Files
aituner/runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh

118 lines
4.5 KiB
Bash

#!/usr/bin/env bash
set -euo pipefail
TP="${1:?usage: run_simulator_group.sh TP MODE}"
MODE="${2:?usage: run_simulator_group.sh TP MODE}"
case "${TP}" in
1|2|4) ;;
*) echo "ERROR: TP must be 1, 2, or 4" >&2; exit 2 ;;
esac
case "${MODE}" in
false|true|both) ;;
*) echo "ERROR: mode must be false, true, or both" >&2; exit 2 ;;
esac
CHECKOUT="${CHECKOUT:-$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)}"
EXPERIMENT_ROOT="${EXPERIMENT_ROOT:-/home/admin/cpfs/wjh/aituner/workload-regime-20260720}"
TRACES_ROOT="${TRACES_ROOT:-${EXPERIMENT_ROOT}/traces}"
FRONTIER_SOURCE="${FRONTIER_SOURCE:-/home/admin/cpfs/wjh/aituner/frontier-t1-dash0-deadc4a}"
REPLAYSERVE_ROOT="${REPLAYSERVE_ROOT:-/home/admin/cpfs/wjh/replayserve}"
PROFILE_ROOT="${PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/profile-v4-trace-final}"
KERNEL_PROFILE_ROOT="${KERNEL_PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/graph-piecewise-qwen30-20260717/full/frozen-kernel-only}"
ALLREDUCE_CSV="${ALLREDUCE_CSV:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/measured-allreduce.csv}"
CUSTOM_PYTHON_DEPS="${CUSTOM_PYTHON_DEPS:-${EXPERIMENT_ROOT}/python-deps}"
BASE_PYTHON_DEPS="${BASE_PYTHON_DEPS:-/home/admin/cpfs/wjh/venvs/qwen36-vllm-0.20.2/lib/python3.12/site-packages}"
RUNNER="${CHECKOUT}/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py"
for path in "${TRACES_ROOT}/manifest.json" "${FRONTIER_SOURCE}" \
"${REPLAYSERVE_ROOT}" "${PROFILE_ROOT}" "${KERNEL_PROFILE_ROOT}" \
"${ALLREDUCE_CSV}" "${CUSTOM_PYTHON_DEPS}" "${BASE_PYTHON_DEPS}" \
"${RUNNER}"; do
[[ -e "${path}" ]] || { echo "ERROR: missing ${path}" >&2; exit 1; }
done
run_mode() {
local prefix_mode="$1" output_root prefix_flag family
local -a families traces configs command
output_root="${EXPERIMENT_ROOT}/sim/tp${TP}-prefix-${prefix_mode}"
mkdir -p "${output_root}/provenance"
if [[ "${prefix_mode}" == "true" ]]; then
prefix_flag="--prefix-caching"
else
prefix_flag="--no-prefix-caching"
fi
mapfile -t families < <(
jq -r --argjson prefix "${prefix_mode}" '
.cases
| map(select(.prefix_caching == $prefix))
| map(.family)
| unique
| .[]
' "${TRACES_ROOT}/manifest.json"
)
[[ "${#families[@]}" -gt 0 ]] || { echo "ERROR: empty family group" >&2; exit 1; }
for mns in 8 16 32 64; do
configs+=(--config "tp${TP}_mns${mns}")
done
{
printf 'host=%s\n' "$(hostname)"
printf 'tp=%s\n' "${TP}"
printf 'prefix_mode=%s\n' "${prefix_mode}"
printf 'family_count=%s\n' "${#families[@]}"
git -C "${CHECKOUT}" rev-parse HEAD
git -C "${FRONTIER_SOURCE}" rev-parse HEAD
sha256sum "${TRACES_ROOT}/manifest.json" "${PROFILE_ROOT}/manifest.json" \
"${KERNEL_PROFILE_ROOT}/manifest.json" "${ALLREDUCE_CSV}"
} > "${output_root}/provenance/launch.txt"
for family in "${families[@]}"; do
traces=()
command=()
mapfile -t traces < <(
jq -r --arg family "${family}" '
.cases
| map(select(.family == $family))
| sort_by(.global_offered_request_rate)
| .[]
| "\(.family)-rho\(.rho | tostring | gsub("\\."; "p"))=\(.public_csv)"
' "${TRACES_ROOT}/manifest.json"
)
[[ "${#traces[@]}" -eq 5 ]] || {
echo "ERROR: expected five load anchors for ${family}" >&2
exit 1
}
for trace in "${traces[@]}"; do
command+=(--trace "${trace}")
done
printf 'SIMULATOR_FAMILY_START family=%s tp=%s prefix=%s\n' \
"${family}" "${TP}" "${prefix_mode}"
PYTHONPATH="${BASE_PYTHON_DEPS}" /usr/bin/python3 "${RUNNER}" \
--frontier-source "${FRONTIER_SOURCE}" \
--replayserve-root "${REPLAYSERVE_ROOT}" \
--profile-root "${PROFILE_ROOT}" \
--kernel-profile-root "${KERNEL_PROFILE_ROOT}" \
--python-deps "${CUSTOM_PYTHON_DEPS}" \
--output-root "${output_root}" \
"${command[@]}" "${configs[@]}" \
--rate-contract trace-window "${prefix_flag}" \
--cc-backend vidur --allreduce-csv "${ALLREDUCE_CSV}" \
--timeout-seconds 3600 --predictor-training-job-threads 4 \
--decode-cuda-graph-mode piecewise --align-real-graph-runtime \
--store-stage-batch-ledger --resume --continue-on-failure
cp "${output_root}/frontier_trace_surface_frozen.json" \
"${output_root}/frontier_trace_surface_${family}.json"
done
}
if [[ "${MODE}" == "both" ]]; then
run_mode false
run_mode true
else
run_mode "${MODE}"
fi