#!/bin/bash
#SBATCH --job-name=lyap_speedup
#SBATCH --account=bfqt-delta-gpu
#SBATCH --partition=gpuA40x4
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=4
#SBATCH --gpus-per-node=1
#SBATCH --mem=32G
#SBATCH --time=01:00:00
#SBATCH --output=runs/slurm_logs/%j_speedup.out
#SBATCH --error=runs/slurm_logs/%j_speedup.err

# ============================================================
# Lyapunov Computation Speedup Benchmark
# ============================================================
# Tests different optimization approaches:
# - Baseline: Current sequential implementation
# - Approach A: Trajectory-as-batch (P=2)
# - Approach B: Global-norm divergence + single-scale renorm
# - Approach C: torch.compile
# - Combined: All optimizations together
# ============================================================

set -e

PROJECT_DIR="/projects/bfqt/users/yurenh2/ml-projects/snn-training"
cd "$PROJECT_DIR"

mkdir -p runs/slurm_logs

echo "============================================================"
echo "Lyapunov Speedup Benchmark"
echo "Job ID: $SLURM_JOB_ID | Node: $SLURM_NODELIST"
echo "Start: $(date)"
echo "============================================================"
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader
echo "============================================================"

# Run main benchmark + scaling tests
python files/experiments/lyapunov_speedup_benchmark.py \
    --batch_size 64 \
    --T 4 \
    --hidden_dims 64 128 256 \
    --scaling

echo "============================================================"
echo "Finished: $(date)"
echo "============================================================"