Add suspend/resume to execute (#20983)

Differential Revision: D112413599

Pull Request resolved: #20983

Author: JakeStevens

backends/nxp/runtime/NeutronBackend.cpp

@@ -523,25 +523,45 @@ class NeutronBackend final : public PyTorchBackendInterface {
       }
     }
 
+    // Resume (clock-ungate) the NPU immediately before inference and suspend it
+    // again immediately after, so its clock only runs during compute
+#ifdef NEUTRON_NPU_POWER_GATING
+    NeutronError resumeRC = neutronResume();
+    if (resumeRC != ENONE) {
+      ET_LOG(Error, "neutronResume failed with error code %ld", resumeRC);
+      return Error::InvalidProgram;
+    }
+#endif
+
 #ifdef ET_EVENT_TRACER_ENABLED
     // Save ticks before neutron compute to measure how much time profiling dump
     // takes
     et_timestamp_t start_ticks = ::executorch::runtime::pal_current_ticks();
 #endif
     // Run neutron compute.
     NeutronError neutronRC = neutronRunBlocking(cfg->nmh, &cfg->dcfg);
+#ifdef ET_EVENT_TRACER_ENABLED
+    // Save ticks after neutron compute to measure how much time profiling dump
+    // takes
+    et_timestamp_t stop_ticks = ::executorch::runtime::pal_current_ticks();
+#endif
+
+#ifdef NEUTRON_NPU_POWER_GATING
+    // Suspend (clock-gate) the NPU again regardless of the run result; a failed
+    // suspend only wastes power, so it must not fail the inference.
+    NeutronError suspendRC = neutronSuspend();
+    if (suspendRC != ENONE) {
+      ET_LOG(Error, "neutronSuspend failed with error code %ld", suspendRC);
+    }
+#endif
+
     if (neutronRC != ENONE) {
       ET_LOG(
           Error,
           "Neutron model evaluation failed with error code %ld",
           neutronRC);
       return Error::InvalidProgram;
     }
-#ifdef ET_EVENT_TRACER_ENABLED
-    // Save ticks after neutron compute to measure how much time profiling dump
-    // takes
-    et_timestamp_t stop_ticks = ::executorch::runtime::pal_current_ticks();
-#endif
 
     // Transpose outputs.
     for (int i = 0; i < cfg->numOutputs; i++) {

backends/nxp/runtime/targets.bzl

@@ -11,7 +11,9 @@ def define_common_targets():
         ],
         link_whole = True,
         # Constructor needed for backend registration.
-        compiler_flags = ["-Wno-global-constructors", "-fno-rtti", "-DNO_HEAP_USAGE"],
+        # NEUTRON_NPU_POWER_GATING clock-gates the NPU around each inference
+        # (neutronResume/neutronSuspend in NeutronBackend.cpp).
+        compiler_flags = ["-Wno-global-constructors", "-fno-rtti", "-DNO_HEAP_USAGE", "-DNEUTRON_NPU_POWER_GATING"],
         labels = [ci.skip_target()],
         visibility = ["PUBLIC"],
         deps = [