projects / oota-llvm.git / history
? search:
summary | shortlog | log | commit | commitdiff | tree
first ⋅ prev ⋅ next
R600: Add helper functions.
[oota-llvm.git] / lib / Target / R600 / AMDGPUISelLowering.cpp
2014-06-11 Matt ArsenaultR600: Add helper functions. blob | commitdiff | raw
2014-06-10 Matt ArsenaultR600: Use BCNT_INT for evergreen blob | commitdiff | raw | diff to current
2014-06-10 Matt ArsenaultR600/SI: Use bcnt instruction for ctpop blob | commitdiff | raw | diff to current
2014-06-10 Matt ArsenaultR600: Handle fcopysign blob | commitdiff | raw | diff to current
2014-06-09 Matt ArsenaultR600: Fix selection failure for vector bswap blob | commitdiff | raw | diff to current
2014-06-01 Matt ArsenaultR600: Set all float vector expands in the same place blob | commitdiff | raw | diff to current
2014-05-22 Matt ArsenaultR600: Try to convert BFE back to standard bit ops when... blob | commitdiff | raw | diff to current
2014-05-22 Matt ArsenaultR600: Add dag combine for BFE blob | commitdiff | raw | diff to current
2014-05-22 Matt ArsenaultR600: Implement ComputeNumSignBitsForTargetNode for BFE blob | commitdiff | raw | diff to current
2014-05-22 Matt ArsenaultR600: Implement computeMaskedBitsForTargetNode for BFE blob | commitdiff | raw | diff to current
2014-05-22 Matt ArsenaultR600: Add intrinsics for mad24 blob | commitdiff | raw | diff to current
2014-05-21 Matt ArsenaultR600: Add comment describing problems with LowerConstan... blob | commitdiff | raw | diff to current
2014-05-21 Matt ArsenaultR600: Partially fix constant initializers for structs... blob | commitdiff | raw | diff to current
2014-05-21 Matt ArsenaultUse cast<> instead of unchecked dyn_cast blob | commitdiff | raw | diff to current
2014-05-15 Matt ArsenaultUse range for blob | commitdiff | raw | diff to current
2014-05-14 Jay FoadRename ComputeMaskedBits to computeKnownBits. "Masked... blob | commitdiff | raw | diff to current
2014-05-12 Matt ArsenaultR600: Add mul24 intrinsics blob | commitdiff | raw | diff to current
2014-05-11 Matt ArsenaultFix return before else blob | commitdiff | raw | diff to current
2014-05-09 Tom StellardR600: Expand i64 SELECT_CC blob | commitdiff | raw | diff to current
2014-05-09 Tom StellardR600: Move MIN/MAX matching from LowerOperation() to... blob | commitdiff | raw | diff to current
2014-05-08 Matt ArsenaultR600: Promote f64 vector load/stores to i64 for consistency blob | commitdiff | raw | diff to current
2014-05-05 Tom StellardR600: Expand i64 ISD:SUB blob | commitdiff | raw | diff to current
2014-05-02 Tom StellardR600: Expand vector sin and cos. blob | commitdiff | raw | diff to current
2014-05-02 Tom StellardR600: Expand TruncStore i64 -> {i16,i8} blob | commitdiff | raw | diff to current
2014-04-29 Tom StellardR600: optimize the UDIVREM 64 algorithm blob | commitdiff | raw | diff to current
2014-04-29 Tom StellardR600: Implement iterative algorithm for udivrem blob | commitdiff | raw | diff to current
2014-04-29 Tom StellardR600: Change UDIV/UREM to UDIVREM when legalizing types blob | commitdiff | raw | diff to current
2014-04-29 Tom StellardR600: remove unused variable blob | commitdiff | raw | diff to current
2014-04-28 Craig TopperConvert more SelectionDAG functions to use ArrayRef. blob | commitdiff | raw | diff to current
2014-04-27 Craig TopperConvert SelectionDAG::getMergeValues to use ArrayRef. blob | commitdiff | raw | diff to current
2014-04-26 Craig TopperConvert SelectionDAG::getNode methods to use ArrayRef... blob | commitdiff | raw | diff to current
2014-04-25 Matt ArsenaultR600: Fix function name printing in LowerCall blob | commitdiff | raw | diff to current
2014-04-25 Craig Topper[C++] Use 'nullptr'. Target edition. blob | commitdiff | raw | diff to current
2014-04-22 Matt ArsenaultR600: Emit error instead of unreachable on function... blob | commitdiff | raw | diff to current
2014-04-22 Matt ArsenaultR600: Change how vector truncating stores are packed. blob | commitdiff | raw | diff to current
2014-04-22 Matt ArsenaultR600: Make sign_extend_inreg legal. blob | commitdiff | raw | diff to current
2014-04-17 Tom StellardR600: Add comment clariying use of sext for result... blob | commitdiff | raw | diff to current
2014-04-16 Matt ArsenaultR600: Expand sign extension of vectors. blob | commitdiff | raw | diff to current
2014-04-15 Matt ArsenaultR600/SI: Fix loads of i1 blob | commitdiff | raw | diff to current
2014-04-15 Nick LewyckyBreak PseudoSourceValue out of the Value hierarchy... blob | commitdiff | raw | diff to current
2014-04-11 Matt ArsenaultMove ExtractVectorElements to SelectionDAG. blob | commitdiff | raw | diff to current
2014-04-07 Tom StellardR600: Match 24-bit arithmetic patterns in a Target... blob | commitdiff | raw | diff to current
2014-04-07 Matt ArsenaultUse .data() instead of &x[0] blob | commitdiff | raw | diff to current
2014-03-31 Matt ArsenaultR600: Compute masked bits for min and max blob | commitdiff | raw | diff to current
2014-03-31 Matt ArsenaultR600: Add BFE, BFI, and BFM intrinsics to help with... blob | commitdiff | raw | diff to current
2014-03-31 Matt ArsenaultR600: Add target nodes for BFM and BFI blob | commitdiff | raw | diff to current
2014-03-27 Matt ArsenaultR600: Implement isZExtFree. blob | commitdiff | raw | diff to current
2014-03-27 Matt ArsenaultR600/SI: Fix unreachable with a sext_in_reg to an illeg... blob | commitdiff | raw | diff to current
2014-03-26 Matt ArsenaultR600: Add a testcase for sext_in_reg I missed. blob | commitdiff | raw | diff to current
2014-03-25 Matt ArsenaultR600: Move computeMaskedBitsForTargetNode out of AMDILI... blob | commitdiff | raw | diff to current
2014-03-24 Matt ArsenaultR600: Implement isNarrowingProfitable. blob | commitdiff | raw | diff to current
2014-03-17 Matt ArsenaultR600: Match sign_extend_inreg to BFE instructions blob | commitdiff | raw | diff to current
2014-03-15 Matt ArsenaultR600: Remove unnecessary attempt to zext a pointer. blob | commitdiff | raw | diff to current
2014-03-15 Matt ArsenaultR600: Code cleanup. blob | commitdiff | raw | diff to current
2014-03-12 Matt ArsenaultR600: Fix trunc store from i64 to i1 blob | commitdiff | raw | diff to current
2014-03-11 Matt ArsenaultR600: Calculate store mask instead of using switch. blob | commitdiff | raw | diff to current
2014-03-11 Matt ArsenaultUse .data() instead of &x[0] blob | commitdiff | raw | diff to current
2014-03-06 Matt ArsenaultR600: Fix extloads from i8 / i16 to i64. blob | commitdiff | raw | diff to current
2014-03-06 Matt ArsenaultR600/SI: Expand selects on vectors. blob | commitdiff | raw | diff to current
2014-03-05 Matt ArsenaultFix typo blob | commitdiff | raw | diff to current
2014-02-24 Matt ArsenaultR600/SI - Add new CI arithmetic instructions. blob | commitdiff | raw | diff to current
2014-02-24 Matt ArsenaultFix DOT4 missing from getTargetOpcodeName blob | commitdiff | raw | diff to current
2014-02-13 Tom StellardR600/SI: Expand all v8[if]32 operations blob | commitdiff | raw | diff to current
2014-02-12 Benjamin KramerR600: Always implement both versions of isTruncateFree... blob | commitdiff | raw | diff to current
2014-02-10 Matt ArsenaultR600: Implement isTruncateFree blob | commitdiff | raw | diff to current
2014-02-04 Tom StellardR600/SI: Expand i1 BR_CC blob | commitdiff | raw | diff to current
2014-02-04 Tom StellardR600: Enable vector fpow. blob | commitdiff | raw | diff to current
2014-01-22 Tom StellardR600: Add support for global addresses with constant... blob | commitdiff | raw | diff to current
2014-01-22 Tom StellardR600/SI: Add support for i8 and i16 private loads/stores blob | commitdiff | raw | diff to current
2013-12-20 Tom StellardR600: Allow ftrunc blob | commitdiff | raw | diff to current
2013-12-14 Matt ArsenaultDon't manually calculate size in bytes blob | commitdiff | raw | diff to current
2013-12-10 Matt ArsenaultUse llvm_unreachable instead of assert(0) blob | commitdiff | raw | diff to current
2013-11-27 Tom StellardR600: Expand vector FABS blob | commitdiff | raw | diff to current
2013-11-27 Tom StellardR600: Add support for ISD::FROUND blob | commitdiff | raw | diff to current
2013-11-15 Matt ArsenaultAdd target hook to prevent folding some bitcasted loads. blob | commitdiff | raw | diff to current
2013-11-13 Tom StellardR600/SI: Add support for private address space load... blob | commitdiff | raw | diff to current
2013-11-06 Vincent LejeuneR600: Fix LowerUDIVREM blob | commitdiff | raw | diff to current
2013-10-30 Tom StellardR600: Custom lower f32 = uint_to_fp i64 blob | commitdiff | raw | diff to current
2013-10-29 Tom StellardR600: Expand vector FSQRT ops blob | commitdiff | raw | diff to current
2013-10-23 Tom StellardR600: Fix handling of vector kernel arguments blob | commitdiff | raw | diff to current
2013-09-12 Tom StellardR600/SI: expose TBUFFER_STORE_FORMAT_* for OpenGL trans... blob | commitdiff | raw | diff to current
2013-09-05 Tom StellardR600: Fix incorrect LDS size calculation blob | commitdiff | raw | diff to current
2013-08-26 Tom StellardR600: Add support for vector local memory loads blob | commitdiff | raw | diff to current
2013-08-26 Tom StellardR600: Add support for i8 and i16 local memory stores blob | commitdiff | raw | diff to current
2013-08-26 Tom StellardR600: Add support for v4i32 and v2i32 local stores blob | commitdiff | raw | diff to current
2013-08-26 Tom StellardSelectionDAG: Use correct pointer size when lowering... blob | commitdiff | raw | diff to current
2013-08-21 Tom StellardR600: Remove unnecessary casts blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Expand vector FRINT ops blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Expand vector FFLOOR ops blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Expand vector float operations for both SI and... blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Add support for global vector loads with element... blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Add support for global vector stores with element... blob | commitdiff | raw | diff to current
2013-08-16 Tom StellardR600: Add support for i16 and i8 global stores blob | commitdiff | raw | diff to current
2013-08-14 Tom StellardR600/SI: Improve legalization of vector operations blob | commitdiff | raw | diff to current
2013-08-14 Tom StellardR600/SI: Convert v16i8 resource descriptors to i128 blob | commitdiff | raw | diff to current
2013-08-05 Tom StellardR600: Implement TargetLowering::getVectorIdxTy() blob | commitdiff | raw | diff to current
2013-08-01 Tom StellardR600: Add 64-bit float load/store support blob | commitdiff | raw | diff to current
2013-07-30 Tom StellardR600/SI: Expand vector fp <-> int conversions blob | commitdiff | raw | diff to current
2013-07-23 Tom StellardDAGCombiner: Pass the correct type to TargetLowering... blob | commitdiff | raw | diff to current
2013-07-23 Tom StellardR600: Use the same compute kernel calling convention... blob | commitdiff | raw | diff to current
next
C/C++ LLVM-based compilers that forbids OOTA behaviors