aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86ISelLowering.cpp
AgeCommit message (Expand)Author
2009-03-13These instructions have special lowering that may lower them to SSEBill Wendling
2009-03-13Fix some significant problems with constant pools that resulted in unnecessar...Evan Cheng
2009-03-13generalize the previous code to use the full generality of LEAChris Lattner
2009-03-13optimize the case of cond ? 42 : 41 and friends. This compiles theChris Lattner
2009-03-12Move 3 "(add (select cc, 0, c), x) -> (select cc, x, (add, x, c))"Chris Lattner
2009-03-12On x86, if the only use of a i64 load is a i64 store, generate a pair of doub...Evan Cheng
2009-03-11Add a -no-implicit-float flag. This acts like -soft-float, but may generateBill Wendling
2009-03-11For yonah, fix a vector shuffle case for v16i8 where we didn't properly clear...Mon P Wang
2009-03-11Fixed a v8i16 shuffle case that should generate a pshufb instead of a pshuflw...Mon P Wang
2009-03-11formatting change, reduce indentation. No functionality change.Chris Lattner
2009-03-07Arithmetic instructions don't set EFLAGS bits OF and CF bitsDan Gohman
2009-03-05When creating X86ISD::INC and X86ISD::DEC nodes, only add one operand.Dan Gohman
2009-03-05Fix the "test" optimization to recognize "dec" as an add ofDan Gohman
2009-03-04Re-apply 66008, now that the unfoldMemoryOperand bug is fixed.Dan Gohman
2009-03-04Revert r66004 for now; it's causing a variety of test failures.Dan Gohman
2009-03-04Teach the x86 backend to eliminate "test" instructions by using the EFLAGSDan Gohman
2009-02-27Refactor TLS code and add some tests. The tests and expected results are:Rafael Espindola
2009-02-25Revert BuildVectorSDNode related patches: 65426, 65427, and 65296.Evan Cheng
2009-02-23Only v1i16 (i.e. _m64) is returned via RAX / RDX.Evan Cheng
2009-02-23Generate better code for v8i16 shuffles on SSE2Nate Begeman
2009-02-22Introduce the BuildVectorSDNode class that encapsulates the ISD::BUILD_VECTORScott Michel
2009-02-22Be bug compatible with gcc by returning MMX values in RAX.Evan Cheng
2009-02-20Support return of MMX values in 64-bit mode.Evan Cheng
2009-02-17Remove trailing whitespace to reduce later commit patch noise.Scott Michel
2009-02-13Teach x86 target -soft-float.Evan Cheng
2009-02-12Arrange to print constants that match "n" and "i" constraintsDale Johannesen
2009-02-07Use getDebugLoc forwarder instead of getNode()->getDebugLoc.Dale Johannesen
2009-02-07Constify TargetInstrInfo::EmitInstrWithCustomInserter, allowingDan Gohman
2009-02-07Get rid of the last non-DebugLoc versions of getNode!Dale Johannesen
2009-02-06Remove more non-DebugLoc getNode variants. UseDale Johannesen
2009-02-06Remove more non-DebugLoc versions of getNode.Dale Johannesen
2009-02-06Get rid of one more non-DebugLoc getNode andDale Johannesen
2009-02-04Remove non-DebugLoc versions of getLoad and getStore.Dale Johannesen
2009-02-04Minor code cleanups; no functionality change.Dan Gohman
2009-02-04Fixes a case where we generate an incorrect mask for pshfhw in the presenceMon P Wang
2009-02-04Patch up omissions in DebugLoc propagation.Dale Johannesen
2009-02-03Add some DL propagation to places that didn'tDale Johannesen
2009-02-03DebugLoc propagation. done with file.Dale Johannesen
2009-02-03DebugLoc propagation. 2/3 through file.Dale Johannesen
2009-02-02ADD / SUB / SMUL / UMUL with overflow second result top bits must be zero.Evan Cheng
2009-02-02Add comment.Evan Cheng
2009-02-02Teach LowerBRCOND to recognize (xor (setcc x), 1). The xor inverts the condit...Evan Cheng
2009-02-01Implement -mno-sse: if SSE is disabled on x86-64, don't store XMM on stack forTorok Edwin
2009-02-01Fix PR3453 and probably a bunch of other potentialDuncan Sands
2009-01-30Make LowerCallTo and LowerArguments take a DebugLocDale Johannesen
2009-01-30Get rid of the non-DebugLoc-ified getNOT() method.Bill Wendling
2009-01-30When PerformBuildVectorCombine, avoid creating a X86ISD::VZEXT_LOAD ofMon P Wang
2009-01-29Make x86's BT instruction matching more thorough, and add someDan Gohman
2009-01-28Fixed lowering of v816 shuffles.Mon P Wang
2009-01-28Add shuffle splat pattern for x86 sse shifts.Mon P Wang