- 06 Apr, 2020 6 commits
-
-
Samuel committed
-
[RUNTIME] Enable auto conversion from str to runtime::String in PackedFunc, move dtype related handling to data_type.h (#5251)
Tianqi Chen committed -
Tang, Shizhi committed
-
fix to skip node not in graph because some network cannot be hybridized with some var unused.
chinakook committed -
Haichen Shen committed
-
Haichen Shen committed
-
- 05 Apr, 2020 4 commits
-
-
* Functional conv3d winograd working. * Formatted python code. * registered conv3d winograd compute and started adding relay without_weight_transform operator. * Add topi testing for conv3d winograd. * Format file. * small tweak to unrolling to prevent build sticking. * Refactoring convolution ops in relay. * Refactored relay convolutions. * Bug fixes. * Fixed static bug in convolution. * Added conv3d alter op layout and related support. * Bug fixes and testing done. * Fix a few autotvm bugs. * Drop silly debug print. * Removed debug_skip_region. * Add variant of conv3d_winograd that doesn't transform depth. * initial infrastructure done for depthless conv. * Fix no_depth schedule bugs. * automatic topi switching between depth and depthless winograd. * Fixed bug in schedule. * lint fixes. * Removed indents in convolution.cc * missed a few indents oops. * fixed flop count. * One more small tweak. * Change kernel pack inner axes order. * Style changes. * Comment fixes.
Josh Fromm committed -
ga committed
-
* Add other static tensor array ops * Add tensor array get data * Minor refactor * Fix pylint * Update docstring * Make get data more generic * Improve test * Improve split test * Improve get data * Minor fix * Further improvement for static shape * Improve shape parsing * Unify get_static_name
Yao Wang committed -
* [REFACTOR][TIR] Migrate all low-level passes to the Pass Manager. This PR migrates the tvm.lower to return IRModule of PrimFuncs instead of the LoweredFuncs. * Remove LoweredFunc.
Tianqi Chen committed
-
- 04 Apr, 2020 3 commits
-
-
* [ONNX]Pool3d and Upsample3d op updated * Pool3d and Upsample3d testcase * Review comments fixed * Review comments
Samuel committed -
* Fix x86 conv2d and depthwise conv2d auto tuning * Fix depthwise conv2d infer layout * Use random data instead of empty data for autotvm * Fix pylint * Keep empty array for now for autotvm
Yao Wang committed -
* Support mixing normal and cross-thread reduction * minor improvements
Tang, Shizhi committed
-
- 03 Apr, 2020 8 commits
-
-
* [REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager. - SplitHostDevice - ThreadSync - BindDevice - LowerThreadAllreduce - Provide a temp fix for printing IRModule with PrimFunc before the formal text printer. * Address comments, fix tests. * Fix relay tests * Explicit move
Tianqi Chen committed -
Tianqi Chen committed
-
* First pass a defining a non-recursive Graph Vistor and Rewriter autoformat remove a currently empty test until testing is solidfied * Make CalcDep from Dead Code Elimination non-recursive * Partially working, not passing all tests yet passes tests when disabling GetExprRefCount, I think I have a bug in visit counting fix GetExprRefCount Fix a subtle bug with nested recursive/non-recursive scopes * Refactor * improve comments * respond to review comments on comments * Fix a problem with default recursion for dataflow nodes mark DataflowVisitor methods as override * implement ScopeMutator * convert forward_rewrite to ScopeMutator, remove DataflowMutator * rewrite ExprRewriter and convert fast_math to use it * switch BiasAddSimplifier to ExprRewriter fix a clang warning fix cpp lint fix doc param error * respond to review comments * fix a typo in the iterative looping * add a regression test for GetExprRefCount issue * Normalize naming * fix lint * First pass a defining a non-recursive Graph Vistor and Rewriter autoformat remove a currently empty test until testing is solidfied * Make CalcDep from Dead Code Elimination non-recursive * Partially working, not passing all tests yet passes tests when disabling GetExprRefCount, I think I have a bug in visit counting fix GetExprRefCount Fix a subtle bug with nested recursive/non-recursive scopes * Refactor * improve comments * respond to review comments on comments * Fix a problem with default recursion for dataflow nodes mark DataflowVisitor methods as override * implement ScopeMutator * convert forward_rewrite to ScopeMutator, remove DataflowMutator * rewrite ExprRewriter and convert fast_math to use it * switch BiasAddSimplifier to ExprRewriter fix a clang warning fix cpp lint fix doc param error * respond to review comments * fix a typo in the iterative looping * add a regression test for GetExprRefCount issue * Normalize naming * fix lint * respond to review comments
Matthew Brookhart committed -
Animesh Jain committed
-
For certain network topologies, MCR could hang. This patch fixes that case. Change-Id: I3edd8a8a6b452b2b838b777720adea22a3b995b4
mbaret committed -
* [KERAS]upsampling3d and zeropadding3d op * [KERAS]upsampling3d and zeropadding3d test case * Review comments updated
Samuel committed -
Samuel committed
-
- Support vectorized casts - It is incorrect to extract elements from int8x4 with 0x000000ff & (x >> i * 8) as this value is of type int in C/C++. If this expression is used for sign extensions, the sign bit will be wrong. Simply use C style casts instead and sign bits will just work. Signed-off-by: Wei Pan <weip@nvidia.com>
Wei Pan committed
-
- 02 Apr, 2020 12 commits
-
-
Rationale: The current hybrid module is more aligned with the te part. We might consider add a new varient of hybrid script that support the unified IR later. This refactor paves for the potential later changes.
Tianqi Chen committed -
- Reduce CI docs task log size. - Update the relation to halide to the latest state.
Tianqi Chen committed -
* [PYTORCH]AvgPool3d, MaxPool3d and Squeeze op support * Testcases added * review comments
Samuel committed -
- Migrate LowerTVMBultin - Migrate inferFragment, LowerThreadAllreduce - Migrate ThreadSync - Refactor target::Build to directly take IRModule. - Remove un-used legacy functions.
Tianqi Chen committed -
Co-authored-by: Siyuan Feng <hzfengsy@sjtu.edu.cn> This PR introduces BufferLoad/Store to TIR. The new nodes will replace Provide and Call with Tensor arguments in the subsequent refactors.
Tianqi Chen committed -
Haozheng Fan committed
-
* expose runtime::String to Python * retrigger ci
Zhi committed -
* expose runtime::String to Python * kExternalSymbol -> kGlobalSymbol
Zhi committed -
* [Frontend][Torch] Simplify operator input handling * [Frontend][Torch] Allow user supplied input names to override graph inputs * Fix pylint issues * Updates from code review feedback * Fix tutorial to use shape list input * Disable intermittent test failure in topi vision test
Jeremy Johnson committed -
Signed-off-by: Wei Pan <weip@nvidia.com>
Wei Pan committed -
Tianqi Chen committed
-
* [REFACTOR][TIR] Introduce ExprDeepEqual, Remove IRDeepCompare This PR introduces ExprDeepEqual which reuses the StructuralEqual infra. We migrated the usecases of ir_pass::Equal to ExprDeepEqual and StructuralEqual. * Address comments
Tianqi Chen committed
-
- 01 Apr, 2020 7 commits
-
-
* [RELAY] Fixed issues with MergeCompilerRegions This PR addresses a few outstanding issues with the implementation of MergeCompilerRegions. In particular, it now handles TupleGetItem nodes properly and other minor bugs related to region merging have been fixed. Change-Id: I07783afc56183a6f798a510209f23b0a5f252255 * Fixed issue using pre-merged regions Change-Id: I0a844ac59bda1089ae0c67cef52f0b0c7ab2cbd7 * Removed some debugging logic Change-Id: Ib6f2eede6f38bbb270073eb8d4c4dc19f60832c6 * Remove default annotations Change-Id: I9b7696a51c95871491cbea33c40f92ec327e417f * Annotate default 'if's Change-Id: I0098bd1bf6788dd6366810dcefa84f1ebbffaab0 * Clang format Change-Id: I944365cd3080a97a9261f643a8f1efa5a63cf82b * Use src/dest in merge Change-Id: Ie43113492bda8f1ce63eaf9615cb645bb9e2ee86 * Fixed partition test Change-Id: I46f9e349b1a813a9140f7e4f8a2241687e2df73b * Removed comments Change-Id: I309afdd1951d7e796e41d13788aa487707e0ac4c
mbaret committed -
MORITA Kazutaka committed
-
* [PYTORCH]Dropouts And InstanceNorm support added * Review comments fixed
Samuel committed -
* [BUGFIX]bugfix in tensorflow space_to_batch_nd * Test case added
Samuel committed -
* [DOCS] Use https link * use http for sphinx
Tianqi Chen committed -
* [RELAY] Codestyle fixes for Graph Partitioner *ran through clang-format * *formatting comments * *further codestyle changes (after clang-format)
manupa-arm committed -
* [PYTORCH]Activations for pytorch * Review comments updated
Samuel committed
-