feat: add CUDA Samples compatibility testing

[baominghelly]

Summary

• add a compatibility adapter that builds and runs selected CUDA Samples
• reuse the shared hardware platform layer for platform aliases, compiler discovery, and device visibility
• support CUDA, MetaX, and CoreX build configuration without adding framework-specific Megatron, vLLM, or InfiniLM paths
• add compatibility report generation, documentation, and focused unit tests
• leave Hygon and Moore Threads unconfigured for follow-up support instead of classifying them as unsupported

Review fixes

• run samples from the executable directory so companion kernels and data files resolve correctly
• enforce the requested architecture at the generated CMake target level
• exclude CMake aggregation manifests and parent-dependent libNVVM children from standalone sample counts
• reject empty sample filters before metric calculation
• preserve the DTK/Hygon-specific marker requirement when detecting hipcc

Validation

• python -m pytest -q: 59 passed
• black --check . with Black 23.9.1: passed
• flake8 .: passed
• python -m compileall: passed
• git diff --check: passed
• pinned CUDA Samples 7b601789: 193 standalone projects discovered; no Tegra aggregate or parent-dependent libNVVM children included

Hardware results

• MetaX C550: 3/3 samples compiled and ran successfully
• Tianshu BI-V150: 3/3 samples compiled; 1/3 ran successfully
  • clock: passed
  • matrixMul: failed with zero output values
  • vectorAdd: failed with invalid device function
  • retesting with ivcore10 produced the same result as ivcore20

This remains a draft while the CoreX runtime failures are investigated.