Commits · 15f800f4bc71733c9f47f0dc4d44799be900bc00 · Roger Ferrer / llvm-epi-0.8 · GitLab

This is an archived project. Repository and other project resources are read-only.

Dec 19, 2019
- [VectorOps] minor cleanup: vector dialect "subscripts" are i32 · 15f800f4
  Aart Bik authored Dec 19, 2019
  15f800f4
- Detemplatize ModuleTranslation::lookupValues · efadb6b8
  Alex Zinenko authored Dec 19, 2019
  efadb6b8
- Add runtime utils support for print_memref_i8 · 50f9be6d
  Nicolas Vasilache authored Dec 18, 2019
  50f9be6d
Dec 18, 2019
- [VectorOps] Replace iostream with stdio in support lib for vector.print · a1e84db6
  Aart Bik authored Dec 18, 2019
  a1e84db6
- Add a couple useful LLVM_DEBUG's to the inliner. · 553f794b
  Sean Silva authored Dec 18, 2019
  553f794b
- Move the specializations of VectorTransferRewriter::matchAndRewrite back into... · 7b3adda8
  River Riddle authored Dec 18, 2019
  7b3adda8
- Added LLVM ops and lowering phases from standard dialect for FAbs, FCeil, Cos, FNeg, CopySign. · 6054610b
  Marcel Koester authored Dec 18, 2019
  6054610b
- [VectorOps] Add vector.print definition, with lowering support · d9b500d3
  Aart Bik authored Dec 18, 2019
  d9b500d3
- NFC: Remove forbidden include of <iostream> · c169852f
  River Riddle authored Dec 18, 2019
  c169852f
- Add support for providing a default implementation for an interface method. · 29807ff5
  River Riddle authored Dec 18, 2019
  29807ff5
- Update code block designations · d7e2cc9b
  Jacques Pienaar authored Dec 18, 2019
  d7e2cc9b
- NFC: Cleanup non-conforming usages of namespaces. · 2666b973
  River Riddle authored Dec 18, 2019
  2666b973
- Introduce prefetch op: affine -> std -> llvm intrinsic · 47034c4b
  Uday Bondhugula authored Dec 18, 2019
  47034c4b
- NFC: Remove unnecessary 'llvm::' prefix from uses of llvm symbols declared in `mlir` namespace. · 4562e389
  River Riddle authored Dec 18, 2019
  4562e389
- Move function template definition to the header file. NFC · 24ab8362
  Alex Zinenko authored Dec 18, 2019
  24ab8362
- Fix line break in LangRef · abcf5ff0
  Jacques Pienaar authored Dec 18, 2019
  abcf5ff0
- Harden the requirements to memory attribution types in gpu.func · 40ef46fb
  Alex Zinenko authored Dec 18, 2019
  40ef46fb
- Add support for float and string attributes to the C API and python bindings · c6c6a74d
  MLIR Team authored Dec 17, 2019
  c6c6a74d
- NFC: Use this-> to appease GCC bug related to template lambda. · 5a0d4803
  River Riddle authored Dec 17, 2019
  5a0d4803
Dec 17, 2019
- NFC: Use TypeSwitch to simplify existing code. · 74278dd0
  River Riddle authored Dec 17, 2019
  74278dd0
- Add pattern rewrite which splits a vector TransferWriteOp into slices... · 6fa3bd5b
  Andy Davis authored Dec 17, 2019
  6fa3bd5b
- Add missing virtual inliner interface method in SPIR-V dialect. · 319cca3b
  Mahesh Ravishankar authored Dec 17, 2019
  319cca3b
- Make it possible to override the lowering of MemRef to the LLVM dialect. NFC. · 42b3fe83
  Alex Zinenko authored Dec 17, 2019
  42b3fe83
- ConversionToLLVMDialect doc: update the syntax for LLVM types · 62f498dc
  Alex Zinenko authored Dec 17, 2019
  62f498dc
- StdToLLVM conversion: drop getMemRefElementType utility function · 0bdc72d2
  Alex Zinenko authored Dec 17, 2019
  0bdc72d2
- Homogenize the description of the MemRef conversion to the LLVM dialect · 651eaa03
  Alex Zinenko authored Dec 17, 2019
  651eaa03
- Add pattern rewrite to forward vector tuple elements to their users. · d1fb285b
  Andy Davis authored Dec 17, 2019
  d1fb285b
- fix a typo in OpDefinitions doc · 9f45a224
  Jin Mingjian authored Dec 17, 2019
  9f45a224
- Add a new utility class TypeSwitch to ADT. · f44cf232
  River Riddle authored Dec 17, 2019
  f44cf232
- Integrate from upstream at revision e4fce659 . · 6e581e29
  MLIR Team authored Dec 17, 2019
  6e581e29
- Add pattern rewrite which splits a vector TransferReadOp into slices according... · 038ad1d8
  Andy Davis authored Dec 17, 2019
  038ad1d8
- Replace code with equivalent satisfiesLLVMModule() function call. · 8d68fe68
  Tres Popp authored Dec 17, 2019
  8d68fe68
- Update vector op unrolling transformation to generate ExtractSlicesOp and... · 4e825c59
  Andy Davis authored Dec 17, 2019
  4e825c59
- Add atomic operations to SPIR-V dialect. · 80ec474a
  Mahesh Ravishankar authored Dec 16, 2019
  80ec474a
Dec 16, 2019
- Fix (de)serialization generation for SPV_ScopeAttr, SPV_MemorySemanticsAttr. · a0557ea9
  Mahesh Ravishankar authored Dec 16, 2019
  a0557ea9
- [spirv] Re-enable nested loop (de)serialization test · 659150b5
  Lei Zhang authored Dec 16, 2019
  659150b5
- Add edsc::ops for pointwise, conv and dilated_conv · 3c179b65
  Nicolas Vasilache authored Dec 16, 2019
  3c179b65
- Add InsertSlicesOp to the VectorOps dialect. · 11e92875
  Andy Davis authored Dec 16, 2019
  11e92875
- Plug gpu.func into the GPU lowering pipelines · 6273fa0c
  Alex Zinenko authored Dec 16, 2019
  6273fa0c
- Insert signature-converted blocks into a region with a parent operation. · ab610e8a
  River Riddle authored Dec 16, 2019
  ab610e8a