| Commit message (Expand) | Author | Age |
* | Be more conservative with clustering f32 / f64 loads. | Evan Cheng | 2010-01-22 |
* | Add two target hooks to determine whether two loads are near and should be sc... | Evan Cheng | 2010-01-22 |
* | Fix a minor issue in x86 load / store folding table. movups does an unaligned... | Evan Cheng | 2010-01-21 |
* | make findDebugLoc a class method | Dale Johannesen | 2010-01-20 |
* | Move findDebugLoc somewhere more central. Fix | Dale Johannesen | 2010-01-20 |
* | For aligned load/store instructions, it's only required to know whether a | Jim Grosbach | 2010-01-19 |
* | For now, avoid issuing extract_subreg to reuse lower 8-bit, it's not safe in ... | Evan Cheng | 2010-01-13 |
* | Add a quick pass to optimize sign / zero extension instructions. For targets ... | Evan Cheng | 2010-01-13 |
* | Reapply the MOV64r0 patch, with a fix: MOV64r0 clobbers EFLAGS. | Dan Gohman | 2010-01-12 |
* | Add TargetInstrInfo::isCoalescableInstr. It returns true if the specified | Evan Cheng | 2010-01-12 |
* | Revert 93158. It's breaking quite a few x86_64 tests. | Evan Cheng | 2010-01-11 |
* | Re-instate MOV64r0 and MOV16r0, with adjustments to work with the | Dan Gohman | 2010-01-11 |
* | Change errs() to dbgs(). | David Greene | 2010-01-05 |
* | Remove dead variable. | Bill Wendling | 2009-12-28 |
* | completely eliminate the MOV16r0 'instruction'. The only | Chris Lattner | 2009-12-23 |
* | Remove target attribute break-sse-dep. Instead, do not fold load into sse par... | Evan Cheng | 2009-12-22 |
* | On recent Intel u-arch's, folding loads into some unary SSE instructions can | Evan Cheng | 2009-12-18 |
* | Instruction fixes, added instructions, and AsmString changes in the | Sean Callanan | 2009-12-18 |
* | Whitespace changes, comment clarification. No functional changes. | Bill Wendling | 2009-12-14 |
* | Disable r91104 for x86. It causes partial register stall which pessimize code... | Evan Cheng | 2009-12-12 |
* | Add comment about potential partial register stall. | Evan Cheng | 2009-12-12 |
* | Add support to 3-addressify 16-bit instructions. | Evan Cheng | 2009-12-11 |
* | Remove the target hook TargetInstrInfo::BlockHasNoFallThrough in favor of | Dan Gohman | 2009-12-05 |
* | Remove an unneeded include. | David Greene | 2009-12-04 |
* | Have hasLoad/StoreFrom/ToStackSlot return the relevant MachineMemOperand. | David Greene | 2009-12-04 |
* | improve portability to avoid conflicting with std::next in c++'0x. | Chris Lattner | 2009-12-03 |
* | Remove ISD::DEBUG_LOC and ISD::DBG_LABEL, which are no longer used. | Dan Gohman | 2009-11-23 |
* | Re-apply 89011. It's not to be blamed. | Evan Cheng | 2009-11-17 |
* | Revert 89011. Buildbot thinks it might be breaking stuff. | Evan Cheng | 2009-11-17 |
* | A few more instructions that should be marked re-materializable. | Evan Cheng | 2009-11-17 |
* | - Check memoperand alignment instead of checking stack alignment. Most load /... | Evan Cheng | 2009-11-16 |
* | - Change TargetInstrInfo::reMaterialize to pass in TargetRegisterInfo. | Evan Cheng | 2009-11-14 |
* | Fix a bootstrap failure. | David Greene | 2009-11-13 |
* | Add hasLoadFromStackSlot and hasStoreToStackSlot to return whether a | David Greene | 2009-11-12 |
* | Fix DenseMap iterator constness. | Jeffrey Yasskin | 2009-11-10 |
* | Fix MachineLICM to use the correct virtual register class when | Dan Gohman | 2009-10-30 |
* | Make isSafeToClobberEFLAGS more aggressive. Teach it to scan backwards | Dan Gohman | 2009-10-14 |
* | Remove a no-longer-necessary #include. | Dan Gohman | 2009-10-10 |
* | Replace X86's CanRematLoadWithDispOperand by calling the target-independent | Dan Gohman | 2009-10-10 |
* | Add basic infrastructure and x86 support for preserving MachineMemOperand | Dan Gohman | 2009-10-09 |
* | Replace TargetInstrInfo::isInvariantLoad and its target-specific | Dan Gohman | 2009-10-07 |
* | Introduce the TargetInstrInfo::KILL machine instruction and get rid of the | Jakob Stoklund Olesen | 2009-09-28 |
* | Improve MachineMemOperand handling. | Dan Gohman | 2009-09-25 |
* | Rename getTargetNode to getMachineNode, for consistency with the | Dan Gohman | 2009-09-25 |
* | Fix X86's unfoldMemoryOperand to properly handle MachineMemOperands. | Dan Gohman | 2009-09-23 |
* | Add support for rematerializing FsFLD0SS and FsFLD0SD as constant-pool | Dan Gohman | 2009-09-21 |
* | Follow up to 81494. When the folded reload is narrowed to a 32-bit load then ... | Evan Cheng | 2009-09-11 |
* | It's not legal to fold a load from a narrower stack slot into a wider instruc... | Evan Cheng | 2009-09-11 |
* | Remove Offset from ExternalSybmol MachineOperands, this is unused (and at lea... | Daniel Dunbar | 2009-09-01 |
* | Short-term workaround for frame-related weirdness on win64. | Anton Korobeynikov | 2009-08-28 |