test_gpu_scripts/tests/test_b300_judgement.py

91 lines
3.8 KiB
Python

import os
import tempfile
import unittest
from unittest.mock import patch
from modules.benchmark import Benchmark
from modules.gpu_specs import get_gpu_specs
from modules.nccl_test import NCCLTest
from modules.rdma_test import RDMATest
from modules.report import ReportGenerator
from modules.training_sim import TrainingSim
class B300JudgementTests(unittest.TestCase):
def test_b300_training_excludes_cudnn_sdpa(self):
self.assertTrue(TrainingSim._requires_b300_sdpa_workaround("b300", None, 91900))
self.assertTrue(TrainingSim._requires_b300_sdpa_workaround("auto", (10, 3), 91900))
self.assertFalse(TrainingSim._requires_b300_sdpa_workaround("b300", (10, 3), 92000))
self.assertFalse(TrainingSim._requires_b300_sdpa_workaround("h200", (9, 0), 91900))
def test_b300_uses_dense_peaks_and_calibrated_floors(self):
specs = get_gpu_specs("b300")
self.assertEqual(specs["fp8_tflops"], 4500)
self.assertEqual(specs["bf16_tflops"], 2250)
self.assertEqual(specs["compute_pass_thresholds_tflops"]["fp8"], 2800)
self.assertEqual(specs["nccl_pass_thresholds_gbps"]["allreduce"], 750)
def test_compute_verdict_uses_slowest_gpu_not_average(self):
result = {
"compute": {
"per_dtype_tflops": {"fp8": 3000.0},
"worst_per_dtype_tflops": {"fp8": 2500.0},
"pass_thresholds_tflops": {"fp8": 2800.0},
"efficiency_pct": {"fp8": 66.7},
}
}
judged = Benchmark.judge_compute(result)
self.assertEqual(judged["verdict"], "FAIL")
self.assertEqual(judged["rows"][0][1], 2500.0)
def test_rdma_without_peer_is_skip_not_false_failure(self):
rdma = RDMATest({"rdma": {}})
with (
patch.object(rdma, "_get_ib_devices", return_value=["mlx5_0"]),
patch.object(rdma, "_get_ib_ports", return_value=["1"]),
patch.object(rdma, "_read_sys", side_effect=["InfiniBand", "4: ACTIVE"]),
patch.object(rdma, "_collect_device_info", return_value=[]),
):
result = rdma.run()
self.assertEqual(result["status"], "SKIP")
self.assertTrue(result["skipped"])
self.assertIn("peer not configured", result["reason"])
def test_nccl_runtime_env_preserves_and_prepends_venv_libraries(self):
with (
patch("modules.nccl_test.sysconfig.get_paths", return_value={"purelib": "/venv/site"}),
patch("modules.nccl_test.os.path.isdir", return_value=True),
patch.dict(os.environ, {"LD_LIBRARY_PATH": "/system/lib"}),
):
env = NCCLTest._runtime_env()
self.assertEqual(
env["LD_LIBRARY_PATH"],
"/venv/site/nvidia/nccl/lib:/venv/site/torch/lib:/system/lib",
)
self.assertEqual(env["NCCL_DEBUG"], "WARN")
def test_markdown_summary_keeps_warn_and_measured_semantics(self):
results = {
"nccl": {"status": "WARN", "passed": True, "tests": {}},
"training": {
"throughput_tokens_per_sec": 1234,
"gpu_scope": "single_gpu:0",
},
}
generator = ReportGenerator({"report": {"output_dir": "."}})
summary = dict(generator._build_summary(results))
self.assertEqual(summary["NCCL"], "WARN")
self.assertTrue(summary["Training"].startswith("MEASURED"))
with tempfile.TemporaryDirectory() as tmpdir:
path = os.path.join(tmpdir, "report.md")
generator.generate(results, fmt="md", output=path)
with open(path, encoding="utf-8") as report_file:
report = report_file.read()
self.assertIn("| NCCL | WARN |", report)
self.assertIn("synthetic workload; not an 8-GPU scaling acceptance test", report)
if __name__ == "__main__":
unittest.main()