Fix inclusive scan for large sizes (#6234)

tests/python-gpu/test_large_input.py

@@ -0,0 +1,21 @@
+import numpy as np
+import xgboost as xgb
+import cupy as cp
+import time
+import pytest
+
+
+# Test for integer overflow or out of memory exceptions
+def test_large_input():
+    available_bytes, _ = cp.cuda.runtime.memGetInfo()
+    # 15 GB
+    required_bytes = 1.5e+10
+    if available_bytes < required_bytes:
+        pytest.skip("Not enough memory on this device")
+    n = 1000
+    m = ((1 << 31) + n - 1) // n
+    assert (np.log2(m * n) > 31)
+    X = cp.ones((m, n), dtype=np.float32)
+    y = cp.ones(m)
+    dmat = xgb.DeviceQuantileDMatrix(X, y)
+    xgb.train({"tree_method": "gpu_hist", "max_depth": 1}, dmat, 1)