* replace LooseVersion with packaging.version
* import packaging from setuptools
* import packaging.version in dgl.utils
* format
* revert changes to apps/kg
* revert changes to _dataloading
* add bf16 specializations
* remove SWITCH_BITS
* enable amp for bf16
* remove SWITCH_BITS for cpu kernels
* enbale bf16 based on CUDART
* fix compiling for sm<80
* fix cpu build
* enable unit tests
* update doc
* disable test for CUDA < 11.0
* address comments
* address comments
* Disable pinning non-contiguous memory
* Prevent views from being converted for write
* Fix linting
* Add unit tests
* Improve error message for users
* Switch to pytest function
* exclude mxnet and tensorflow from inplace pinning
* Add skip
* Restrict to pytorch backend
* Use backend to retrieve device
* Fix capitalization in decorator
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
* WIP: TypedLinear and new RelGraphConv
* wip
* further simplify RGCN
* a bunch of tweak for performance; add basic cpu support
* update on segmm
* wip: segment.cu
* new backward kernel works
* fix a bunch of bugs in kernel; leave idx_a for future
* add nn test for typed_linear
* rgcn nn test
* bugfix in corner case; update RGCN README
* doc
* fix cpp lint
* fix lint
* fix ut
* wip: hgtconv; presorted flag for rgcn
* hgt code and ut; WIP: some fix on reorder graph
* better typed linear init
* fix ut
* fix lint; add docstring
* init
* init
* working cublasGemm
* benchmark high-mem/low-mem, err gather_mm output
* cuda kernel for bmm like kernel
* removed cpu copy for E_per_Rel
* benchmark code from Minjie
* fixed cublas results in gathermm sorted
* use GPU shared mem in unsorted gather mm
* minor
* Added an optimal version of gather_mm_unsorted
* lint
* init gather_mm_scatter
* cublas transpose added
* fixed h_offset for multiple rel
* backward unittest
* cublas support to transpose W
* adding missed file
* forgot to add header file
* lint
* lint
* cleanup
* lint
* docstring
* lint
* added unittest
* lint
* lint
* unittest
* changed err type
* skip cpu test
* skip CPU code
* move in-len loop inside
* lint
* added check different dim length for B
* w_per_len is optional now
* moved gather_mm to pytorch/backend with backward support
* removed a_/b_trans support
* transpose op inside GEMM call
* removed out alloc from API, changed W 2D to 3D
* Added se_gather_mm, Separate API for sortedE
* Fixed gather_mm (unsorted) user interface
* unsorted gmm backward + separate CAPI for un/sorted A
* typecast to float to support atomicAdd
* lint typecast
* lint
* added gather_mm_scatter
* minor
* const
* design changes
* Added idx_a, idx_b support gmm_scatter
* dgl doc
* lint
* adding gather_mm in ops
* lint
* lint
* minor
* removed benchmark files
* minor
* empty commit
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
* edge_softmax_hetero forwar+cpu+norm=dst
* convert eids to list
* addedunittest
* added unittest
* added backward. Not tested correctness
* minor
* changed reducer to max from sum
* bugfix
* docstring
* add GPU unittest
* output converted to dict from tuple
* lint check
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
* min/max support for forward CPU heterograph
* Added etype with each argU values
* scatter_add needs fix
* added scatter_add_hetero. Grads dont match for max reducer
* storing ntype in argX
* fixing scatter_add_hetero
* hetero matches with torch's scatter add
* works copy_e forward+cpu
* added backward for copy_rhs
* Computes gradient for all node types in one kernel
* bug fix
* unnitest for max/min on CPU
* renamed scatter_add_hetero to update_grad_minmax_hetero
* lint check and comment out cuda call for max. Code is for CPU only
* lint check
* replace inf with zero
* minor
* lint check
* removed LIBXSMM code from hetro code
* fixing backward operator of UpdateGradMinMaxHetero
* removed backward from update_grad_minmax_hetero
* docstring
* improved docstring and coding style
* Added pass by pointer for output
* typos and pass by references
* Support for copy_rhs
* Added header <string>
* fix bug in copy_u_max
* Added comments and dimension check of all etypes
* skip mxnet check
* pass by pointer output arrays
* updated docstring
Co-authored-by: Israt Nisa <nisisrat@amazon.com>
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>
* csr and csc creation
* fix
* fix
* fixes to adj transpose
* fine
* raise error if indptr did not match number of nodes
* fix
* huh?
* oh
Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com>
* Split from NCCL PR
* Fix type in comment
* Expand documentation for sparse_all_to_all_push
* Restore previous behavior in example
* Re-work optimizer to use NCCL based on gradient location
* Allow for running with embedding on CPU but using NCCL for gradient exchange
* Optimize single partition case
* Fix pylint errors
* Add missing include
* fix gradient indexing
* Fix line continuation
* Migrate 'first_step'
* Skip tests without enough GPUs to run NCCL
* Improve empty tensor handling for pytorch 1.5
* Fix indentation
* Allow multiple NCCL communicator to coexist
* Improve handling of empty message
* Update python/dgl/nn/pytorch/sparse_emb.py
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com>
* Update python/dgl/nn/pytorch/sparse_emb.py
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com>
* Keepy empty tensor dimensionaless
* th.empty -> th.tensor
* Preserve shape for empty non-zero dimension tensors
* Use shared state, when embedding is shared
* Add support for gathering an embedding
* Fix typo
* Fix more typos
* Fix backend call
* Use NodeDataLoader to take advantage of ddp
* Update training script to share memory
* Only squeeze last dimension
* Better handle empty message
* Keep embedding on the target device GPU if dgl_sparse if false in RGCN example
* Fix typo in comment
* Add asserts
* Improve documentation in example
Co-authored-by: xiang song(charlie.song) <classicxsong@gmail.com>
* test commit
* fixes
* oops
* add docs
* lint
* why does it say I have a trailing whitespace
* oh ok
* fixes
* why there's an invalid argument error
* address comments
* fix
* address comments
* Start on uniform GPU sampling
* Save more work
* Get cu file compiling
* Update sampling
* More changes
* Get GPU sampling for uniform probabilities solved
* Fix batch tensor migration
* Fix
* update kernels
* expand blocking
* Undo testing change
* Cut down on sampling overhead
* Fix replacement
* Update unit tests
* Add option to gpu sample in graphsage
* Copy only csc to gpu
* Add ogbn support
* Fix linting
* Remove nvtx from sample
* Improve documentation and error checking
* Expand documentation
* Update assert checking
* delete extra space
* Use standard dataloader when dataset is a dictionary
* ogb -> ogbn
* Fix edge selection determinism
* Fix typos
* Remove nvtx
* Add comment for self.fanout_arrays and assert
* Fix linting
* Migrate to scalarbatcher
* Fix indentation
* Fix batcher
* Fix indexing
* Only use databatcher for GPU
* Convert to DGL NDArray to PyTorch Tensor
* Add optimization for PyTorch's F.tensor() for list of GPU tensors
Co-authored-by: Da Zheng <zhengda1936@gmail.com>
Rhett Ying