summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/X86/X86ISelPattern.cpp
Commit message (Expand)AuthorAgeFilesLines
* Kill the x86 pattern isel. boom.Nate Begeman2006-02-171-3648/+0
* provide an explicit alignment for cp entriesChris Lattner2006-02-091-6/+22
* remove now-dead code, the legalizer takes care of this for usChris Lattner2006-01-291-6/+1
* x86 CPU detection and proper subtarget supportEvan Cheng2006-01-271-0/+4
* Loosen up these checks to allow direct uses of ESPChris Lattner2006-01-251-4/+12
* Add explicit #includes of <iostream>Chris Lattner2006-01-221-0/+1
* Rename fcmovae to fcmovnb and fcmova to fcmovnbe (following Intel manual).Evan Cheng2006-01-211-1/+1
* Use the default lowering of ISD::DYNAMIC_STACKALLOC, delete now dead code.Chris Lattner2006-01-151-41/+0
* Fix a bug in my last X86 checkin, pointed out by cozmicChris Lattner2006-01-131-1/+2
* Enable X86 support for savestack/restorestackChris Lattner2006-01-131-1/+1
* Fix sint_to_fp (fild*) support.Evan Cheng2006-01-121-2/+2
* Support for MEMCPY and MEMSET.Evan Cheng2006-01-111-2/+2
* * Add special entry code main() (to set x87 to 64-bit precision).Evan Cheng2006-01-111-3/+6
* implement FP_REG_KILL insertion for the dag-dag instruction selectorChris Lattner2006-01-111-1/+0
* silence a bogus gcc warningChris Lattner2006-01-061-1/+1
* Rewrite FP stackifier support in the X86InstrInfo.td file, splitting patternsChris Lattner2005-12-211-38/+38
* Fixed a typo: line 2323: MOVSX16rm8 -> MOVZX16rm8. This was the cause fo 12/1...Evan Cheng2005-12-141-1/+1
* Fix PR672 another way which should be more robustChris Lattner2005-12-041-16/+14
* Fix test/Regression/ExecutionEngine/2005-12-02-TailCallBug.ll and PR672.Chris Lattner2005-12-031-0/+14
* The second patch of X86 support for read cycle counter.Andrew Lenharth2005-11-201-0/+5
* Separate X86ISelLowering stuff out from the X86ISelPattern.cpp file. PatchChris Lattner2005-11-151-1002/+3
* Invert the TargetLowering flag that controls divide by consant expansion.Nate Begeman2005-10-211-54/+0
* Remove some dead code now that the dag combiner exists.Nate Begeman2005-10-151-15/+0
* Properly split f32 and f64 into separate register classes for scalar sse fpNate Begeman2005-10-141-4/+4
* silence some warningsChris Lattner2005-10-021-3/+2
* Add FP versions of the binary operators, keeping the int and fp worlds seperate.Chris Lattner2005-09-281-6/+21
* fix a major regression from my patch this afternoonChris Lattner2005-09-141-0/+1
* This code is no longer needed, it is moved to the target-indep codeChris Lattner2005-09-131-25/+0
* Handle any_extend like zextChris Lattner2005-09-021-0/+1
* Adjust to member variable name change.Reid Spencer2005-08-271-1/+1
* Fix a bug in my previous checkinChris Lattner2005-08-261-1/+1
* Change ConstantPoolSDNode to actually hold the Constant itself instead ofChris Lattner2005-08-261-4/+9
* Fix a warningChris Lattner2005-08-251-0/+1
* The variable SAR's only take one operand tooChris Lattner2005-08-191-1/+1
* Stop adding bogus operands to variable shifts on X86. These instructionsChris Lattner2005-08-191-2/+2
* update the backends to work with the new CopyFromReg/CopyToReg/ImplicitDef nodesChris Lattner2005-08-161-28/+26
* Implement BR_CC and BRTWOWAY_CC. This allows the removal of a rather nastyNate Begeman2005-08-161-0/+1
* Fix last night's X86 regressions by putting code for SSE in the if(SSE)Nate Begeman2005-08-141-5/+5
* Fix FP_TO_UINT with Scalar SSE2 now that the legalizer can handle it. WeNate Begeman2005-08-141-1/+9
* Update the targets to the new SETCC/CondCodeSDNode interfaces.Chris Lattner2005-08-091-54/+55
* adjust to change in getSubtarget() apiChris Lattner2005-08-051-1/+1
* Scalar SSE: load +0.0 -> xorps/xorpdNate Begeman2005-08-031-80/+122
* Update to use the new MathExtras.h support for log2 computation.Chris Lattner2005-08-021-1/+1
* Keep tabs and trailing spaces out.Jeff Cohen2005-07-301-14/+14
* fix a typeoChris Lattner2005-07-301-1/+1
* Change the fp to integer code to not perform 2-byte stores followed byChris Lattner2005-07-301-7/+4
* Use a custom expander for all FP to int conversions, as the X86 only hasChris Lattner2005-07-301-71/+41
* Implement a FIXME: move a bunch of cruft for handling FP_TO_*INT operationsChris Lattner2005-07-291-27/+17
* Don't forget to diddle with the control word when performing an FISTP64.Chris Lattner2005-07-291-8/+36
* Use a custom expander to compile this:Chris Lattner2005-07-291-13/+57
OpenPOWER on IntegriCloud