even better more structured throughput scheduling

plot adjustments
validation adjustments

validation/validate.py

@@ -225,7 +225,7 @@ def main():
     ap.add_argument("--threshold", type=float, default=1e-3,
                     help="Absolute tolerance for per-element output comparison.")
     ap.add_argument("--relative-threshold", type=float, default=1e-5,
-                    help="Relative tolerance for per-element output comparison.")
+                    help="Relative tolerance for per-element and output L2 comparison; 0 disables the L2 check.")
     ap.add_argument("--seed", type=int, default=0, help="RNG seed for generated validation inputs.")
     ap.add_argument("--crossbar-size", type=int, default=default_hardware["crossbar_rows"],
                     help=f"Crossbar size (default: {default_hardware['crossbar_rows']}).")
@@ -416,10 +416,10 @@ def main():
     n_passed = sum(1 for result in results.values() if result.passed)
     n_total = len(results)
     latency_headers = ("Operation", "Arch", "Result", "Compile", "Host mem", "Cores mem",
-                       "Cores", "Xbars", "Latency", "Power", "Energy")
+                       "Cores", "Xbars", "Latency", "Average power", "Energy per inference")
     throughput_headers = ("Operation", "Arch", "Result", "Compile", "Host mem", "Cores mem",
-                          "Cores", "Xbars", "Throughput", "Avg latency", "Avg power",
-                          "Avg energy")
+                          "Cores", "Xbars", "Throughput", "Output interval", "Average power",
+                          "Energy per inference")
     csv_headers = (
         "Operation", "Arch", "Result (l)", "Result (t)",
         "Compile (l)", "Host mem (l)", "Cores mem (l)", "Cores (l)", "Xbars (l)",