You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by gi...@apache.org on 2022/11/08 00:01:09 UTC

[tvm] branch nightly-docker-update updated (ee02f551ae -> 8dc4c97086)

This is an automated email from the ASF dual-hosted git repository.

github-bot pushed a change to branch nightly-docker-update
in repository https://gitbox.apache.org/repos/asf/tvm.git


    omit ee02f551ae [ci][docker] Nightly Docker image update
     add 60e2c98fdb [Hexagon] Fix Hexagon external libs check (#13257)
     add dd257e478e [Relay][Op] Add support for large index fp16 mean and var (#13289)
     add 6b238c4b6e [Bugfix][Runtime] Fix sched_setaffinity in Android (#13158)
     add e398d16de8 [Torch] Fix advanced indexing with boolean mask (#13306)
     add ce777fde18 [TOPI] Enhance VNNI dot product (#12588)
     add b16a64d6ed [MetaSchedule] Refactor ScheduleRule Attributes (#13195)
     add 8dc4c97086 [ci][docker] Nightly Docker image update

This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version.  This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:

 * -- * -- B -- O -- O -- O   (ee02f551ae)
            \
             N -- N -- N   refs/heads/nightly-docker-update (8dc4c97086)

You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.

Any revisions marked "omit" are not gone; other references still
refer to them.  Any revisions marked "discard" are gone forever.

No new revisions were added by this update.

Summary of changes:
 Jenkinsfile                                        |  20 +-
 ci/jenkins/Jenkinsfile.j2                          |  20 +-
 cmake/modules/Hexagon.cmake                        |   2 +-
 include/tvm/meta_schedule/schedule/cpu/.gitignore  |   0
 .../tvm/meta_schedule/schedule/cuda/thread_bind.h  |  50 ++-
 .../schedule/generic/winograd.h}                   |  30 +-
 include/tvm/meta_schedule/schedule/x86/.gitignore  |   0
 include/tvm/meta_schedule/schedule_rule.h          |   8 +
 python/tvm/meta_schedule/__init__.py               |   6 +-
 python/tvm/meta_schedule/relay_integration.py      |  16 +-
 .../_ctypes => meta_schedule/schedule}/__init__.py |   3 +-
 .../tvm/meta_schedule/schedule/cpu}/__init__.py    |   7 +-
 .../tvm/meta_schedule/schedule/cuda}/__init__.py   |   7 +-
 .../schedule/generic}/__init__.py                  |   2 +-
 .../tvm/meta_schedule/schedule/x86}/__init__.py    |   7 +-
 python/tvm/meta_schedule/schedule_rule/__init__.py |   5 +-
 ...om_compute_location.py => apply_custom_rule.py} |  12 +-
 .../search_strategy/evolutionary_search.py         |   2 +-
 .../meta_schedule/testing/conv2d_winograd_cpu.py   | 172 ----------
 .../meta_schedule/testing/conv2d_winograd_cuda.py  | 173 ----------
 python/tvm/meta_schedule/testing/relay_workload.py |   1 -
 .../tvm/meta_schedule/testing/space_generation.py  |   2 +-
 python/tvm/meta_schedule/testing/te_workload.py    | 150 ++++-----
 python/tvm/relay/backend/te_compiler.py            |   4 +-
 python/tvm/relay/frontend/pytorch.py               |  15 +-
 python/tvm/relay/op/nn/_nn.py                      |   4 +-
 python/tvm/relay/op/strategy/adreno.py             |  10 +-
 python/tvm/relay/op/strategy/arm_cpu.py            |  12 +-
 python/tvm/relay/op/strategy/bifrost.py            |  10 +-
 python/tvm/relay/op/strategy/cuda.py               |  72 +++--
 python/tvm/relay/op/strategy/generic.py            |  10 +-
 python/tvm/relay/op/strategy/mali.py               |  10 +-
 python/tvm/relay/op/strategy/x86.py                |  10 +-
 python/tvm/topi/cuda/conv2d_alter_op.py            |  56 ++--
 python/tvm/topi/cuda/conv2d_nhwc_winograd.py       |   4 +-
 python/tvm/topi/cuda/conv2d_winograd.py            |  35 +-
 python/tvm/topi/nn/conv2d.py                       | 352 +++++++++++++++++---
 python/tvm/topi/utils.py                           |  14 +-
 python/tvm/topi/x86/batch_matmul.py                |   8 +-
 python/tvm/topi/x86/dense.py                       |  14 +-
 python/tvm/topi/x86/tensor_intrin.py               |  14 +-
 .../postproc/rewrite_unbound_block.cc              |   3 +-
 src/meta_schedule/schedule/cpu/winograd.cc         | 101 ++++++
 .../auto_bind.cc => schedule/cuda/thread_bind.cc}  | 167 ++++------
 src/meta_schedule/schedule/cuda/winograd.cc        | 163 ++++++++++
 .../meta_schedule/schedule/generic/winograd.cc     |  44 +--
 src/meta_schedule/schedule/x86/.gitignore          |   0
 .../schedule_rule/apply_custom_rule.cc             |  92 ++++++
 src/meta_schedule/schedule_rule/auto_bind.cc       | 138 +-------
 src/meta_schedule/schedule_rule/schedule_rule.cc   |  56 ++--
 src/meta_schedule/schedule_rule/winograd.cc        | 249 ---------------
 .../space_generator/post_order_apply.cc            |  49 +--
 src/meta_schedule/utils.h                          |  35 +-
 src/relay/op/tensor/reduce.cc                      |  37 ++-
 src/runtime/threading_backend.cc                   |  17 +-
 src/target/tag.cc                                  |   9 +-
 src/te/operation/create_primfunc.cc                |  17 +-
 .../metaschedule_e2e/test_resnet50_int8.py         |  14 +-
 tests/python/frontend/pytorch/test_forward.py      |   8 +
 tests/python/relay/test_op_level4.py               |  23 +-
 .../test_meta_schedule_custom_rule_winograd_cpu.py | 206 ------------
 ...test_meta_schedule_custom_rule_winograd_cuda.py | 328 -------------------
 .../test_meta_schedule_post_order_apply.py         |  43 ---
 .../test_meta_schedule_relay_integration.py        |   7 +-
 .../test_meta_schedule_space_cpu_winograd.py       | 168 ++++++++++
 .../unittest/test_meta_schedule_space_cuda.py      | 169 ----------
 .../test_meta_schedule_space_cuda_winograd.py      | 355 +++++++++++++++++++++
 .../test_meta_schedule_vnni_integration.py         |  14 +-
 tests/python/unittest/test_te_create_primfunc.py   |   2 -
 .../unittest/test_tir_analysis_stmt_finding.py     |   7 +-
 70 files changed, 1798 insertions(+), 2072 deletions(-)
 create mode 100644 include/tvm/meta_schedule/schedule/cpu/.gitignore
 rename src/meta_schedule/schedule_rule/auto_bind.h => include/tvm/meta_schedule/schedule/cuda/thread_bind.h (57%)
 copy include/tvm/{relay/op.h => meta_schedule/schedule/generic/winograd.h} (63%)
 create mode 100644 include/tvm/meta_schedule/schedule/x86/.gitignore
 copy python/tvm/{_ffi/_ctypes => meta_schedule/schedule}/__init__.py (90%)
 copy {apps/uma/_template => python/tvm/meta_schedule/schedule/cpu}/__init__.py (92%)
 copy {apps/uma/_template => python/tvm/meta_schedule/schedule/cuda}/__init__.py (91%)
 copy python/tvm/{contrib/ethosu => meta_schedule/schedule/generic}/__init__.py (92%)
 copy {apps/uma/_template => python/tvm/meta_schedule/schedule/x86}/__init__.py (92%)
 copy python/tvm/meta_schedule/schedule_rule/{random_compute_location.py => apply_custom_rule.py} (66%)
 delete mode 100644 python/tvm/meta_schedule/testing/conv2d_winograd_cpu.py
 delete mode 100644 python/tvm/meta_schedule/testing/conv2d_winograd_cuda.py
 create mode 100644 src/meta_schedule/schedule/cpu/winograd.cc
 copy src/meta_schedule/{schedule_rule/auto_bind.cc => schedule/cuda/thread_bind.cc} (61%)
 create mode 100644 src/meta_schedule/schedule/cuda/winograd.cc
 copy include/tvm/topi/detail/array_utils.h => src/meta_schedule/schedule/generic/winograd.cc (56%)
 create mode 100644 src/meta_schedule/schedule/x86/.gitignore
 create mode 100644 src/meta_schedule/schedule_rule/apply_custom_rule.cc
 delete mode 100644 src/meta_schedule/schedule_rule/winograd.cc
 delete mode 100644 tests/python/unittest/test_meta_schedule_custom_rule_winograd_cpu.py
 delete mode 100644 tests/python/unittest/test_meta_schedule_custom_rule_winograd_cuda.py
 create mode 100644 tests/python/unittest/test_meta_schedule_space_cpu_winograd.py
 create mode 100644 tests/python/unittest/test_meta_schedule_space_cuda_winograd.py