summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp
Commit message (Expand)AuthorAgeFilesLines
* [LegalizeTypes] Add SoftenFloatResult support for STRICT_SINT_TO_FP/STRICT_UI...Andrew Wei2020-01-141-8/+16
* [X86] Adding fp128 support for strict fcmpWang, Pengfei2020-01-081-16/+31
* [LegalizeTypes] Teach BitcastToInt_ATOMIC_SWAP to only create FP16_TO_FP when...Craig Topper2019-12-141-4/+9
* [LegalizeTypes] In PromoteFloatOp_SETCC, don't both querying for transforming...Craig Topper2019-12-141-2/+1
* [LegalizeTypes] Remove unnecessary if before calling ReplaceValueWith on the ...Craig Topper2019-12-131-2/+1
* [LegalizeTypes] In SoftenFloatRes_FP_EXTEND, move the check for input already...Craig Topper2019-12-111-9/+8
* [LegalizeTypes] Remove manual worklist management from SoftenFloatRes_FP_EXTEND.Craig Topper2019-12-101-3/+0
* [LegalizeTypes] Add missing case for STRICT_FP_ROUND softeningJohn Brawn2019-12-061-0/+1
* [FPEnv] [PowerPC] Lowering ppc_fp128 StrictFP Nodes to libcallsCraig Topper2019-12-031-181/+245
* [LegalizeTypes] Add strict FP support to SoftenFloatRes_FP_ROUND. Fix mistake...Craig Topper2019-11-281-6/+13
* [LegalizeTypes] In SoftenFloatRes_FNEG, always generate integer arithmetic, n...Craig Topper2019-11-281-19/+4
* [LegalizeTypes] Use SoftenFloatRes_Unary in SoftenFloatRes_FCBRT to reduce code.Craig Topper2019-11-281-8/+2
* [LegalizeTypes] Remove dead code related to softening f16 which we no longer do.Craig Topper2019-11-271-26/+0
* [LegalTypes][X86] Add SoftenFloatOperand support for STRICT_FP_TO_SINT/STRICT...Craig Topper2019-11-271-8/+22
* [LegalizeTypes][FPEnv][X86] Add initial support for softening strict fp nodesCraig Topper2019-11-271-44/+146
* [LegalizeTypes] Add SoftenFloatOp_Unary to reduce some duplication for soften...Craig Topper2019-11-261-54/+35
* [LegalizeTypes] Add SoftenFloatRes_Unary and SoftenFloatRes_Binary functions ...Craig Topper2019-11-261-281/+155
* [LegalizeTypes][RISCV] Soften FCOPYSIGN operandLuís Marques2019-11-261-0/+35
* [LegalizeTypes] Remove code to create ISD::FP_TO_FP16 from SoftenFloatRes_FTR...Craig Topper2019-11-251-3/+0
* [LegalizeTypes] Remove unnecessary conversion from EVT to MVT to MVT::SimpleV...Craig Topper2019-11-171-8/+8
* [AArch64][X86] Don't assume __powidf2 is available on Windows.Eli Friedman2019-11-081-7/+14
* [Codegen][ARM] Add float softening for cbrtDavid Green2019-10-281-0/+27
* [LegalizeTypes] Remove code for softening a float type to itself.Craig Topper2019-09-121-178/+27
* [LegalizeTypes] Teach SoftenFloatOp_SELECT_CC to handle operand 2 or 3 being ...Craig Topper2019-09-101-2/+14
* [TargetLowering] Fix Bugzilla ID 43183 to avoid soften comparison broken with...Shiva Chen2019-09-011-35/+81
* [X86] Make inline assembly 'x' and 'v' constraints work for f128.Craig Topper2019-08-291-2/+6
* [RISCV] Avoid generating AssertZext for LP64 ABI when lowering floating LibCallShiva Chen2019-08-281-3/+41
* [TargetLowering] Remove optional arguments passing to makeLibCallShiva Chen2019-08-221-48/+97
* AMDGPU: Correct behavior of f16 buffer loadsMatt Arsenault2019-08-051-0/+6
* [CodeGen] Add lrint/llrint builtinsAdhemerval Zanella2019-05-281-0/+56
* [CodeGen] Add lround/llround builtinsAdhemerval Zanella2019-05-161-0/+55
* [LegalizeTypes] Expand FNEG to bitwise op for IEEE FP typesAna Pazos2019-02-111-0/+9
* [LegalizeTypes] Add debug prints to the top of PromoteFloatOperand and Promot...Craig Topper2019-01-221-0/+12
* Update the file headers across all of the LLVM projects in the monorepoChandler Carruth2019-01-191-4/+3
* Allow FP types for atomicrmw xchgMatt Arsenault2019-01-171-1/+28
* [Legalizer] Use correct ValueType of SELECT_CC node during Float promotionPirama Arumuga Nainar2019-01-111-3/+3
* [NFC] Rename minnan and maxnan to minimum and maximumThomas Lively2018-10-241-2/+2
* DAG: Try to custom lower when promoting float operandsMatt Arsenault2018-08-151-0/+5
* [SelectionDAG] In PromoteFloatOp_BITCAST, insert a bitcast after the fp_to_fp...Craig Topper2018-08-131-8/+11
* [SelectionDAG] In PromoteFloatRes_BITCAST, insert a bitcast before the fp16_t...Craig Topper2018-08-131-2/+4
* DAG: Fix PromoteFloatResult for fcanonicalizeMatt Arsenault2018-07-311-1/+2
* Remove trailing spaceFangrui Song2018-07-301-3/+3
* DAG: Stop dropping invariant/dereferencableMatt Arsenault2018-06-051-4/+3
* Rename DEBUG macro to LLVM_DEBUG.Nicola Zaghen2018-05-141-6/+6
* [PowerPC][LegalizeFloatTypes] Move the PPC hacks for (i32 fp_to_sint/fp_to_ui...Craig Topper2018-03-201-37/+0
* [SelectionDAG][X86] Don't use ->getValueType(0) after a call to getOperand to...Craig Topper2017-12-231-1/+1
* [legalize-types] Clean up softening machinery.Anton Yartsev2017-07-041-20/+73
* Revert "[APInt] Fix a few places that use APInt::getRawData to operate within...Renato Golin2017-04-231-3/+5
* [APInt] Fix a few places that use APInt::getRawData to operate within the nor...Craig Topper2017-04-231-5/+3
* [X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64.Chih-Hung Hsieh2017-04-181-2/+5
OpenPOWER on IntegriCloud