Add multi-nodes example & update doc

[Binyang2014]

Documentation update:

• docs/design/mscclpp-dsl.md: Updated the link to the examples folder to reflect the correct path.

New example script:

• python/examples/allgather_allpairs_multinodes_packets.py: Added a new example script demonstrating the allgather all-pairs algorithm across multiple nodes using packet communication.

IR module improvements:

• python/mscclpp/language/ir.py: Refined the sorting criteria for GPU instance channels and thread block channels to include the channel type, ensuring a more accurate order.
  Debugging enhancements:

• src/executor/executor.cc: Added a debug log to indicate the start of communication collective execution with details about the execution plan and collective.

• src/include/debug.h: Introduced a new debug log subsystem identifier MSCCLPP_EXECUTOR for logging executor-related information.

Copilot reviewed 3 out of 6 changed files in this pull request and generated no comments.

Files not reviewed (3)

• python/test/configs/mscclpp_lang_test_config.json: Language not supported
• src/executor/executor.cc: Language not supported
• src/include/debug.h: Language not supported

Comments suppressed due to low confidence (1)

python/examples/allgather_allpairs_multinodes_packets.py:11

• The docstring should clearly explain the purpose of the gpus_per_node argument and ensure that the steps listed are complete or rephrase to avoid implying there are more steps.

def allgather_multinodes_allpair(gpus, gpus_per_node, instances):