[tvm] branch nightly updated (13b487fa2d -> 71caa19f96)

[gi...@apache.org]

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

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


    from 13b487fa2d [TFLite][Frontend] Support quantized ELU (#15821)
     add 486513ae16 [TIR] Fix offset_factor in cuda tensor core intrins (#15913)
     add ab1aef962a [Target][CI] Add LLVM functions for current system info (#15903)
     add 2afb854cf8 [Relay] fix the conflicted documentation description (#15889)
     add 71caa19f96 [LLVM] Fix for llvm CodeGenOpt API change (#15921)

No new revisions were added by this update.

Summary of changes:
 python/tvm/relay/frontend/keras.py                 |  6 +-
 python/tvm/target/codegen.py                       | 42 ++++++++++
 python/tvm/testing/utils.py                        | 89 +++++++---------------
 python/tvm/tir/tensor_intrin/cuda.py               | 46 +++++------
 src/target/llvm/codegen_amdgpu.cc                  | 11 ++-
 src/target/llvm/codegen_hexagon.cc                 |  5 +-
 src/target/llvm/codegen_llvm.cc                    | 18 +++++
 src/target/llvm/codegen_nvptx.cc                   |  5 +-
 src/target/llvm/llvm_instance.cc                   | 51 ++++++++++++-
 src/target/llvm/llvm_instance.h                    |  8 ++
 src/target/llvm/llvm_module.cc                     | 39 +++++++++-
 tests/python/contrib/test_amx.py                   | 13 +++-
 tests/python/contrib/test_gemm_acc32_vnni.py       |  4 +-
 tests/python/integration/test_auto_tensorize.py    | 12 +--
 tests/python/relay/test_op_level1.py               |  4 +-
 tests/python/relay/test_op_level10.py              |  4 +-
 tests/python/relay/test_op_level2.py               |  4 +-
 tests/python/target/test_llvm_features_info.py     |  6 ++
 .../unittest/test_meta_schedule_cpu_dot_product.py |  8 +-
 19 files changed, 255 insertions(+), 120 deletions(-)