From 495ffc4777522e40941753e3b1b79c02f84b25b4 Mon Sep 17 00:00:00 2001
From: Grafting Rayman <156515434+GraftingRayman@users.noreply.github.com>
Date: Fri, 17 Jan 2025 11:00:30 +0000
Subject: Add files via upload

---
 r_basicsr/utils/dist_util.py | 82 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 82 insertions(+)
 create mode 100644 r_basicsr/utils/dist_util.py

(limited to 'r_basicsr/utils/dist_util.py')

diff --git a/r_basicsr/utils/dist_util.py b/r_basicsr/utils/dist_util.py
new file mode 100644
index 0000000..380f155
--- /dev/null
+++ b/r_basicsr/utils/dist_util.py
@@ -0,0 +1,82 @@
+# Modified from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/dist_utils.py  # noqa: E501
+import functools
+import os
+import subprocess
+import torch
+import torch.distributed as dist
+import torch.multiprocessing as mp
+
+
+def init_dist(launcher, backend='nccl', **kwargs):
+    if mp.get_start_method(allow_none=True) is None:
+        mp.set_start_method('spawn')
+    if launcher == 'pytorch':
+        _init_dist_pytorch(backend, **kwargs)
+    elif launcher == 'slurm':
+        _init_dist_slurm(backend, **kwargs)
+    else:
+        raise ValueError(f'Invalid launcher type: {launcher}')
+
+
+def _init_dist_pytorch(backend, **kwargs):
+    rank = int(os.environ['RANK'])
+    num_gpus = torch.cuda.device_count()
+    torch.cuda.set_device(rank % num_gpus)
+    dist.init_process_group(backend=backend, **kwargs)
+
+
+def _init_dist_slurm(backend, port=None):
+    """Initialize slurm distributed training environment.
+
+    If argument ``port`` is not specified, then the master port will be system
+    environment variable ``MASTER_PORT``. If ``MASTER_PORT`` is not in system
+    environment variable, then a default port ``29500`` will be used.
+
+    Args:
+        backend (str): Backend of torch.distributed.
+        port (int, optional): Master port. Defaults to None.
+    """
+    proc_id = int(os.environ['SLURM_PROCID'])
+    ntasks = int(os.environ['SLURM_NTASKS'])
+    node_list = os.environ['SLURM_NODELIST']
+    num_gpus = torch.cuda.device_count()
+    torch.cuda.set_device(proc_id % num_gpus)
+    addr = subprocess.getoutput(f'scontrol show hostname {node_list} | head -n1')
+    # specify master port
+    if port is not None:
+        os.environ['MASTER_PORT'] = str(port)
+    elif 'MASTER_PORT' in os.environ:
+        pass  # use MASTER_PORT in the environment variable
+    else:
+        # 29500 is torch.distributed default port
+        os.environ['MASTER_PORT'] = '29500'
+    os.environ['MASTER_ADDR'] = addr
+    os.environ['WORLD_SIZE'] = str(ntasks)
+    os.environ['LOCAL_RANK'] = str(proc_id % num_gpus)
+    os.environ['RANK'] = str(proc_id)
+    dist.init_process_group(backend=backend)
+
+
+def get_dist_info():
+    if dist.is_available():
+        initialized = dist.is_initialized()
+    else:
+        initialized = False
+    if initialized:
+        rank = dist.get_rank()
+        world_size = dist.get_world_size()
+    else:
+        rank = 0
+        world_size = 1
+    return rank, world_size
+
+
+def master_only(func):
+
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+        rank, _ = get_dist_info()
+        if rank == 0:
+            return func(*args, **kwargs)
+
+    return wrapper
-- 
cgit v1.2.3