blazingly fasterer

validation/raptor.py

@@ -11,6 +11,8 @@ PIM_PASS_LABELS = (
     ("SpatialToPimPass", "Spatial to PIM"),
     ("PimBufferizationPass", "Bufferize PIM"),
     ("HostConstantFoldingPass", "Fold Host Constants"),
+    ("PimMemoryCoalescingPass", "Coalesce Local Memory"),
+    ("PimLocalMemoryPlanningPass", "Plan Local Memory"),
     ("VerificationPass", "Verify PIM"),
     ("EmitPimCodePass", "Emit PIM Code"),
 )

validation/tools/classification_local_image_validation.py

@@ -250,9 +250,9 @@ def main():
     parser.add_argument("--raptor-path", type=Path, default=defaults["raptor_path"])
     parser.add_argument("--onnx-include-dir", type=Path, default=defaults["onnx_include_dir"])
     parser.add_argument("--simulator-dir", type=Path, default=defaults["simulator_dir"])
-    parser.add_argument("--crossbar-size", type=int, default=2048)
-    parser.add_argument("--crossbar-count", type=int, default=256)
-    parser.add_argument("--core-count", type=int, default=1000)
+    parser.add_argument("--crossbar-size", type=int, default=128)
+    parser.add_argument("--crossbar-count", type=int, default=64)
+    parser.add_argument("--core-count", type=int, default=144)
     parser.add_argument("--top-k", type=int, default=5)
     parser.add_argument("--command-timeout-seconds", type=float, default=7200.0)
     parser.add_argument("--skip-compile", action="store_true")

validation/tools/yolo_local_image_validation.py

@@ -198,9 +198,9 @@ def main():
     parser.add_argument("--raptor-path", type=Path, default=defaults["raptor_path"])
     parser.add_argument("--onnx-include-dir", type=Path, default=defaults["onnx_include_dir"])
     parser.add_argument("--simulator-dir", type=Path, default=defaults["simulator_dir"])
-    parser.add_argument("--crossbar-size", type=int, default=2048)
-    parser.add_argument("--crossbar-count", type=int, default=256)
-    parser.add_argument("--core-count", type=int, default=1000)
+    parser.add_argument("--crossbar-size", type=int, default=128)
+    parser.add_argument("--crossbar-count", type=int, default=64)
+    parser.add_argument("--core-count", type=int, default=144)
     parser.add_argument("--command-timeout-seconds", type=float, default=7200.0)
     parser.add_argument("--skip-compile", action="store_true")
     parser.add_argument("--verbose", action="store_true")

validation/tools/yolo_real_image_validation.py

@@ -399,9 +399,9 @@ def main():
     parser.add_argument("--remote-project", default="/home/gmagnani/Project/Raptor")
     parser.add_argument("--remote-python", default="/home/gmagnani/venv/bin/python")
     parser.add_argument("--network-dir", default="validation/networks/yolo11n/depth_51")
-    parser.add_argument("--crossbar-size", type=int, default=2048)
-    parser.add_argument("--crossbar-count", type=int, default=256)
-    parser.add_argument("--core-count", type=int, default=1000)
+    parser.add_argument("--crossbar-size", type=int, default=128)
+    parser.add_argument("--crossbar-count", type=int, default=64)
+    parser.add_argument("--core-count", type=int, default=144)
     parser.add_argument("--command-timeout-seconds", type=int, default=7200)
     parser.add_argument("--skip-compile", action="store_true")
     parser.add_argument("--annotated-dir", default="validation/networks/yolo11n/depth_51/real_image_validation/annotated")

validation/validate.py

@@ -72,10 +72,9 @@ def main():
     ap.add_argument("--relative-threshold", type=float, default=1e-5,
                     help="Relative tolerance for per-element output comparison.")
     ap.add_argument("--seed", type=int, default=0, help="RNG seed for generated validation inputs.")
-    ap.add_argument("--crossbar-size", type=int, default=64)
-    ap.add_argument("--crossbar-count", type=int, default=8)
-    ap.add_argument("--core-count", type=int, default=None,
-                    help="Core count to pass to Raptor. Required for PIM validation.")
+    ap.add_argument("--crossbar-size", type=int, default=128)
+    ap.add_argument("--crossbar-count", type=int, default=64)
+    ap.add_argument("--core-count", type=int, default=144)
     ap.add_argument("--pim-memory-report", choices=("none", "summary", "full"), default="none",
                     help="Emit a human-readable PIM memory planning report during codegen.")
     ap.add_argument("--raptor-extra-arg", action="append", default=[],
@@ -120,8 +119,6 @@ def main():
         missing_args.append("--raptor-path")
     if not a.onnx_include_dir:
         missing_args.append("--onnx-include-dir")
-    if a.core_count is None:
-        missing_args.append("--core-count")
     if missing_args:
         ap.error("the following arguments are required unless --clean is used: " + ", ".join(missing_args))
 

validation/validate_one.py

@@ -311,7 +311,7 @@ def validate_outputs(sim_arrays, runner_out_dir, outputs_descriptor, threshold=1
 
 
 def validate_network(network_onnx_path, raptor_path, onnx_include_dir,
-                     simulator_dir, crossbar_size=64, crossbar_count=8, core_count=None,
+                     simulator_dir, crossbar_size=128, crossbar_count=64, core_count=144,
                      pim_memory_report="none", raptor_extra_args=None,
                      threshold=1e-3, rtol=1e-5,
                      seed=0, reporter=None, model_index=1, model_total=1, verbose=False,