Add PCIe transfer benchmark (H2D/D2H) for Ironwood

[linamy85]

• Implement benchmark_pcie_transfer.py to measure H2D and D2H transfer performance using JAX, supporting various transfer modes (Standard, Parallel, Threaded, Chunked).
• Integrate the new benchmark into run_benchmark.py.
• Add configuration files for single device, single chip, and single VM topologies in configs/pcie_transfer/.
• Add scripts/run_pcie_transfer_benchmark.sh for bulk execution with numactl interleaving option.
• Add guides/pcie_transfer to run on Kubernetes Ironwood 2x2x1

[chishuen]

Thank you for the PR. Shall we rename pcie_transfer to something else everywhere, because in a TPU tray or VM (consists of 4 chips), there are a few places where PCIe is used if I understand it correctly from https://docs.cloud.google.com/tpu/docs/tpu7x. Replace the name with something like host_device? Wdyt?

[linamy85]

Thanks Chi, the PR has been updated