intervals shoul... |
tree | commitdiff |
2009-11-30 |
Mon P Wang | Add test case for r90108 |
tree | commitdiff |
2009-11-26 |
Evan Cheng | Test for 89905. |
tree | commitdiff |
2009-11-22 |
Benjamin Kramer | Turns out stuff gets allocated to different registers... |
tree | commitdiff |
2009-11-22 |
Edward O'Callaghan | Fix for bad FileCheck converts in revision 89584. |
tree | commitdiff |
2009-11-22 |
Edward O'Callaghan | Convert a few tests to FileCheck for PR5307. |
tree | commitdiff |
2009-11-20 |
Evan Cheng | Enable hoisting load from constant memories. |
tree | commitdiff |
2009-11-20 |
Sean Callanan | Recommitting PALIGNR shift width fixes. |
tree | commitdiff |
2009-11-20 |
Sean Callanan | Reverting PALIGNR fix until I figure out how this |
tree | commitdiff |
2009-11-20 |
Sean Callanan | Fixed PALIGNR to take 8-bit rotations in all cases. |
tree | commitdiff |
2009-11-20 |
Dan Gohman | Fix fast-isel to avoid selecting the return instruction... |
tree | commitdiff |
2009-11-19 |
Bill Wendling | Test from Dhrystone to make sure that we're not emittin... |
tree | commitdiff |
2009-11-18 |
Jakob Stoklund Olesen | Fix PR5300. |
tree | commitdiff |
2009-11-18 |
Jakob Stoklund Olesen | Fix inverted test and add testcase from failing self... |
tree | commitdiff |
2009-11-17 |
Jakob Stoklund Olesen | Remove fragile test. |
tree | commitdiff |
2009-11-17 |
Jakob Stoklund Olesen | Enable -split-phi-edges by default, except when -regall... |
tree | commitdiff |
2009-11-17 |
Evan Cheng | Revert 89021. It's miscompiling llvm-gcc driver driver... |
tree | commitdiff |
2009-11-17 |
Jakob Stoklund Olesen | Enable -split-phi-edges by default |
tree | commitdiff |
2009-11-17 |
Evan Cheng | MOV64rm should be marked isReMaterializable. |
tree | commitdiff |
2009-11-16 |
Dan Gohman | Fix this test - there don't appear to be any actual... |
tree | commitdiff |
2009-11-16 |
Dan Gohman | Revert r87049, which was the workaround for the regress... |
tree | commitdiff |
2009-11-16 |
Evan Cheng | - Check memoperand alignment instead of checking stack... |
tree | commitdiff |
2009-11-16 |
David Greene | Support spill comments. |
tree | commitdiff |
2009-11-14 |
Evan Cheng | Added getSubRegIndex(A,B) that returns subreg index... |
tree | commitdiff |
2009-11-14 |
Dan Gohman | Enable the tail call optimization when the caller retur... |
tree | commitdiff |
2009-11-13 |
Dan Gohman | When optimizing for size, don't tail-merge unless it... |
tree | commitdiff |
2009-11-13 |
Dan Gohman | Don't let a noalias difference disrupt the tailcall... |
tree | commitdiff |
2009-11-13 |
Daniel Dunbar | Update test. |
tree | commitdiff |
2009-11-12 |
Dan Gohman | Tail merge at any size when there are two potentials... |
tree | commitdiff |
2009-11-11 |
Kenneth Uildriks | x86 users can now return arbitrary sized structs. ... |
tree | commitdiff |
2009-11-11 |
Dan Gohman | Add support for tail duplication to BranchFolding,... |
tree | commitdiff |
2009-11-11 |
Evan Cheng | Add nounwind. |
tree | commitdiff |
2009-11-11 |
Bill Wendling | Fix test to work on every platform. |
tree | commitdiff |
2009-11-11 |
Bill Wendling | Make sure that the exception handling data has the... |
tree | commitdiff |
2009-11-09 |
Mike Stump | Add testcase for recent checkin. |
tree | commitdiff |
2009-11-07 |
Nate Begeman | x86 vector shuffle cleanup/fixes: |
tree | commitdiff |
2009-11-07 |
Eric Christopher | Fix a couple of shuffle patterns to use movhlps instead |
tree | commitdiff |
2009-11-07 |
Chris Lattner | merge cmp1 into cmp0 and filecheckize. |
tree | commitdiff |
2009-11-06 |
Eric Christopher | Fix PR5315, original patch by Nicolas Capens! |
tree | commitdiff |
2009-11-04 |
Evan Cheng | RangeIsDefinedByCopyFromReg() should check for subreg_t... |
tree | commitdiff |
2009-11-03 |
Evan Cheng | Re-apply 85799. It turns out my code isn't buggy. |
tree | commitdiff |
2009-11-03 |
Kenneth Uildriks | Make opt default to not adding a target data string... |
tree | commitdiff |
2009-11-02 |
Evan Cheng | Revert 85799 for now. It might be breaking llvm-gcc... |
tree | commitdiff |
2009-11-02 |
Evan Cheng | Initilize the machine LICM CSE map upon the first time... |
tree | commitdiff |
2009-11-01 |
Chris Lattner | improve x86 codegen support for blockaddress. We now... |
tree | commitdiff |
2009-10-31 |
Dan Gohman | Add a target triple so that this test behaves consisten... |
tree | commitdiff |
2009-10-30 |
Dan Gohman | Fix the -mattr line for this test so that it passes... |
tree | commitdiff |
2009-10-30 |
Dan Gohman | Fix MachineLICM to use the correct virtual register... |
tree | commitdiff |
2009-10-30 |
Evan Cheng | I forgot to commit this test. |
tree | commitdiff |
2009-10-28 |
Bob Wilson | Reimplement BranchFolding change to avoid tail merging... |
tree | commitdiff |
2009-10-28 |
Dan Gohman | Teach MachineLICM to unfold loads from constant memory... |
tree | commitdiff |
2009-10-28 |
Dan Gohman | Mark dead physregdefs dead immediately. This helps... |
tree | commitdiff |
2009-10-28 |
Dan Gohman | Allow constants of different types to share constant... |
tree | commitdiff |
2009-10-26 |
David Goodwin | Break anti-dependence breaking out into its own class. |
tree | commitdiff |
2009-10-26 |
Dan Gohman | Make LSR's OptimizeShadowIV ignore induction variables... |
tree | commitdiff |
2009-10-26 |
Evan Cheng | - Revert some changes from 85044, 85045, and 85047... |
tree | commitdiff |
2009-10-25 |
Chris Lattner | fix PR5295 where the .ll parser didn't reject a functio... |
tree | commitdiff |
2009-10-23 |
Dan Gohman | APInt-ify the gep scaling code, so that it correctly... |
tree | commitdiff |
2009-10-23 |
Evan Cheng | Update tests for 84931. |
tree | commitdiff |
2009-10-22 |
David Goodwin | Allow the target to select the level of anti-dependence... |
tree | commitdiff |
2009-10-22 |
Dan Gohman | Revert the main portion of r31856. It was causing Branc... |
tree | commitdiff |
2009-10-21 |
Dan Gohman | Revert r84658 and r84691. They were causing llvm-gcc... |
tree | commitdiff |
2009-10-20 |
David Goodwin | Checkpoint more aggressive anti-dependency breaking... |
tree | commitdiff |
2009-10-20 |
Dan Gohman | Make TranslateX86CC return COND_INVALID instead of... |
tree | commitdiff |
2009-10-20 |
Dan Gohman | Re-apply r84295, with fixes to how the loop "top" and... |
tree | commitdiff |
2009-10-20 |
Evan Cheng | If the physical register being spilled does not have... |
tree | commitdiff |
2009-10-19 |
Anton Korobeynikov | Revert r84295, this unbreaks llvm-gcc bootstrap on... |
tree | commitdiff |
2009-10-19 |
Torok Edwin | Fix PR5247, "lock addq" pattern (and other atomics... |
tree | commitdiff |
2009-10-19 |
Nate Begeman | Add support for matching shuffle patterns with palignr. |
tree | commitdiff |
2009-10-18 |
Evan Cheng | Turn on post-alloc scheduling for x86. |
tree | commitdiff |
next |