Convert PyTorch models via NNVM #23
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
markrogersjr
force-pushed
the
neo_pytorch
branch
4 times, most recently
from
22b3d74
to
ac2146e
Compare
yongwww
suggested changes
Apr 2, 2019
|
The unit tests are failing(https://neo-ai-ci.amazon-ml.com/blue/organizations/jenkins/tvm/detail/PR-23/5/pipeline): Could you install torch at the beginning |
wweic
suggested changes
Apr 5, 2019
|
|
||
| def add_input(self, name, tensor): | ||
| self.inputs[name] = PyTorchInput(name, tensor) | ||
| self.inputs[name].graph = self |
There was a problem hiding this comment.
PyTorchInput does not have property graph
There was a problem hiding this comment.
Yeah, I suppose we can set to None by default. graph is set by PyTorchGraph in add_input.
|
|
||
| def add_param(self, name, tensor): | ||
| self.params[name] = PyTorchParam(name, tensor.astype('float32')) | ||
| self.params[name].graph = self |
There was a problem hiding this comment.
PyTorchParam does not have property graph.
| 'stride': self._inputs[4].as_json(), | ||
| } | ||
|
|
||
| # @property |
| self.input_names = [self._input_name(0)] | ||
| self.shape = self._inputs[1].as_json() | ||
|
|
||
| #def expand(node, *inputs): |
yuruofeifei
reviewed
Apr 5, 2019
|
|
||
| def __init__(self, node, graph): | ||
| super(ATenOp, self).__init__(node, graph) | ||
| self.dtype = 'float32' |
There was a problem hiding this comment.
For simplicity, yes but we can add other datatypes, perhaps in a separate PR. DLR only supports float32.
yuruofeifei
reviewed
Apr 5, 2019
|
|
||
| @property | ||
| def shape(self): | ||
| print('shape of', self.name) |
yuruofeifei
reviewed
Apr 5, 2019
| print('shape of', self.name) | ||
| if not hasattr(self, '_shape'): | ||
| self._shape = list(infer_shape(create(self.as_nnvm()))[1][0]) | ||
| print('got the shape') |
markrogersjr
force-pushed
the
neo_pytorch
branch
5 times, most recently
from
58faed8
to
cff5503
Compare
|
@Laurawly @icemelon9 can you please take a look? Particularly at the topi implementation of adaptive pooling. Thanks! |
markrogersjr
force-pushed
the
neo_pytorch
branch
4 times, most recently
from
383d321
to
6c03d0b
Compare
|
@wweic seems PyTorch is still not installed (see CI results). Can you please investigate? |
markrogersjr
force-pushed
the
neo_pytorch
branch
from
6c03d0b
to
d3c1895
Compare
Laurawly
reviewed
Apr 9, 2019
| PoolType pool_type, | ||
| const size_t height_axis, | ||
| const size_t width_axis) { | ||
| CHECK(x->shape.size() >= 2) << "Adaptive Pooling input must >= 2-D (H, W)"; |
There was a problem hiding this comment.
Can the input shape be other shape besides 2D and 4D?
There was a problem hiding this comment.
Probably best to assume it's only 4D but I think greater than 4D is supported.
markrogersjr
force-pushed
the
neo_pytorch
branch
6 times, most recently
from
427b7de
to
766c33f
Compare
markrogersjr
force-pushed
the
neo_pytorch
branch
6 times, most recently
from
7cdfc43
to
e130a00
Compare
markrogersjr
force-pushed
the
neo_pytorch
branch
5 times, most recently
from
41d4f6f
to
07dace7
Compare
|
@KoinFlyp @wweic @yongwww @zhiics @kevinthesun @Laurawly @icemelon9 @yuruofeifei What's the blocking issue for this PR right now? |
markrogersjr
force-pushed
the
neo_pytorch
branch
5 times, most recently
from
51ee22a
to
acf5162
Compare
markrogersjr
force-pushed
the
neo_pytorch
branch
3 times, most recently
from
edceb6b
to
0d50913
Compare
|
close this pr since inactivity & we would like to go with relay. Feel free to re-open it into upstream tvm directly if needed. |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Jul 27, 2020
…generating (apache#5962) * Code migration Start (neo-ai#1) * Init commit: Code migration Start * Add loop_state.cc/h * Add ComputeDAG basic test * Split transform_step out & Update more UTs (neo-ai#3) * Split transform_step out * Update GetProducers & GetConsumers * Update UTs * Add UT for CacheReadWrite & Some bug fix * Add search_task, measure and serialization (neo-ai#4) * Add FollowSplit & FollowFusedSplit tests * Update dag.InferBound & its UT * Add search_task, measure and serialization * Update Serialization UT * Add MetaTileRewritePolicy (neo-ai#5) * Add feature * Add cost_model, meta_tile_rewrite_policy * Add MetaTileRewritePolicy basic UT * Basic Python API for State (neo-ai#6) * Add Basic Python API for State * Add UTs for State * Add Python API: Measure & Task (neo-ai#7) * Update the return value of state operation * Add task * Copy measure.py & utils.py * Fix LocalBuilder * Fix LocalRunner * Add ansor.auto_schedule() API; First AutoSchedule working version(neo-ai#8) * Add basic Python support for ansor.auto_schedule * Update AutoSchedule API * Bug fix for get the attach point of a fused iter * Update UT after infer bug fix * Bug fix & Add python serialization API (neo-ai#10) * Delete C++ UT hack since Python is ready * Add ndarray.non_empty * Update Serialization python API * Improve code style, python wrapper and test cases (neo-ai#11) * Update c++ code style and unit test * Update python State wrapper and test cases * fix unit tests * Add RPCRunner & OpenCL/CUDA test (neo-ai#12) * Add RPCRunner & OpenCL search test * Add CUDA search test * Add RPCRunner test * rebase to upstream/master * Add Ansor basic tutorial (neo-ai#13) * Add basic tutorial * migrate feature extraction (neo-ai#14) * Add XGBModel & RPCRunnerWarpper (neo-ai#15) * Add XGBModel & RPCRunnerWarpper * Revert "Add Parallel Granularity Mutation" * Migrate workload_registry.py (neo-ai#16) * add workload registry * update * update * add task scheduler (neo-ai#17) * Add conv2d cuda tutorial with workload registry (neo-ai#18) * add tune_test.py (the old tune_wkl.py) (neo-ai#19) * add tune_test.py (the old tune_wkl.py) * update * fix measure * fix for gpu * Code refine for tune_test.py & Add a pre load callback (neo-ai#20) * Bug fix for tutorials * Add PreLoadMeasuredStates * Add search_callback support for task tuner * Code refine for tune_test.py * Update * Update * Update * Update * Bug fix * Add python custom sketch rule (neo-ai#21) * Add custom sketch rule * Bug fix * Ansor Relay Integration (without layout rewrite) (neo-ai#22) * relay integration * Add tune_op_subgraph.py & Some code clean for tune_network.py (neo-ai#23) * Add single op tune scripts * Add tune subgraph support * Merge all op & all subgraph to one file * Rename file * add explicit_unroll_max_extent (neo-ai#25) * Add Index simplification & API update (neo-ai#26) * Add vectorized cooperative_fetching test * Update math simplify for vectorized CF * File rename * Update tune_network * API update * Update PreLoadMeasuredStates & Some bug fix (neo-ai#27) * Add a threading wrapper to fix the test bug * Set default TVM_USE_AUTO_SCHEDULER to false * Update PreLoadMeasuredStates callback * Add tensorize step for loop_state (neo-ai#31) * Add tensorize step * State python api update (neo-ai#33) * Start to update api * Add compute_dag to state * API update * kernel layout rewrite (neo-ai#28) * kernel layout rewrite * remove some hacks * add defuse_ops pass and move kernel_layout_rewrite pass after fuse_ops pass * set TVM_RELAY_DISABLE_BUILD_CACHE for task extraction and prepare_layout_rewrite * [cache flush] port cache flush to ansor (neo-ai#32) * Improve relay integration (neo-ai#34) * tmp checkpoint * Improve relay integration * Improve relay integration * Fix xgb error & Simplify dispatcher (neo-ai#35) * Rename "MetaTileRewritePolicy" to "SketchPolicy". (neo-ai#36) * Rename "MetaTileRewritePolicy" to "SketchPolicy". * Add a new class for auto_unroll_max_step, storage_offset in StageNode * fix tune_op_subgraph.py * rebase * Migrate all node::make to noderef's construct function (neo-ai#37) * Start to move xxxnode::make to noderef() * Update * Update * Finish transform_step * Finish comute dag & auto schedule * Update * Update * Update * Update * Update * Code refine * Code refine * Code refine * Update * Update * Some lint fix & Recover the double constructor of tvm::PrimExpr (neo-ai#39) * lint fix * clang-format-fix * pylint fix * Update * Recover the double constructor of tvm::PrimExpr * Fix pylint * pylint fix * pylint fix * Add MutateComputeLocation and MutateParallel in evolutionary search (neo-ai#40) * Add MutateComputeLocation and MutateParallel in evolutionary search * fix lint * Improve loop state python API (stage_tensors -> stage_ops) (neo-ai#41) * improve loop state python API (stage_tensors -> stage_ops) * fix * ComputeDAG bug fix & Add Custom TensorCore Matmul Example (neo-ai#42) * Bug Fix * Sample example of Custom TensorCore Matmul * Rever Commits, Start to build minimum Ansor system * Code clean for minimum Ansor system * Bug fix & Delete AccessAnalyzer * Delete attachmap & Code clean * Doc update Update statenode::stages from vector to Array * Headfile update & Python doc update * clang-format fix * pylint fix * Update * Doc update * Update * Bug fix after code merge to the new master * clang-format fix * Update * Update * Update std::vector to Array; Update verbosity setting; Some commemts addressed * std::vector->Array & std::string->String * Add init_state to ComputeDAG * Update * Update some unordered_map to Map * clang-format fix * Comments addressed Delete ReplayAndInferBound Delete ReplaySteps & InferBoundCommon * Lint fix * Update * Update * Update * Update * Update * Update * Update * Update * Update * Rename ansor namespace to auto_schedule * Update * Rename ThreadPool to ParallelFor * Add parallel_for * Remove ThreadPool * Update python/tvm/auto_schedule/auto_schedule.py * trigger CI Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Minmin Sun (孙敏敏) <minmin.smm@alibaba-inc.com> Co-authored-by: Zhao Wu <zhaowu@apache.org>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Aug 26, 2020
…generating (apache#5962) * Code migration Start (neo-ai#1) * Init commit: Code migration Start * Add loop_state.cc/h * Add ComputeDAG basic test * Split transform_step out & Update more UTs (neo-ai#3) * Split transform_step out * Update GetProducers & GetConsumers * Update UTs * Add UT for CacheReadWrite & Some bug fix * Add search_task, measure and serialization (neo-ai#4) * Add FollowSplit & FollowFusedSplit tests * Update dag.InferBound & its UT * Add search_task, measure and serialization * Update Serialization UT * Add MetaTileRewritePolicy (neo-ai#5) * Add feature * Add cost_model, meta_tile_rewrite_policy * Add MetaTileRewritePolicy basic UT * Basic Python API for State (neo-ai#6) * Add Basic Python API for State * Add UTs for State * Add Python API: Measure & Task (neo-ai#7) * Update the return value of state operation * Add task * Copy measure.py & utils.py * Fix LocalBuilder * Fix LocalRunner * Add ansor.auto_schedule() API; First AutoSchedule working version(neo-ai#8) * Add basic Python support for ansor.auto_schedule * Update AutoSchedule API * Bug fix for get the attach point of a fused iter * Update UT after infer bug fix * Bug fix & Add python serialization API (neo-ai#10) * Delete C++ UT hack since Python is ready * Add ndarray.non_empty * Update Serialization python API * Improve code style, python wrapper and test cases (neo-ai#11) * Update c++ code style and unit test * Update python State wrapper and test cases * fix unit tests * Add RPCRunner & OpenCL/CUDA test (neo-ai#12) * Add RPCRunner & OpenCL search test * Add CUDA search test * Add RPCRunner test * rebase to upstream/master * Add Ansor basic tutorial (neo-ai#13) * Add basic tutorial * migrate feature extraction (neo-ai#14) * Add XGBModel & RPCRunnerWarpper (neo-ai#15) * Add XGBModel & RPCRunnerWarpper * Revert "Add Parallel Granularity Mutation" * Migrate workload_registry.py (neo-ai#16) * add workload registry * update * update * add task scheduler (neo-ai#17) * Add conv2d cuda tutorial with workload registry (neo-ai#18) * add tune_test.py (the old tune_wkl.py) (neo-ai#19) * add tune_test.py (the old tune_wkl.py) * update * fix measure * fix for gpu * Code refine for tune_test.py & Add a pre load callback (neo-ai#20) * Bug fix for tutorials * Add PreLoadMeasuredStates * Add search_callback support for task tuner * Code refine for tune_test.py * Update * Update * Update * Update * Bug fix * Add python custom sketch rule (neo-ai#21) * Add custom sketch rule * Bug fix * Ansor Relay Integration (without layout rewrite) (neo-ai#22) * relay integration * Add tune_op_subgraph.py & Some code clean for tune_network.py (neo-ai#23) * Add single op tune scripts * Add tune subgraph support * Merge all op & all subgraph to one file * Rename file * add explicit_unroll_max_extent (neo-ai#25) * Add Index simplification & API update (neo-ai#26) * Add vectorized cooperative_fetching test * Update math simplify for vectorized CF * File rename * Update tune_network * API update * Update PreLoadMeasuredStates & Some bug fix (neo-ai#27) * Add a threading wrapper to fix the test bug * Set default TVM_USE_AUTO_SCHEDULER to false * Update PreLoadMeasuredStates callback * Add tensorize step for loop_state (neo-ai#31) * Add tensorize step * State python api update (neo-ai#33) * Start to update api * Add compute_dag to state * API update * kernel layout rewrite (neo-ai#28) * kernel layout rewrite * remove some hacks * add defuse_ops pass and move kernel_layout_rewrite pass after fuse_ops pass * set TVM_RELAY_DISABLE_BUILD_CACHE for task extraction and prepare_layout_rewrite * [cache flush] port cache flush to ansor (neo-ai#32) * Improve relay integration (neo-ai#34) * tmp checkpoint * Improve relay integration * Improve relay integration * Fix xgb error & Simplify dispatcher (neo-ai#35) * Rename "MetaTileRewritePolicy" to "SketchPolicy". (neo-ai#36) * Rename "MetaTileRewritePolicy" to "SketchPolicy". * Add a new class for auto_unroll_max_step, storage_offset in StageNode * fix tune_op_subgraph.py * rebase * Migrate all node::make to noderef's construct function (neo-ai#37) * Start to move xxxnode::make to noderef() * Update * Update * Finish transform_step * Finish comute dag & auto schedule * Update * Update * Update * Update * Update * Code refine * Code refine * Code refine * Update * Update * Some lint fix & Recover the double constructor of tvm::PrimExpr (neo-ai#39) * lint fix * clang-format-fix * pylint fix * Update * Recover the double constructor of tvm::PrimExpr * Fix pylint * pylint fix * pylint fix * Add MutateComputeLocation and MutateParallel in evolutionary search (neo-ai#40) * Add MutateComputeLocation and MutateParallel in evolutionary search * fix lint * Improve loop state python API (stage_tensors -> stage_ops) (neo-ai#41) * improve loop state python API (stage_tensors -> stage_ops) * fix * ComputeDAG bug fix & Add Custom TensorCore Matmul Example (neo-ai#42) * Bug Fix * Sample example of Custom TensorCore Matmul * Rever Commits, Start to build minimum Ansor system * Code clean for minimum Ansor system * Bug fix & Delete AccessAnalyzer * Delete attachmap & Code clean * Doc update Update statenode::stages from vector to Array * Headfile update & Python doc update * clang-format fix * pylint fix * Update * Doc update * Update * Bug fix after code merge to the new master * clang-format fix * Update * Update * Update std::vector to Array; Update verbosity setting; Some commemts addressed * std::vector->Array & std::string->String * Add init_state to ComputeDAG * Update * Update some unordered_map to Map * clang-format fix * Comments addressed Delete ReplayAndInferBound Delete ReplaySteps & InferBoundCommon * Lint fix * Update * Update * Update * Update * Update * Update * Update * Update * Update * Rename ansor namespace to auto_schedule * Update * Rename ThreadPool to ParallelFor * Add parallel_for * Remove ThreadPool * Update python/tvm/auto_schedule/auto_schedule.py * trigger CI Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Minmin Sun (孙敏敏) <minmin.smm@alibaba-inc.com> Co-authored-by: Zhao Wu <zhaowu@apache.org>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Aug 26, 2020
…generating (apache#5962) * Code migration Start (neo-ai#1) * Init commit: Code migration Start * Add loop_state.cc/h * Add ComputeDAG basic test * Split transform_step out & Update more UTs (neo-ai#3) * Split transform_step out * Update GetProducers & GetConsumers * Update UTs * Add UT for CacheReadWrite & Some bug fix * Add search_task, measure and serialization (neo-ai#4) * Add FollowSplit & FollowFusedSplit tests * Update dag.InferBound & its UT * Add search_task, measure and serialization * Update Serialization UT * Add MetaTileRewritePolicy (neo-ai#5) * Add feature * Add cost_model, meta_tile_rewrite_policy * Add MetaTileRewritePolicy basic UT * Basic Python API for State (neo-ai#6) * Add Basic Python API for State * Add UTs for State * Add Python API: Measure & Task (neo-ai#7) * Update the return value of state operation * Add task * Copy measure.py & utils.py * Fix LocalBuilder * Fix LocalRunner * Add ansor.auto_schedule() API; First AutoSchedule working version(neo-ai#8) * Add basic Python support for ansor.auto_schedule * Update AutoSchedule API * Bug fix for get the attach point of a fused iter * Update UT after infer bug fix * Bug fix & Add python serialization API (neo-ai#10) * Delete C++ UT hack since Python is ready * Add ndarray.non_empty * Update Serialization python API * Improve code style, python wrapper and test cases (neo-ai#11) * Update c++ code style and unit test * Update python State wrapper and test cases * fix unit tests * Add RPCRunner & OpenCL/CUDA test (neo-ai#12) * Add RPCRunner & OpenCL search test * Add CUDA search test * Add RPCRunner test * rebase to upstream/master * Add Ansor basic tutorial (neo-ai#13) * Add basic tutorial * migrate feature extraction (neo-ai#14) * Add XGBModel & RPCRunnerWarpper (neo-ai#15) * Add XGBModel & RPCRunnerWarpper * Revert "Add Parallel Granularity Mutation" * Migrate workload_registry.py (neo-ai#16) * add workload registry * update * update * add task scheduler (neo-ai#17) * Add conv2d cuda tutorial with workload registry (neo-ai#18) * add tune_test.py (the old tune_wkl.py) (neo-ai#19) * add tune_test.py (the old tune_wkl.py) * update * fix measure * fix for gpu * Code refine for tune_test.py & Add a pre load callback (neo-ai#20) * Bug fix for tutorials * Add PreLoadMeasuredStates * Add search_callback support for task tuner * Code refine for tune_test.py * Update * Update * Update * Update * Bug fix * Add python custom sketch rule (neo-ai#21) * Add custom sketch rule * Bug fix * Ansor Relay Integration (without layout rewrite) (neo-ai#22) * relay integration * Add tune_op_subgraph.py & Some code clean for tune_network.py (neo-ai#23) * Add single op tune scripts * Add tune subgraph support * Merge all op & all subgraph to one file * Rename file * add explicit_unroll_max_extent (neo-ai#25) * Add Index simplification & API update (neo-ai#26) * Add vectorized cooperative_fetching test * Update math simplify for vectorized CF * File rename * Update tune_network * API update * Update PreLoadMeasuredStates & Some bug fix (neo-ai#27) * Add a threading wrapper to fix the test bug * Set default TVM_USE_AUTO_SCHEDULER to false * Update PreLoadMeasuredStates callback * Add tensorize step for loop_state (neo-ai#31) * Add tensorize step * State python api update (neo-ai#33) * Start to update api * Add compute_dag to state * API update * kernel layout rewrite (neo-ai#28) * kernel layout rewrite * remove some hacks * add defuse_ops pass and move kernel_layout_rewrite pass after fuse_ops pass * set TVM_RELAY_DISABLE_BUILD_CACHE for task extraction and prepare_layout_rewrite * [cache flush] port cache flush to ansor (neo-ai#32) * Improve relay integration (neo-ai#34) * tmp checkpoint * Improve relay integration * Improve relay integration * Fix xgb error & Simplify dispatcher (neo-ai#35) * Rename "MetaTileRewritePolicy" to "SketchPolicy". (neo-ai#36) * Rename "MetaTileRewritePolicy" to "SketchPolicy". * Add a new class for auto_unroll_max_step, storage_offset in StageNode * fix tune_op_subgraph.py * rebase * Migrate all node::make to noderef's construct function (neo-ai#37) * Start to move xxxnode::make to noderef() * Update * Update * Finish transform_step * Finish comute dag & auto schedule * Update * Update * Update * Update * Update * Code refine * Code refine * Code refine * Update * Update * Some lint fix & Recover the double constructor of tvm::PrimExpr (neo-ai#39) * lint fix * clang-format-fix * pylint fix * Update * Recover the double constructor of tvm::PrimExpr * Fix pylint * pylint fix * pylint fix * Add MutateComputeLocation and MutateParallel in evolutionary search (neo-ai#40) * Add MutateComputeLocation and MutateParallel in evolutionary search * fix lint * Improve loop state python API (stage_tensors -> stage_ops) (neo-ai#41) * improve loop state python API (stage_tensors -> stage_ops) * fix * ComputeDAG bug fix & Add Custom TensorCore Matmul Example (neo-ai#42) * Bug Fix * Sample example of Custom TensorCore Matmul * Rever Commits, Start to build minimum Ansor system * Code clean for minimum Ansor system * Bug fix & Delete AccessAnalyzer * Delete attachmap & Code clean * Doc update Update statenode::stages from vector to Array * Headfile update & Python doc update * clang-format fix * pylint fix * Update * Doc update * Update * Bug fix after code merge to the new master * clang-format fix * Update * Update * Update std::vector to Array; Update verbosity setting; Some commemts addressed * std::vector->Array & std::string->String * Add init_state to ComputeDAG * Update * Update some unordered_map to Map * clang-format fix * Comments addressed Delete ReplayAndInferBound Delete ReplaySteps & InferBoundCommon * Lint fix * Update * Update * Update * Update * Update * Update * Update * Update * Update * Rename ansor namespace to auto_schedule * Update * Rename ThreadPool to ParallelFor * Add parallel_for * Remove ThreadPool * Update python/tvm/auto_schedule/auto_schedule.py * trigger CI Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Minmin Sun (孙敏敏) <minmin.smm@alibaba-inc.com> Co-authored-by: Zhao Wu <zhaowu@apache.org>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Sep 2, 2020
…generating (apache#5962) * Code migration Start (neo-ai#1) * Init commit: Code migration Start * Add loop_state.cc/h * Add ComputeDAG basic test * Split transform_step out & Update more UTs (neo-ai#3) * Split transform_step out * Update GetProducers & GetConsumers * Update UTs * Add UT for CacheReadWrite & Some bug fix * Add search_task, measure and serialization (neo-ai#4) * Add FollowSplit & FollowFusedSplit tests * Update dag.InferBound & its UT * Add search_task, measure and serialization * Update Serialization UT * Add MetaTileRewritePolicy (neo-ai#5) * Add feature * Add cost_model, meta_tile_rewrite_policy * Add MetaTileRewritePolicy basic UT * Basic Python API for State (neo-ai#6) * Add Basic Python API for State * Add UTs for State * Add Python API: Measure & Task (neo-ai#7) * Update the return value of state operation * Add task * Copy measure.py & utils.py * Fix LocalBuilder * Fix LocalRunner * Add ansor.auto_schedule() API; First AutoSchedule working version(neo-ai#8) * Add basic Python support for ansor.auto_schedule * Update AutoSchedule API * Bug fix for get the attach point of a fused iter * Update UT after infer bug fix * Bug fix & Add python serialization API (neo-ai#10) * Delete C++ UT hack since Python is ready * Add ndarray.non_empty * Update Serialization python API * Improve code style, python wrapper and test cases (neo-ai#11) * Update c++ code style and unit test * Update python State wrapper and test cases * fix unit tests * Add RPCRunner & OpenCL/CUDA test (neo-ai#12) * Add RPCRunner & OpenCL search test * Add CUDA search test * Add RPCRunner test * rebase to upstream/master * Add Ansor basic tutorial (neo-ai#13) * Add basic tutorial * migrate feature extraction (neo-ai#14) * Add XGBModel & RPCRunnerWarpper (neo-ai#15) * Add XGBModel & RPCRunnerWarpper * Revert "Add Parallel Granularity Mutation" * Migrate workload_registry.py (neo-ai#16) * add workload registry * update * update * add task scheduler (neo-ai#17) * Add conv2d cuda tutorial with workload registry (neo-ai#18) * add tune_test.py (the old tune_wkl.py) (neo-ai#19) * add tune_test.py (the old tune_wkl.py) * update * fix measure * fix for gpu * Code refine for tune_test.py & Add a pre load callback (neo-ai#20) * Bug fix for tutorials * Add PreLoadMeasuredStates * Add search_callback support for task tuner * Code refine for tune_test.py * Update * Update * Update * Update * Bug fix * Add python custom sketch rule (neo-ai#21) * Add custom sketch rule * Bug fix * Ansor Relay Integration (without layout rewrite) (neo-ai#22) * relay integration * Add tune_op_subgraph.py & Some code clean for tune_network.py (neo-ai#23) * Add single op tune scripts * Add tune subgraph support * Merge all op & all subgraph to one file * Rename file * add explicit_unroll_max_extent (neo-ai#25) * Add Index simplification & API update (neo-ai#26) * Add vectorized cooperative_fetching test * Update math simplify for vectorized CF * File rename * Update tune_network * API update * Update PreLoadMeasuredStates & Some bug fix (neo-ai#27) * Add a threading wrapper to fix the test bug * Set default TVM_USE_AUTO_SCHEDULER to false * Update PreLoadMeasuredStates callback * Add tensorize step for loop_state (neo-ai#31) * Add tensorize step * State python api update (neo-ai#33) * Start to update api * Add compute_dag to state * API update * kernel layout rewrite (neo-ai#28) * kernel layout rewrite * remove some hacks * add defuse_ops pass and move kernel_layout_rewrite pass after fuse_ops pass * set TVM_RELAY_DISABLE_BUILD_CACHE for task extraction and prepare_layout_rewrite * [cache flush] port cache flush to ansor (neo-ai#32) * Improve relay integration (neo-ai#34) * tmp checkpoint * Improve relay integration * Improve relay integration * Fix xgb error & Simplify dispatcher (neo-ai#35) * Rename "MetaTileRewritePolicy" to "SketchPolicy". (neo-ai#36) * Rename "MetaTileRewritePolicy" to "SketchPolicy". * Add a new class for auto_unroll_max_step, storage_offset in StageNode * fix tune_op_subgraph.py * rebase * Migrate all node::make to noderef's construct function (neo-ai#37) * Start to move xxxnode::make to noderef() * Update * Update * Finish transform_step * Finish comute dag & auto schedule * Update * Update * Update * Update * Update * Code refine * Code refine * Code refine * Update * Update * Some lint fix & Recover the double constructor of tvm::PrimExpr (neo-ai#39) * lint fix * clang-format-fix * pylint fix * Update * Recover the double constructor of tvm::PrimExpr * Fix pylint * pylint fix * pylint fix * Add MutateComputeLocation and MutateParallel in evolutionary search (neo-ai#40) * Add MutateComputeLocation and MutateParallel in evolutionary search * fix lint * Improve loop state python API (stage_tensors -> stage_ops) (neo-ai#41) * improve loop state python API (stage_tensors -> stage_ops) * fix * ComputeDAG bug fix & Add Custom TensorCore Matmul Example (neo-ai#42) * Bug Fix * Sample example of Custom TensorCore Matmul * Rever Commits, Start to build minimum Ansor system * Code clean for minimum Ansor system * Bug fix & Delete AccessAnalyzer * Delete attachmap & Code clean * Doc update Update statenode::stages from vector to Array * Headfile update & Python doc update * clang-format fix * pylint fix * Update * Doc update * Update * Bug fix after code merge to the new master * clang-format fix * Update * Update * Update std::vector to Array; Update verbosity setting; Some commemts addressed * std::vector->Array & std::string->String * Add init_state to ComputeDAG * Update * Update some unordered_map to Map * clang-format fix * Comments addressed Delete ReplayAndInferBound Delete ReplaySteps & InferBoundCommon * Lint fix * Update * Update * Update * Update * Update * Update * Update * Update * Update * Rename ansor namespace to auto_schedule * Update * Rename ThreadPool to ParallelFor * Add parallel_for * Remove ThreadPool * Update python/tvm/auto_schedule/auto_schedule.py * trigger CI Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Minmin Sun (孙敏敏) <minmin.smm@alibaba-inc.com> Co-authored-by: Zhao Wu <zhaowu@apache.org>
trevor-m
pushed a commit
that referenced
this pull request
Sep 3, 2020
…generating (apache#5962) * Code migration Start (#1) * Init commit: Code migration Start * Add loop_state.cc/h * Add ComputeDAG basic test * Split transform_step out & Update more UTs (#3) * Split transform_step out * Update GetProducers & GetConsumers * Update UTs * Add UT for CacheReadWrite & Some bug fix * Add search_task, measure and serialization (#4) * Add FollowSplit & FollowFusedSplit tests * Update dag.InferBound & its UT * Add search_task, measure and serialization * Update Serialization UT * Add MetaTileRewritePolicy (#5) * Add feature * Add cost_model, meta_tile_rewrite_policy * Add MetaTileRewritePolicy basic UT * Basic Python API for State (#6) * Add Basic Python API for State * Add UTs for State * Add Python API: Measure & Task (#7) * Update the return value of state operation * Add task * Copy measure.py & utils.py * Fix LocalBuilder * Fix LocalRunner * Add ansor.auto_schedule() API; First AutoSchedule working version(#8) * Add basic Python support for ansor.auto_schedule * Update AutoSchedule API * Bug fix for get the attach point of a fused iter * Update UT after infer bug fix * Bug fix & Add python serialization API (#10) * Delete C++ UT hack since Python is ready * Add ndarray.non_empty * Update Serialization python API * Improve code style, python wrapper and test cases (#11) * Update c++ code style and unit test * Update python State wrapper and test cases * fix unit tests * Add RPCRunner & OpenCL/CUDA test (#12) * Add RPCRunner & OpenCL search test * Add CUDA search test * Add RPCRunner test * rebase to upstream/master * Add Ansor basic tutorial (#13) * Add basic tutorial * migrate feature extraction (#14) * Add XGBModel & RPCRunnerWarpper (#15) * Add XGBModel & RPCRunnerWarpper * Revert "Add Parallel Granularity Mutation" * Migrate workload_registry.py (#16) * add workload registry * update * update * add task scheduler (#17) * Add conv2d cuda tutorial with workload registry (#18) * add tune_test.py (the old tune_wkl.py) (#19) * add tune_test.py (the old tune_wkl.py) * update * fix measure * fix for gpu * Code refine for tune_test.py & Add a pre load callback (#20) * Bug fix for tutorials * Add PreLoadMeasuredStates * Add search_callback support for task tuner * Code refine for tune_test.py * Update * Update * Update * Update * Bug fix * Add python custom sketch rule (#21) * Add custom sketch rule * Bug fix * Ansor Relay Integration (without layout rewrite) (#22) * relay integration * Add tune_op_subgraph.py & Some code clean for tune_network.py (#23) * Add single op tune scripts * Add tune subgraph support * Merge all op & all subgraph to one file * Rename file * add explicit_unroll_max_extent (#25) * Add Index simplification & API update (#26) * Add vectorized cooperative_fetching test * Update math simplify for vectorized CF * File rename * Update tune_network * API update * Update PreLoadMeasuredStates & Some bug fix (#27) * Add a threading wrapper to fix the test bug * Set default TVM_USE_AUTO_SCHEDULER to false * Update PreLoadMeasuredStates callback * Add tensorize step for loop_state (#31) * Add tensorize step * State python api update (#33) * Start to update api * Add compute_dag to state * API update * kernel layout rewrite (#28) * kernel layout rewrite * remove some hacks * add defuse_ops pass and move kernel_layout_rewrite pass after fuse_ops pass * set TVM_RELAY_DISABLE_BUILD_CACHE for task extraction and prepare_layout_rewrite * [cache flush] port cache flush to ansor (#32) * Improve relay integration (#34) * tmp checkpoint * Improve relay integration * Improve relay integration * Fix xgb error & Simplify dispatcher (#35) * Rename "MetaTileRewritePolicy" to "SketchPolicy". (#36) * Rename "MetaTileRewritePolicy" to "SketchPolicy". * Add a new class for auto_unroll_max_step, storage_offset in StageNode * fix tune_op_subgraph.py * rebase * Migrate all node::make to noderef's construct function (#37) * Start to move xxxnode::make to noderef() * Update * Update * Finish transform_step * Finish comute dag & auto schedule * Update * Update * Update * Update * Update * Code refine * Code refine * Code refine * Update * Update * Some lint fix & Recover the double constructor of tvm::PrimExpr (#39) * lint fix * clang-format-fix * pylint fix * Update * Recover the double constructor of tvm::PrimExpr * Fix pylint * pylint fix * pylint fix * Add MutateComputeLocation and MutateParallel in evolutionary search (#40) * Add MutateComputeLocation and MutateParallel in evolutionary search * fix lint * Improve loop state python API (stage_tensors -> stage_ops) (#41) * improve loop state python API (stage_tensors -> stage_ops) * fix * ComputeDAG bug fix & Add Custom TensorCore Matmul Example (#42) * Bug Fix * Sample example of Custom TensorCore Matmul * Rever Commits, Start to build minimum Ansor system * Code clean for minimum Ansor system * Bug fix & Delete AccessAnalyzer * Delete attachmap & Code clean * Doc update Update statenode::stages from vector to Array * Headfile update & Python doc update * clang-format fix * pylint fix * Update * Doc update * Update * Bug fix after code merge to the new master * clang-format fix * Update * Update * Update std::vector to Array; Update verbosity setting; Some commemts addressed * std::vector->Array & std::string->String * Add init_state to ComputeDAG * Update * Update some unordered_map to Map * clang-format fix * Comments addressed Delete ReplayAndInferBound Delete ReplaySteps & InferBoundCommon * Lint fix * Update * Update * Update * Update * Update * Update * Update * Update * Update * Rename ansor namespace to auto_schedule * Update * Rename ThreadPool to ParallelFor * Add parallel_for * Remove ThreadPool * Update python/tvm/auto_schedule/auto_schedule.py * trigger CI Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com> Co-authored-by: Minmin Sun (孙敏敏) <minmin.smm@alibaba-inc.com> Co-authored-by: Zhao Wu <zhaowu@apache.org>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Consists of an operator map from Prim/ATen operators to NNVM operators and a traversal of PyTorch JIT IR graphs. @wweic @yuruofeifei