[Do not merge] Fix test_barrier hang by using static global rank in ProcessGroupXCCL

[frost-intel]

Fixes #1978

In ProcessGroupNCCL, globalRank() returns a static int globalRank, which is first initialized by the ProcessGroup setup, so the globalRank assigned to each thread matches the id of the CUDA device. However, we were not using this same pattern for XCCL. Instead, we were just using the assigned rank of the thread, which were not necessarily the same as the globalRank.

The failing test test_barrier created two separate groups of 2 ranks each, and then 4 threads called barrier, but all on the same 2-thread group. Since initially the device id is not specified in this barrier call, the thread attempts to "guess" the device index. In the previous code, this guess would be 0 or 1, since the rank of each thread was not actually the globalRank. In barrier, this guessed id was used to initialize XCCLComm objects, and then call allreduce on a single element tensor. However, this resulted in an allreduce call two times on each device, which could result in a hang based on the execution order of the 4 threads.

With the update in this PR, PGXCCL now uses the static globalRank in the same places as ProcessGroupNCCL, so the initialized XCCLComm objects are for unique devices and allreduce doesn't call on the same device multiple times.

[frost-intel]

Please wait on merging, I want to confirm behavior in scale-out test.

[Copilot]

Pull Request Overview

This PR fixes a hang in the test_barrier test by making ProcessGroupXCCL use static global ranks consistently, matching the pattern used in ProcessGroupNCCL. The issue occurred when multiple threads used the same device ID for barrier operations, causing duplicate allreduce calls that could hang based on execution order.

Key changes:

• Added globalRank() method that returns a static global rank value
• Updated device ID guessing logic to use global rank instead of thread rank
• Updated logging and debugging to reference global rank consistently

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
ProcessGroupXCCL.hpp	Added declaration for globalRank() method
ProcessGroupXCCL.cpp	Implemented globalRank() method and updated references to use it

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

The static variable globalRank is initialized from rank_ on first call, but this could lead to race conditions if multiple threads call this method simultaneously during initialization. Consider using std::call_once or atomic operations to ensure thread-safe initialization.

Suggested change

	const int& ProcessGroupXCCL::globalRank() const {
	static int globalRank = rank_;
	return globalRank;
	int ProcessGroupXCCL::globalRank() const {
	return rank_;