You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/08/04 18:49:09 UTC
[tvm] branch unity-staging updated (53fd712bf7 -> 6c38001fe1)
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch unity-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 53fd712bf7 [MERGE-FIX] Update the code to fix merge issues
add ef00a96394 [Unity]: fix error on enum (#15451)
add 54e304467e [Unity] Eslint and TypeScript configuration fix (#15452)
add 605a61450b [Unity][Op] Support symbolic shape inference for slice op. (#15450)
add 1aecc9b8b6 [Unity][Frontend][Onnx] Simplify gemm (#15458)
add c3f26858ba [Unity][Op] Conv1dTranspose (#15456)
add d9e1659d2a [Unity][Transform] Elide redundant bindings of dataflow vars (#15341)
add f3501d85b7 [Unity][Fix][Op] Add groups to conv1d (#15457)
add 13bd656546 [Bugfix][CUTLASS] CUTLASS path finding (#15476)
add 5e1414275f [Cherry-Pick][BugFix][TIR] ThreadSync with shared.dyn awareness (#15481)
add 9d6e153497 [Unity][BugFix][Op] fix error when calling full_like in masked_fill (#15477)
add a8218b31c2 [Unity][DLight] Use less shared memory for gemv (#15482)
add b77d659c9a [microNPU][ETHOSU] Fix concatenation with reused buffers (#15428)
add bab295e409 [ROCm] Fix some ROCm codegen bugs (#15454)
add 1b7175b52a [TVMScript] Support starred indices in for-loop (#15442)
add 0e905aa4d7 [Relay] Stop ToMixedPrecision when constant is out of dtype range (#15461)
add 49fd318e90 [ROCm] fma intrin (#15464)
add 7dc5ae7894 [CYTHON] Make cython compatible with 3.0 (#15469)
add 608553462b [TIR][Schedule] Fix decompose reduction with thread binding loops (#15465)
add 63a95d54f4 [Relay][Strategy] Fix `arm_cpu` int8 conv2d schedule selection for 32-bit targets (#15468)
add dcbf2b2fb4 [TIR] Output DeclBuffer in MakePackedAPI (#15263)
add 543838303b [BugFix][TIR] ThreadSync with shared.dyn awareness (#15478)
add 2f090648d2 [Bugfix][CUTLASS] CUTLASS path finding (#15480)
new 6c38001fe1 [MERGE] Merge main into unity 2023-08-04
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
include/tvm/relax/attrs/index.h | 6 +
include/tvm/relax/attrs/nn.h | 45 +++
include/tvm/relax/transform.h | 10 +
python/tvm/_ffi/_cython/ndarray.pxi | 3 +-
python/tvm/_ffi/libinfo.py | 9 +-
python/tvm/contrib/cutlass/build.py | 15 +-
python/tvm/dlight/gpu/gemv.py | 16 +-
python/tvm/relax/frontend/onnx/onnx_frontend.py | 10 +-
python/tvm/relax/op/index.py | 8 +-
python/tvm/relax/op/mask.py | 3 +-
python/tvm/relax/op/nn/nn.py | 91 ++++++
python/tvm/relax/transform/legalize_ops/nn.py | 41 +++
python/tvm/relax/transform/transform.py | 15 +
python/tvm/relay/backend/contrib/ethosu/codegen.py | 101 ++++++
python/tvm/relay/op/strategy/arm_cpu.py | 10 +-
python/tvm/script/ir_builder/tir/ir.py | 3 +
python/tvm/script/parser/core/parser.py | 2 +
python/tvm/script/parser/tir/parser.py | 4 +-
python/tvm/topi/nn/conv1d.py | 5 +-
python/tvm/topi/nn/conv2d.py | 2 +-
src/relax/op/nn/convolution.cc | 126 ++++++++
src/relax/op/nn/convolution.h | 11 +
src/relax/op/tensor/index.cc | 36 ++-
src/relax/op/tensor/index.h | 12 +-
src/relax/transform/fold_dataflow_block_output.cc | 192 +++++++++++
src/relay/transforms/to_mixed_precision.cc | 41 ++-
src/runtime/rocm/rocm_module.cc | 4 +-
src/target/llvm/codegen_llvm.cc | 4 +-
src/target/llvm/intrin_rule_rocm.cc | 7 +-
src/tir/schedule/primitive/reduction.cc | 10 +-
src/tir/transforms/arg_binder.cc | 2 +
src/tir/transforms/lower_thread_allreduce.cc | 2 +-
src/tir/transforms/make_packed_api.cc | 11 +-
src/tir/transforms/thread_storage_sync.cc | 18 +-
tests/python/contrib/test_ethosu/test_codegen.py | 18 ++
tests/python/dlight/test_gpu_gemv.py | 80 ++---
tests/python/relax/test_frontend_onnx.py | 4 +-
tests/python/relax/test_op_index.py | 78 ++++-
tests/python/relax/test_op_nn_convolution.py | 351 +++++++++++++++++++++
.../test_transform_fold_dataflow_block_output.py | 149 +++++++++
.../python/relax/test_transform_legalize_ops_nn.py | 26 +-
tests/python/relax/test_tvmscript_parser_op_nn.py | 18 ++
.../relay/strategy/test_select_implementation.py | 97 ++++++
tests/python/relay/test_to_mixed_precision.py | 49 +++
.../python/unittest/test_tir_schedule_reduction.py | 33 ++
.../unittest/test_tir_transform_thread_sync.py | 42 +++
.../python/unittest/test_tvmscript_error_report.py | 8 +-
tests/python/unittest/test_tvmscript_parser_tir.py | 62 ++++
web/.eslintrc.json | 3 +-
web/package-lock.json | 11 +-
web/package.json | 9 +-
web/src/rpc_server.ts | 4 +-
web/src/runtime.ts | 44 +--
web/src/tvmjs_runtime_wasi.d.ts | 2 +-
web/src/webgpu.ts | 32 +-
web/tsconfig.json | 3 +-
56 files changed, 1813 insertions(+), 185 deletions(-)
create mode 100644 src/relax/transform/fold_dataflow_block_output.cc
create mode 100644 tests/python/relax/test_transform_fold_dataflow_block_output.py
[tvm] 01/01: [MERGE] Merge main into unity 2023-08-04
Posted by tq...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch unity-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 6c38001fe1bf5213e27afb83b547073649edc932
Merge: a8218b31c2 2f090648d2
Author: tqchen <ti...@gmail.com>
AuthorDate: Fri Aug 4 14:48:27 2023 -0400
[MERGE] Merge main into unity 2023-08-04
python/tvm/_ffi/_cython/ndarray.pxi | 3 +-
python/tvm/relay/backend/contrib/ethosu/codegen.py | 101 +++++++++++++++++++++
python/tvm/relay/op/strategy/arm_cpu.py | 10 +-
python/tvm/script/ir_builder/tir/ir.py | 3 +
python/tvm/script/parser/core/parser.py | 2 +
python/tvm/script/parser/tir/parser.py | 4 +-
src/relay/transforms/to_mixed_precision.cc | 41 ++++++++-
src/runtime/rocm/rocm_module.cc | 4 +-
src/target/llvm/codegen_llvm.cc | 4 +-
src/target/llvm/intrin_rule_rocm.cc | 7 +-
src/tir/schedule/primitive/reduction.cc | 10 +-
src/tir/transforms/arg_binder.cc | 2 +
src/tir/transforms/lower_thread_allreduce.cc | 2 +-
src/tir/transforms/make_packed_api.cc | 11 ++-
tests/python/contrib/test_ethosu/test_codegen.py | 18 ++++
.../relay/strategy/test_select_implementation.py | 97 ++++++++++++++++++++
tests/python/relay/test_to_mixed_precision.py | 49 ++++++++++
.../python/unittest/test_tir_schedule_reduction.py | 33 +++++++
.../python/unittest/test_tvmscript_error_report.py | 8 +-
tests/python/unittest/test_tvmscript_parser_tir.py | 62 +++++++++++++
20 files changed, 448 insertions(+), 23 deletions(-)