url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

profile CPU GPU tier execution costs

Browse Source
This commit is contained in:
ZacharyZcR
2026-07-18 04:54:59 +08:00
parent 8b36736e5d
commit c3a90eca36
3 changed files with 69 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/tools/benchmark_cuda_fixture.py
+25 -3
View File
@@ -17,6 +17,11 @@ PROFILE_RE = re.compile(
r"\| attention ([0-9.]+)s .* lm_head ([0-9.]+)s \| other ([0-9.-]+)s"
)
PROFILE_KEYS = ("disk", "expert_matmul", "attention", "lm_head", "other")
P0_RE = re.compile(
r"P0-EXEC: routed CPU ([0-9.]+)s \| routed GPU critical ([0-9.]+)s \| "
r"router ([0-9.]+)s \| residual P2P ([0-9.]+)s / ([0-9]+) hop \| orchestration ([0-9.]+)s"
)
P0_KEYS = ("routed_cpu", "routed_gpu_critical", "router", "p2p", "p2p_hops", "orchestration")
def parse_output(stdout: str, stderr: str = "") -> tuple[float, list[float]]:
@@ -30,11 +35,20 @@ def parse_output(stdout: str, stderr: str = "") -> tuple[float, list[float]]:
return float(speed.group(1)), [disk] + [float(value) for value in rest]
def execute(engine: str, env: dict[str, str]) -> tuple[float, list[float]]:
def parse_p0(stdout: str) -> list[float]:
"""Extract the optional PROF=1 execution-layer breakdown."""
row = P0_RE.search(stdout)
if not row:
raise RuntimeError("benchmark output missing P0-EXEC profile")
return [float(value) for value in row.groups()]
def execute(engine: str, env: dict[str, str]) -> tuple[float, list[float], list[float]]:
run = subprocess.run(
[engine, "4", "4", "4"], env=env, text=True, capture_output=True, check=True
)
return parse_output(run.stdout, run.stderr)
speed, profile = parse_output(run.stdout, run.stderr)
return speed, profile, parse_p0(run.stdout)
def main() -> None:
@@ -63,6 +77,8 @@ def main() -> None:
OMP_NUM_THREADS=str(args.threads),
OMP_PROC_BIND="spread",
OMP_PLACES="cores",
DRAFT="0",
PROF="1",
)
execute(args.engine, base | {"STATS": str(stats)})
@@ -86,13 +102,15 @@ def main() -> None:
execute(args.engine, base | extra) # warm-up
speeds = {name: [] for name in modes}
profiles = {name: [] for name in modes}
p0_profiles = {name: [] for name in modes}
names = list(modes)
for run_index in range(args.runs):
order = names[run_index % len(names):] + names[:run_index % len(names)]
for name in order:
speed, profile = execute(args.engine, base | modes[name])
speed, profile, p0 = execute(args.engine, base | modes[name])
speeds[name].append(speed)
profiles[name].append(profile)
p0_profiles[name].append(p0)
result = {}
for name in names:
@@ -103,6 +121,10 @@ def main() -> None:
key: statistics.median(row[index] for row in profiles[name])
for index, key in enumerate(PROFILE_KEYS)
},
"median_p0": {
key: statistics.median(row[index] for row in p0_profiles[name])
for index, key in enumerate(P0_KEYS)
},
}
print(json.dumps(result, indent=2))