This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 5786e82 add dnnl (#5936)
add eb66fd9 [TIR][OP][API-CHANGE] Remove CallNode.call_type in favor of
attribute. (#5937)
No new revisions were added by this update.
Summary of changes:
include/tvm/tir/builtin.h | 34 ++++-
include/tvm/tir/expr.h | 28 +---
include/tvm/tir/op.h | 16 +--
include/tvm/tir/op_attr_types.h | 37 +++++
python/tvm/te/hybrid/calls.py | 4 +-
python/tvm/tir/__init__.py | 8 +-
python/tvm/tir/expr.py | 39 +++--
python/tvm/tir/ir_builder.py | 3 +-
python/tvm/tir/op.py | 127 ++++++++--------
src/arith/ir_mutator_with_analyzer.cc | 2 +-
src/arith/pattern_match.h | 26 ++--
src/contrib/hybrid/codegen_hybrid.cc | 3 +-
src/printer/tir_text_printer.cc | 20 +--
src/target/intrin_rule.cc | 50 +++----
src/target/intrin_rule.h | 4 +-
src/target/llvm/codegen_arm.cc | 15 +-
src/target/llvm/codegen_llvm.cc | 4 +-
src/target/llvm/codegen_llvm.h | 3 +
src/target/llvm/codegen_x86_64.cc | 11 +-
src/target/llvm/intrin_rule_llvm.h | 5 +-
src/target/llvm/intrin_rule_nvptx.cc | 48 +++----
src/target/llvm/intrin_rule_rocm.cc | 61 ++++----
src/target/source/codegen_c.cc | 2 +-
src/target/source/codegen_c.h | 1 +
src/target/source/intrin_rule_aocl.cc | 44 +++---
src/target/source/intrin_rule_cuda.cc | 55 +++----
src/target/source/intrin_rule_metal.cc | 40 +++---
src/target/source/intrin_rule_opencl.cc | 42 +++---
src/target/source/intrin_rule_vhls.cc | 38 ++---
src/target/spirv/codegen_spirv.cc | 10 +-
src/target/spirv/intrin_rule_spirv.cc | 3 +-
src/te/autodiff/jacobian.cc | 52 ++++---
src/te/operation/compute_op.cc | 7 +-
src/te/operation/cross_thread_reduction.cc | 4 +-
src/te/operation/extern_op.cc | 2 +-
src/te/operation/tensor_compute_op.cc | 12 +-
src/te/operation/tensorize.cc | 12 +-
.../schedule_postproc_rewrite_for_tensor_core.cc | 23 ++-
src/tir/analysis/side_effect.cc | 16 ++-
src/tir/ir/buffer.cc | 2 +-
src/tir/ir/expr.cc | 7 +-
src/tir/ir/expr_functor.cc | 2 +-
src/tir/ir/stmt.cc | 6 +-
src/tir/op/builtin.cc | 160 +++++++++++++++------
src/tir/op/op.cc | 60 ++++----
src/tir/op/runtime.cc | 6 +-
src/tir/transforms/arg_binder.cc | 3 +-
src/tir/transforms/bf16_legalize.cc | 4 +-
src/tir/transforms/coproc_sync.cc | 12 +-
src/tir/transforms/inject_virtual_thread.cc | 3 +-
src/tir/transforms/ir_util.h | 9 +-
src/tir/transforms/lower_intrin.cc | 20 ++-
src/tir/transforms/lower_thread_allreduce.cc | 8 +-
src/tir/transforms/lower_tvm_builtin.cc | 20 +--
src/tir/transforms/lower_warp_memory.cc | 5 +-
src/tir/transforms/make_packed_api.cc | 5 +-
src/tir/transforms/rewrite_unsafe_select.cc | 18 ++-
src/tir/transforms/split_host_device.cc | 3 +-
src/tir/transforms/storage_flatten.cc | 6 +-
src/tir/transforms/storage_rewrite.cc | 3 +-
src/tir/transforms/thread_storage_sync.cc | 11 +-
src/tir/transforms/vectorize_loop.cc | 6 +-
tests/cpp/ir_functor_test.cc | 4 +-
.../unittest/test_arith_canonical_simplify.py | 2 +-
.../python/unittest/test_target_codegen_c_host.py | 2 +-
tests/python/unittest/test_target_codegen_llvm.py | 8 +-
tests/python/unittest/test_tir_constructor.py | 3 +-
tests/python/unittest/test_tir_nodes.py | 26 ++--
.../unittest/test_tir_transform_bf16_legalize.py | 12 +-
.../test_tir_transform_combine_context_call.py | 2 +-
.../test_tir_transform_inject_virtual_thread.py | 2 +-
topi/include/topi/detail/extern.h | 14 +-
topi/include/topi/elemwise.h | 3 +-
topi/python/topi/arm_cpu/bitserial_conv2d.py | 28 ++--
topi/python/topi/arm_cpu/tensor_intrin.py | 13 +-
topi/python/topi/cuda/nms.py | 6 +-
topi/python/topi/cuda/rcnn/proposal.py | 6 +-
topi/python/topi/cuda/sort.py | 9 +-
topi/python/topi/x86/tensor_intrin.py | 70 ++++-----
tutorials/language/intrin_math.py | 4 +-
vta/python/vta/environment.py | 12 +-
vta/python/vta/transform.py | 2 +-
82 files changed, 800 insertions(+), 718 deletions(-)
