Gitiles
Code Review Sign In
gerrit-public.fairphone.software / toolchain / llvm-project / 3af97225291fe0c74ece7e15d6b45773a2a60007 / llvm / lib / CodeGen / BasicTargetTransformInfo.cpp
  1. 7f33ff7 Allow vectorization of division by uniform power of 2. by Karthik Bhat · 11 years ago
  2. b9fd9ed Temporarily Revert "Nuke the old JIT." as it's not quite ready to by Eric Christopher · 11 years ago
  3. f8b27c4 Nuke the old JIT. by Rafael Espindola · 11 years ago
  4. d913448 Remove the TargetMachine forwards for TargetSubtargetInfo based by Eric Christopher · 11 years ago
  5. 9304691 Add @llvm.assume, lowering, and some basic properties by Hal Finkel · 11 years ago
  6. e03a25d Add Support to Recognize and Vectorize NON SIMD instructions in SLPVectorizer. by Karthik Bhat · 11 years ago
  7. e8172d8 Fix a spelling error by Hal Finkel · 11 years ago
  8. 6532c20 Move late partial-unrolling thresholds into the processor definitions by Hal Finkel · 11 years ago
  9. 1625bfc TTI: Estimate @llvm.fmuladd cost as fmul + fadd when FMA's aren't legal on the target. by Benjamin Kramer · 11 years ago
  10. 1b9dde0 [Modules] Remove potential ODR violations by sinking the DEBUG_TYPE by Chandler Carruth · 12 years ago
  11. 56bf297 Don't assert in BasicTTI::getMemoryOpCost for non-simple types by Hal Finkel · 12 years ago
  12. c0196b1 [C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. by Craig Topper · 12 years ago
  13. 6fd19ab Account for scalarization costs in BasicTTI::getMemoryOpCost for extending vector loads by Hal Finkel · 12 years ago
  14. 55312de Fix multi-register costs in BasicTTI::getCastInstrCost by Hal Finkel · 12 years ago
  15. ce376c0 When analyzing vectors of element type that require legalization, by Raul E. Silvera · 12 years ago
  16. 24e685f [C++11] Remove 'virtual' keyword from methods marked with 'override' keyword. by Craig Topper · 12 years ago
  17. aee3ca6 [TTI] There is actually no realistic way to pop TTI implementations off by Chandler Carruth · 12 years ago
  18. 7315602 Switch all uses of LLVM_OVERRIDE to just use 'override' directly. by Craig Topper · 12 years ago
  19. 77dfe45 Switch all uses of LLVM_FINAL to just use 'final', and remove the macro. by Craig Topper · 12 years ago
  20. 3e752e7 Add final and owerride keywords to TargetTransformInfo's subclasses. by Juergen Ributzka · 12 years ago
  21. cae8735 Costmodel: Add support for horizontal vector reductions by Arnold Schwaighofer · 12 years ago
  22. 8f2e700 Add getUnrollingPreferences to TTI by Hal Finkel · 12 years ago
  23. 8e83820 Revert: r189565 - Add getUnrollingPreferences to TTI by Hal Finkel · 12 years ago
  24. 63e6c0e Add getUnrollingPreferences to TTI by Hal Finkel · 12 years ago
  25. 37cd6cf Turn MipsOptimizeMathLibCalls into a target-independent scalar transform by Richard Sandiford · 12 years ago
  26. 0c5c01aa Add a llvm.copysign intrinsic by Hal Finkel · 12 years ago
  27. 171817e Add ISD::FROUND for libm round() by Hal Finkel · 12 years ago
  28. a7cd6bf LoopVectorize: Allow vectorization of loops with lifetime markers by Arnold Schwaighofer · 12 years ago
  29. 8b1e021 SimplifyCFG: Use parallel-and and parallel-or mode to consolidate branch conditions by Tom Stellard · 12 years ago
  30. 9da9a43 TargetTransformInfo: address calculation parameter for gather/scather by Arnold Schwaighofer · 12 years ago
  31. ec474f2 Add the nearbyint -> FNEARBYINT mapping to BasicTargetTransformInfo by Hal Finkel · 12 years ago
  32. afc1036 Access the TargetLoweringInfo from the TargetMachine object instead of caching it. The TLI may change between functions. No functionality change. by Bill Wendling · 12 years ago
  33. bf490d4 Loop Strength Reduce: Scaling factor cost. by Quentin Colombet · 12 years ago
  34. 0db0690 Document the decision to assume that the cost of floats is twice as much as integers. by Nadav Rotem · 13 years ago
  35. 87a0af6 CostModel: increase the default cost of supported floating point operations from 1 to two. Fixed a few tests that changes because now the cost of one insert + a vector operation on two doubles is lower than two scalar operations on doubles. by Nadav Rotem · 13 years ago
  36. b977387 CostModel: Add parameter to instruction cost to further classify operand values by Arnold Schwaighofer · 13 years ago
  37. f7cfac7 Cost model support for lowered math builtins. by Benjamin Kramer · 13 years ago
  38. 594fa2d ARM cost model: Address computation in vector mem ops not free by Arnold Schwaighofer · 13 years ago
  39. 56b31bd Split TargetLowering into a CodeGen and a SelectionDAG part. by Benjamin Kramer · 13 years ago
  40. e55aa3c ARM Cost Model: Modify the target independent cost model to ask by Nadav Rotem · 13 years ago
  41. b1791a7 ARM Cost model: Use the size of vector registers and widest vectorizable instruction to determine the max vectorization factor. by Nadav Rotem · 13 years ago
  42. b696c36 Cost Model: Move the 'max unroll factor' variable to the TTI and add initial Cost Model support on ARM. by Nadav Rotem · 13 years ago
  43. 95f83e0 Sink AddrMode back into TargetLowering, removing one of the most by Chandler Carruth · 13 years ago
  44. d3e7355 Move TargetTransformInfo to live under the Analysis library. This no by Chandler Carruth · 13 years ago
  45. 664e354 Switch TargetTransformInfo from an immutable analysis pass that requires by Chandler Carruth · 13 years ago