unify memory opimization passes

better reports
cleanups

validation/raptor.py

@@ -11,7 +11,6 @@ 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"),
@@ -43,7 +42,7 @@ def _format_command(cmd):
 
 def compile_with_raptor(network_path, raptor_onnx_path: Path, output_base: Path,
                         crossbar_size, crossbar_count, core_count=None,
-                        pim_memory_report="none", raptor_extra_args=None, cwd=None, verbose=False,
+                        raptor_extra_args=None, cwd=None, verbose=False,
                         reporter=None, timeout_sec=None):
     # Define the arguments, with the possibility to set crossbar size and count
     args = [
@@ -57,8 +56,6 @@ def compile_with_raptor(network_path, raptor_onnx_path: Path, output_base: Path,
     ]
     if core_count is not None:
         args.append(f"--core-count={core_count}")
-    if pim_memory_report != "none":
-        args.append(f"--pim-memory-report={pim_memory_report}")
     if raptor_extra_args:
         args.extend(str(arg) for arg in raptor_extra_args)
     if verbose:

validation/validate.py

@@ -75,8 +75,6 @@ def main():
     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=[],
                     help="Additional argument to pass through to the Raptor compiler. Repeat as needed.")
     ap.add_argument("--command-timeout-seconds", type=float, default=1000000.0,
@@ -144,7 +142,6 @@ def main():
             result = validate_network(
                 onnx_path, a.raptor_path, a.onnx_include_dir, simulator_dir,
                 crossbar_size=a.crossbar_size, crossbar_count=a.crossbar_count, core_count=a.core_count,
-                pim_memory_report=a.pim_memory_report,
                 raptor_extra_args=a.raptor_extra_arg,
                 command_timeout_seconds=a.command_timeout_seconds,
                 threshold=a.threshold,

validation/validate_one.py

@@ -312,7 +312,7 @@ 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=128, crossbar_count=64, core_count=144,
-                     pim_memory_report="none", raptor_extra_args=None,
+                     raptor_extra_args=None,
                      threshold=1e-3, rtol=1e-5,
                      seed=0, reporter=None, model_index=1, model_total=1, verbose=False,
                      command_timeout_seconds=60.0, mode=MODE_FULL):
@@ -367,7 +367,7 @@ def validate_network(network_onnx_path, raptor_path, onnx_include_dir,
                 pim_pass_timings = compile_with_raptor(
                     network_onnx_path, raptor_path, pim_output_base, crossbar_size, crossbar_count,
                     core_count=core_count,
-                    pim_memory_report=pim_memory_report, raptor_extra_args=raptor_extra_args,
+                    raptor_extra_args=raptor_extra_args,
                     cwd=raptor_dir, verbose=verbose, reporter=reporter, timeout_sec=command_timeout_seconds)
                 print_info(reporter, f"PIM artifacts saved to {raptor_dir / 'pim'}")
                 reporter.advance()
@@ -407,7 +407,7 @@ def validate_network(network_onnx_path, raptor_path, onnx_include_dir,
             pim_pass_timings = compile_with_raptor(
                 network_onnx_path, raptor_path, pim_output_base, crossbar_size, crossbar_count,
                 core_count=core_count,
-                pim_memory_report=pim_memory_report, raptor_extra_args=raptor_extra_args,
+                raptor_extra_args=raptor_extra_args,
                 cwd=raptor_dir, verbose=verbose, reporter=reporter, timeout_sec=command_timeout_seconds)
             print_info(reporter, f"PIM artifacts saved to {raptor_dir / 'pim'}")
             reporter.advance()