2009-02-03 |
Dale Johannesen | Add some DL propagation to places that didn't |
blob | commitdiff | raw |
2009-02-03 |
Dale Johannesen | DebugLoc propagation. done with file. |
blob | commitdiff | raw | diff to current |
2009-02-03 |
Dale Johannesen | DebugLoc propagation. 2/3 through file. |
blob | commitdiff | raw | diff to current |
2009-02-02 |
Evan Cheng | ADD / SUB / SMUL / UMUL with overflow second result... |
blob | commitdiff | raw | diff to current |
2009-02-02 |
Evan Cheng | Add comment. |
blob | commitdiff | raw | diff to current |
2009-02-02 |
Evan Cheng | Teach LowerBRCOND to recognize (xor (setcc x), 1).... |
blob | commitdiff | raw | diff to current |
2009-02-01 |
Torok Edwin | Implement -mno-sse: if SSE is disabled on x86-64, don... |
blob | commitdiff | raw | diff to current |
2009-02-01 |
Duncan Sands | Fix PR3453 and probably a bunch of other potential |
blob | commitdiff | raw | diff to current |
2009-01-30 |
Dale Johannesen | Make LowerCallTo and LowerArguments take a DebugLoc |
blob | commitdiff | raw | diff to current |
2009-01-30 |
Bill Wendling | Get rid of the non-DebugLoc-ified getNOT() method. |
blob | commitdiff | raw | diff to current |
2009-01-30 |
Mon P Wang | When PerformBuildVectorCombine, avoid creating a X86ISD... |
blob | commitdiff | raw | diff to current |
2009-01-29 |
Dan Gohman | Make x86's BT instruction matching more thorough, and... |
blob | commitdiff | raw | diff to current |
2009-01-28 |
Mon P Wang | Fixed lowering of v816 shuffles. |
blob | commitdiff | raw | diff to current |
2009-01-28 |
Mon P Wang | Add shuffle splat pattern for x86 sse shifts. |
blob | commitdiff | raw | diff to current |
2009-01-26 |
Dan Gohman | Take the next steps in making SDUse more consistent... |
blob | commitdiff | raw | diff to current |
2009-01-26 |
Nate Begeman | De-identifying per sabre review |
blob | commitdiff | raw | diff to current |
2009-01-26 |
Nate Begeman | Support pattern matching various x86 sse shifts. |
blob | commitdiff | raw | diff to current |
2009-01-22 |
Bob Wilson | Add SelectionDAG::getNOT method to construct bitwise... |
blob | commitdiff | raw | diff to current |
2009-01-19 |
Evan Cheng | Minor tweak to LowerUINT_TO_FP_i32. Bias (after scalar_... |
blob | commitdiff | raw | diff to current |
2009-01-19 |
Evan Cheng | Now not UINT_TO_FP is legal (it's marked custom), dag... |
blob | commitdiff | raw | diff to current |
2009-01-17 |
Bill Wendling | Extend thi |
blob | commitdiff | raw | diff to current |
2009-01-17 |
Bill Wendling | Temporarily revert my last change. It is causing a... |
blob | commitdiff | raw | diff to current |
2009-01-17 |
Bill Wendling | Implement a special algorithm for converting uint_to_fp... |
blob | commitdiff | raw | diff to current |
2009-01-16 |
Bill Wendling | Add support for non-zero __builtin_return_address value... |
blob | commitdiff | raw | diff to current |
2009-01-15 |
Mon P Wang | Expand insert/extract of a <4 x i32> with a variable... |
blob | commitdiff | raw | diff to current |
2009-01-15 |
Dan Gohman | Make getWidenVectorType const. |
blob | commitdiff | raw | diff to current |
2009-01-13 |
Dan Gohman | BT appears to be available on all >= i386 chips. |
blob | commitdiff | raw | diff to current |
2009-01-13 |
Dan Gohman | Don't use a BT instruction if the AND has multiple... |
blob | commitdiff | raw | diff to current |
2009-01-13 |
Devang Patel | Use DebugInfo interface to lower dbg_* intrinsics. |
blob | commitdiff | raw | diff to current |
2009-01-07 |
Dan Gohman | X86_COND_C and X86_COND_NC are alternate mnemonics for |
blob | commitdiff | raw | diff to current |
2009-01-05 |
Devang Patel | squash warnings. |
blob | commitdiff | raw | diff to current |
2009-01-02 |
Evan Cheng | Use movaps / movd to extract vector element 0 even... |
blob | commitdiff | raw | diff to current |
2009-01-01 |
Duncan Sands | Fix PR3274: when promoting the condition of a BRCOND... |
blob | commitdiff | raw | diff to current |
2008-12-25 |
Chris Lattner | Add a simple pattern for matching 'bt'. |
blob | commitdiff | raw | diff to current |
2008-12-24 |
Chris Lattner | translateX86CC can never fail. Simplify it based on... |
blob | commitdiff | raw | diff to current |
2008-12-24 |
Chris Lattner | indentation |
blob | commitdiff | raw | diff to current |
2008-12-23 |
Chris Lattner | simplify some control flow and reduce indentation,... |
blob | commitdiff | raw | diff to current |
2008-12-23 |
Dan Gohman | Add instruction patterns and encodings for the x86... |
blob | commitdiff | raw | diff to current |
2008-12-23 |
Dan Gohman | Clean up the atomic opcodes in SelectionDAG. |
blob | commitdiff | raw | diff to current |
2008-12-23 |
Mon P Wang | Fixed code generation for v8i16 and v16i8 splats on... |
blob | commitdiff | raw | diff to current |
2008-12-18 |
Mon P Wang | Fixed x86 code generation of multiple for v2i64. It... |
blob | commitdiff | raw | diff to current |
2008-12-12 |
Bill Wendling | - Use patterns instead of creating completely new instr... |
blob | commitdiff | raw | diff to current |
2008-12-12 |
Mon P Wang | Added support for SELECT v8i8 v4i16 for X86 (MMX) |
blob | commitdiff | raw | diff to current |
2008-12-12 |
Bill Wendling | Redo the arithmetic with overflow architecture. I was... |
blob | commitdiff | raw | diff to current |
2008-12-10 |
Bill Wendling | Whitespace changes. |
blob | commitdiff | raw | diff to current |
2008-12-09 |
Bill Wendling | Add sub/mul overflow intrinsics. This currently doesn... |
blob | commitdiff | raw | diff to current |
2008-12-05 |
Dale Johannesen | Make LoopStrengthReduce smarter about hoisting things... |
blob | commitdiff | raw | diff to current |
2008-12-03 |
Evan Cheng | Refactor code. No functionality change. |
blob | commitdiff | raw | diff to current |
2008-12-03 |
Bill Wendling | CC should only be a ConstantSDNode at this point. Just... |
blob | commitdiff | raw | diff to current |
2008-12-02 |
Bill Wendling | Second stab at target-dependent lowering of everyone... |
blob | commitdiff | raw | diff to current |
2008-12-01 |
Duncan Sands | There are no longer any places that require a |
blob | commitdiff | raw | diff to current |
2008-12-01 |
Duncan Sands | Change the interface to the type legalization method |
blob | commitdiff | raw | diff to current |
2008-11-27 |
Bill Wendling | Comment out code that isn't entirely correct. |
blob | commitdiff | raw | diff to current |
2008-11-26 |
Bill Wendling | Generate something sensible for an [SU]ADDO op when... |
blob | commitdiff | raw | diff to current |
2008-11-24 |
Bill Wendling | - Make lowering of "add with overflow" customizable... |
blob | commitdiff | raw | diff to current |
2008-11-24 |
Mon P Wang | Added missing description for -disable-mmx option. |
blob | commitdiff | raw | diff to current |
2008-11-23 |
Duncan Sands | Rename SetCCResultContents to BooleanContents. In |
blob | commitdiff | raw | diff to current |
2008-11-23 |
Mon P Wang | Added -disable-mmx using a patch from Preston Gurd. |
blob | commitdiff | raw | diff to current |
2008-11-13 |
Dale Johannesen | Extend InlineAsm::C_Register to allow multiple specific... |
blob | commitdiff | raw | diff to current |
2008-11-06 |
Mon P Wang | Widening cleanup |
blob | commitdiff | raw | diff to current |
2008-11-05 |
Evan Cheng | Indentation. |
blob | commitdiff | raw | diff to current |
2008-10-31 |
Dan Gohman | Use MOVSSmr instead of EXTRACTPSmr in the case of extra... |
blob | commitdiff | raw | diff to current |
2008-10-30 |
Mon P Wang | Add initial support for vector widening. Logic is... |
blob | commitdiff | raw | diff to current |
2008-10-28 |
Chris Lattner | Fix a nasty miscompilation of 176.gcc on linux/x86... |
blob | commitdiff | raw | diff to current |
2008-10-24 |
Duncan Sands | Fix translateX86CC: if SetCCOpcode is SETULE and |
blob | commitdiff | raw | diff to current |
2008-10-22 |
Dale Johannesen | Remove allocation of unused stack slot. |
blob | commitdiff | raw | diff to current |
2008-10-22 |
Duncan Sands | Get this working with LegalizeTypes: (1) don't |
blob | commitdiff | raw | diff to current |
2008-10-22 |
Dale Johannesen | Adjust comments for pedantic satisfaction. |
blob | commitdiff | raw | diff to current |
2008-10-21 |
Dale Johannesen | Add comments to explain uint64->f64 algorithm, |
blob | commitdiff | raw | diff to current |
2008-10-21 |
Dale Johannesen | Add an SSE2 algorithm for uint64->f64 conversion. |
blob | commitdiff | raw | diff to current |
2008-10-21 |
Dan Gohman | Don't create TargetGlobalAddress nodes with offsets... |
blob | commitdiff | raw | diff to current |
2008-10-21 |
Dan Gohman | Optimized FCMP_OEQ and FCMP_UNE for x86. |
blob | commitdiff | raw | diff to current |
2008-10-20 |
Duncan Sands | Have X86 custom lowering for LegalizeTypes use |
blob | commitdiff | raw | diff to current |
2008-10-18 |
Dan Gohman | Teach DAGCombine to fold constant offsets into GlobalAd... |
blob | commitdiff | raw | diff to current |
2008-10-17 |
Chris Lattner | add support for 128 bit inputs on both x86-64 and x86-32. |
blob | commitdiff | raw | diff to current |
2008-10-17 |
Chris Lattner | Fix a bug where the x86 backend would reject 64-bit... |
blob | commitdiff | raw | diff to current |
2008-10-16 |
Dan Gohman | Remove an unused variable. |
blob | commitdiff | raw | diff to current |
2008-10-15 |
Evan Cheng | - Add target lowering hooks that specify which setcc... |
blob | commitdiff | raw | diff to current |
2008-10-14 |
Dan Gohman | FastISel support for exception-handling constructs. |
blob | commitdiff | raw | diff to current |
2008-10-14 |
Evan Cheng | Rename LoadX to LoadExt. |
blob | commitdiff | raw | diff to current |
2008-10-11 |
Chris Lattner | Change CALLSEQ_BEGIN and CALLSEQ_END to take TargetCons... |
blob | commitdiff | raw | diff to current |
2008-10-09 |
Dale Johannesen | Add a "loses information" return value to APFloat:... |
blob | commitdiff | raw | diff to current |
2008-10-06 |
Evan Cheng | Fix PR2850 and PR2863. Only generate movddup for 128... |
blob | commitdiff | raw | diff to current |
2008-10-03 |
Dale Johannesen | Make atomic Swap work, 64-bit on x86-32. |
blob | commitdiff | raw | diff to current |
2008-10-03 |
Dale Johannesen | Pass MemOperand through for 64-bit atomics on 32-bit, |
blob | commitdiff | raw | diff to current |
2008-10-03 |
Dan Gohman | Switch the MachineOperand accessors back to the short... |
blob | commitdiff | raw | diff to current |
2008-10-02 |
Dale Johannesen | Handle some 64-bit atomics on x86-32, some of the time. |
blob | commitdiff | raw | diff to current |
2008-10-01 |
Bill Wendling | Implement the -fno-builtin option in the front-end... |
blob | commitdiff | raw | diff to current |
2008-09-30 |
Bill Wendling | Just don't transform this memset into "bzero" if no... |
blob | commitdiff | raw | diff to current |
2008-09-30 |
Bill Wendling | Add the new `-no-builtin' flag. This flag is meant... |
blob | commitdiff | raw | diff to current |
2008-09-29 |
Dale Johannesen | Remove misuse of ReplaceNodeResults for atomics with |
blob | commitdiff | raw | diff to current |
2008-09-27 |
Evan Cheng | Re-apply 56683 with fixes. |
blob | commitdiff | raw | diff to current |
2008-09-26 |
Bill Wendling | Temporarily reverting r56683. This is causing a failure... |
blob | commitdiff | raw | diff to current |
2008-09-26 |
Dan Gohman | Rename ConstantSDNode's getSignExtended to getSExtValue... |
blob | commitdiff | raw | diff to current |
2008-09-26 |
Evan Cheng | Fix @llvm.frameaddress codegen. FP elimination optimiza... |
blob | commitdiff | raw | diff to current |
2008-09-26 |
Dale Johannesen | Add "inreg" field to CallSDNode (doesn't increase |
blob | commitdiff | raw | diff to current |
2008-09-25 |
Evan Cheng | Prefer movlhps over punpcklqdq, etc. in more cases. |
blob | commitdiff | raw | diff to current |
2008-09-25 |
Devang Patel | Large mechanical patch. |
blob | commitdiff | raw | diff to current |
2008-09-25 |
Evan Cheng | With sse3 and when the source is a load or has multiple... |
blob | commitdiff | raw | diff to current |
2008-09-24 |
Evan Cheng | X86ISD::VZEXT_LOAD should produce and fold a chain. |
blob | commitdiff | raw | diff to current |
next |