aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/X86
Commit message (Expand)AuthorAgeFilesLines
* Pad Short Functions for Intel AtomPreston Gurd2013-01-087-3/+194
* Renamed MCInstFragment to MCRelaxableFragment and added some comments.Eli Bendersky2013-01-081-2/+2
* Change SMRange to be half-open (exclusive end) instead of closed (inclusive)Jordan Rose2013-01-071-30/+26
* Remove # from the beginning and end of def names.Craig Topper2013-01-074-283/+283
* Remove unnecessary # tokens at the beginning and end of defm names.Craig Topper2013-01-071-10/+10
* Fix the enumerator names for ShuffleKind to match tho coding standards,Chandler Carruth2013-01-071-1/+1
* Make the popcnt support enums and methods have more clear names andChandler Carruth2013-01-071-3/+3
* Move TargetTransformInfo to live under the Analysis library. This noChandler Carruth2013-01-071-1/+1
* Switch TargetTransformInfo from an immutable analysis pass that requiresChandler Carruth2013-01-077-318/+377
* Fix suffix handling for parsing and printing of cvtsi2ss, cvtsi2sd, cvtss2si,...Craig Topper2013-01-061-27/+100
* Fix for PR14739. It's not safe to fold a load into a call across a store. Tha...Evan Cheng2013-01-061-0/+5
* Recommit r171461 which was incorrectly reverted. Mark DIV/IDIV instructions h...Craig Topper2013-01-051-1/+1
* Revert revision 171524. Original message:Nadav Rotem2013-01-057-206/+3
* Move 'break' to the right place to prevent fallthru. There is no test-caseJakub Staszak2013-01-041-1/+1
* The current Intel Atom microarchitecture has a feature whereby when a functionPreston Gurd2013-01-047-3/+206
* LoopVectorizer:Nadav Rotem2013-01-042-0/+9
* Revert revision: 171467. This transformation is incorrect and makes some test...Nadav Rotem2013-01-041-20/+3
* Simplified TRUNCATE operation that comes after SETCC. It is possible since SE...Elena Demikhovsky2013-01-031-3/+20
* Revert "Mark DIV/IDIV instructions hasSideEffects=1 because they can trap whe...Michael Gottesman2013-01-031-1/+1
* Mark DIV/IDIV instructions hasSideEffects=1 because they can trap when dividi...Craig Topper2013-01-031-1/+1
* Add a subtype parameter to VTTI::getShuffleCostHal Finkel2013-01-032-3/+5
* Adds missing aliases for fcom and fcomp instructions without arguments.Kevin Enderby2013-01-021-0/+2
* AVX: Fix a bug in WidenMaskArithmetic.Nadav Rotem2013-01-021-1/+1
* Move all of the header files which are involved in modelling the LLVM IRChandler Carruth2013-01-0217-40/+40
* Merge SSE and AVX instruction definitions for scalar forms of SQRT, RSQRT, an...Craig Topper2013-01-021-82/+97
* Merge SSE and AVX instruction definitions for PSHUFD/PSHUFHW/PSHUFLW.Craig Topper2013-01-021-62/+61
* Revert 171351. It broke MC/X86/x86-32-avx.s.Rafael Espindola2013-01-021-97/+82
* Merge SSE and AVX instruction definitions for scalar forms of SQRT, RSQRT, an...Craig Topper2013-01-011-82/+97
* Remove unused argument from a multiclass.Craig Topper2013-01-011-5/+3
* Merge intrinsic instruction definitions for SSE and AVX versions of RCPPS and...Craig Topper2013-01-011-30/+34
* Remove 2 unused multiclasses.Craig Topper2013-01-011-26/+0
* Merge AVX/SSE instruction definitions for SQRTPS/PD, RSQRTPS, RCPPS. No funci...Craig Topper2013-01-011-47/+58
* Use packed instead of scalar itineraries for SSE1/2 SQRTPS/PD, RCPPS, and RSQ...Craig Topper2012-12-311-6/+6
* Use the predicate methods off of AttributeSet instead of Attribute.Bill Wendling2012-12-301-1/+1
* Remove the Function::getRetAttributes method in favor of using the AttributeS...Bill Wendling2012-12-301-4/+2
* Remove the Function::getFnAttributes method in favor of using the AttributeSetBill Wendling2012-12-305-19/+24
* Remove intrinsic specific instructions for (V)SQRTPS/PD. Instead lower to tar...Craig Topper2012-12-293-26/+7
* Merge similar functionality using a nested switch.Craig Topper2012-12-291-8/+39
* Remove intrinsic specific instructions for SSE/SSE2/AVX floating point max/mi...Craig Topper2012-12-293-74/+29
* Simplify code, no functionality change.Jakub Staszak2012-12-291-19/+14
* CostModel: initial checkin for code that estimates the cost of special shuffles.Nadav Rotem2012-12-282-0/+18
* wrap 80-col lines.Nadav Rotem2012-12-281-2/+5
* AVX: Move the ZEXT/ANYEXT DAGCo optimizations to the lowering of these optimi...Nadav Rotem2012-12-282-45/+71
* Reverse the 'if' condition and reduce the indentation.Nadav Rotem2012-12-271-29/+28
* Merge basic_sse12_fp_binop_p_int and basic_sse12_fp_binop_p_y_int multiclasses.Craig Topper2012-12-271-28/+28
* AVX/AVX2: Move the SEXT lowering code from a target specific DAGco to a lower...Nadav Rotem2012-12-272-42/+53
* Merge basic_sse12_fp_binop_p and basic_sse12_fp_binop_p_y multiclasses.Craig Topper2012-12-271-49/+41
* On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sizedNadav Rotem2012-12-271-15/+106
* AVX/AVX2: Move the code that lowers vector-trunc from a DAGCo-hook to custom ...Nadav Rotem2012-12-271-106/+96
* Add hasSideEffects=0 to some forms of ROUND, RCP, and RSQRT.Craig Topper2012-12-271-0/+3