- 18 Jul, 2019 1 commit
-
-
Adam Procter authored
* WIP * All but two unit tests passing * Explanatory comment * Cleanup * A bit of cleanup stemming from review comments * Rewrite to use LoopNestBuilder * Remove unnecessary check from CompiledKernel * Removed some dead-ish code I missed * Switch to camelCase in lowerer.cpp * Fix assignment of resIndexHandles that was triggering an assert * Add in some safety checks * dyn_cast -> cast
-
- 17 Jul, 2019 3 commits
-
-
Diego Caballero authored
Aliasing prevents vectorization and other optimizations in LLVM (dot2d, for example). I found that LLVM dialect contemplates the possibility of previous dialects adding llvm.noalias attribute to function arguments so that the NoAlias attribute is generated in LLVM-IR. This should be good for now although we should discuss how to model this in Standard dialect and co.
-
Pruthvi authored
* - templatize computing binary elementwise - added lowering support for Add, Sub, Multiply, Divide * - Added Support for Greater and less Op * -Add support for Minimum and Maximum * use edsc::intrinsics::select instead of terenary operator * Addressed PR comments * - return after the conditional check
-
Nagy Mostafa authored
* Fix incorrect callback lookup * Use std.AllocOp(malloc) for static tensor allocations * Clean up * revert getCallDecl change * style
-
- 16 Jul, 2019 1 commit
-
-
Diego Caballero authored
Fix a mismatch after changing get_inputs API.
-
- 11 Jul, 2019 2 commits
-
-
Nagy Mostafa authored
* Initial sub-graph extraction * Works without detaching input edges from sub-graph * Added removing input edges to graph * Works with whole func sub-graphs. Inputs edges to sub-graph are still there * Works on 2 exclusive sub-graphs. Still not on merged sub-graphs * Revert removing inputs to sub-graph. nGraph validation crashes * Added 3 sub-graph test. Remove compiled_kernel fusion pass. Comments * Revert some changes * Added cycle detection. Removed unit-tests to backend_mlir.in.cpp. Still not fully functional * Construct CK nodes after finding outputs to preserve the graph. * Fix topological sort. UTs pass. * Minor fixes * PR fixes * Enable mlir tests only when building with MLIR on
-
Nagy Mostafa authored
* Support MLIR lowering of Relu * Use EDSC comparison * style-apply * Use .inc file for Conversion classes list * Disable i32 Relu for plaidml
-
- 02 Jul, 2019 1 commit
-
-
Diego Caballero authored
-
- 28 Jun, 2019 1 commit
-
-
Diego Caballero authored
Improvements and changes in dialect conversion APIs. Type conversion and op rewriting are now a bit more independent mechanisms. Dialect conversion now requires a target object with the legal transformations to be applied. Legality checks to detect illegal operations after dialect conversion have been strengthened significantly. MLIR LLVM commit: commit 82d5084cf28bca7a0eebec283cdeae118dfa1d11 (HEAD) Author: Jacques Pienaar <jpienaar@google.com> Date: Wed Jun 26 11:12:40 2019 -0700 Split out TranslateClParser and add new parse method that reuses SourceMgr. MLIR commit: commit 82d5084cf28bca7a0eebec283cdeae118dfa1d11 (HEAD) Author: Jacques Pienaar <jpienaar@google.com> Date: Wed Jun 26 11:12:40 2019 -0700 Split out TranslateClParser and add new parse method that reuses SourceMgr.
-
- 20 Jun, 2019 1 commit
-
-
nmostafa authored
-
- 19 Jun, 2019 1 commit
-
-
nmostafa authored
-
- 13 Jun, 2019 6 commits
- 10 Jun, 2019 3 commits
- 03 Jun, 2019 6 commits
-
-
nmostafa authored
-
Diego Caballero authored
Unused variables.
-
Diego Caballero authored
-
Diego Caballero authored
It refactor MLIR dump code in MLIRCompiler and adds missing dumps for some steps of the lowering. It also removes some redundant dump for affine dialect.
-
nmostafa authored
-
Diego Caballero authored
-
- 02 Jun, 2019 14 commits
-
-
Diego Caballero authored
-
nmostafa authored
-
Diego Caballero authored
-
Diego Caballero authored
This patch introduces tablegen definitions for element-wise reduction operations (only definitions, not building/lowering code). This includes argmin, argmax, min, max, sum, prod, all and any. From the design point of view, a single base class seems to be enough to cover all the common ground of these operations. A different base class will be necessary for avg pool reduction operations.
-
Nagy Mostafa authored
* Improve verification for unary, binary, cmp and select ops. Refactor .td file to enable that.
-
Nagy Mostafa authored
MLIR Compile only supported ops
-
Diego Caballero authored
Element type was not lowered.
-
Diego Caballero authored
It introduces end-to-end support for sub-graphs with multiple nodes. It adds a test with a dot+add ops. Co-authored-by: Diego Caballero <diego.caballero@intel.com> Co-authored-by: Nagy Mostafa <nagy.mostafa@gmail.com>
-
Diego Caballero authored
It extends dot definition to be able to deal with operands that are not square tensors. It also fixes a bug in the lowerer related to that.
-
Diego Caballero authored
* [MLIR] Replace MatmulBiasOp with DotOp We disable CPUFusion if MLIR is enabled to avoid CPU specific ops to be introduced for now.
-
Nagy Mostafa authored
* Upgrade MLIR. Several code fixes based on API changes * Fixes due to DialectConv API changes * style-apply * PR fixes
-
Diego Caballero authored
MLIR is now initialize once once in CPU backend.
-
Nagy Mostafa authored
* Move dialect and types to mlir namespace * PR fixes and some cleanup * Merge fix
-
Nagy Mostafa authored
-