[TEST] Cover Gluon Blackwell tensor memory reductions

[Jokeren]

Summary

Add CPU-result coverage for Blackwell tensor-memory load reductions through Gluon.

This adds a focused end-to-end test that:

• stores a 64x64 tile into tensor memory
• slices the tensor-memory descriptor to columns 8:24
• runs load_max and load_min(abs=True) on the sliced descriptor
• checks the loaded values, row maxima, and row min-absolute values against PyTorch references

The branch also returns a distributed AutoLayout for reduced tensor-memory load results in the CPU builder, matching the current Gluon create_tmem_load contract for reduction outputs.

Validation

• PYTHONPATH=/mnt/keren/triton-viz pytest tests/end_to_end/test_gluon_blackwell_tensor_memory_reduction_ops.py -q
• PYTHONPATH=/mnt/keren/triton-viz pytest tests/end_to_end/test_gluon_blackwell_tensor_memory_reduction_ops.py tests/end_to_end/test_gluon_blackwell_tcgen05_copy_ops.py tests/end_to_end/test_gluon_blackwell_tcgen05_scaled_ops.py tests/end_to_end/test_gluon_blackwell_tcgen05_ops.py tests/end_to_end/test_gluon_blackwell_tensor_memory_ops.py tests/end_to_end/test_gluon_wgmma_ops.py tests/end_to_end/test_gluon_tma_im2col_ops.py tests/end_to_end/test_gluon_blackwell_tma_ops.py tests/end_to_end/test_gluon_tma_ops.py tests/end_to_end/test_gluon_async_copy_ops.py tests/end_to_end/test_gluon_core_ops.py tests/end_to_end/test_gluon.py tests/end_to_end/test_core.py tests/unit/test_adapters.py -q
• pre-commit run --files triton_viz/core/simulation/gluon.py tests/end_to_end/test_gluon_blackwell_tensor_memory_reduction_ops.py