Add external calling functionality#187
Open
bwasti wants to merge 294 commits intobertmaher:pytorch_fusionfrom bwasti:nnc
Commits
This pull request is big! We're only showing the most recent 250 commits
Commits on Feb 18, 2020
authored andOwen AndersoncommittedMikhail Zolotukhin- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
- authored andOwen AndersoncommittedMikhail Zolotukhin
Rename compiler to tensorexpr and move files around to be more similar to other pytorch parts. (pytorch#6)
- committedMikhail Zolotukhin
refactor CallNode and BaseCallNode, so we can have a common concrete base class for visitors. (pytorch#22)
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- authored andProtonu BasucommittedMikhail Zolotukhin
- committedMikhail Zolotukhin
- committedMikhail Zolotukhin
Refactor CudaCodeGen into generic registration, so we can have both the Cuda and non-Cuda builds. (pytorch#118)
- committedMikhail Zolotukhin
- committedMikhail Zolotukhin
Move memory management classes (KernelArena, KernelScope, KernelScopedObject) to a separate file. (pytorch#132)
(IR Interpreter) Adding more Operators: Erfc, Exmp1, frac, lgamma, neg, sigmoid, reciprocal, neg, relu (pytorch#133)
Fix verifier errors in LLVM codegen when conditional loads feed directly into concats. (pytorch#143)
Commits on Feb 20, 2020
- authored
- authored
- authored
- authored
- authored
Commits on Feb 21, 2020
- authored
- authored
- authored
- authored
- authored
- authored
Remove TensorNode and TensorOperationNode classes and remove some wrapper accessors to make the code more explicit. (pytorch#186)
authored- authored
- authored
Commits on Feb 23, 2020
Commits on Feb 24, 2020
- authored
- authored
- authored
- authored
Commits on Feb 25, 2020
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Feb 26, 2020
- authored
- authored
- authored
- authored
- authored
- authored
- committed
Commits on Feb 27, 2020
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Feb 29, 2020
- committedBram Wasti