Performance improvement: Avoid unnecessary GPU detail queries in _monitor_power()

.context/gpu-benchmark-results.jsonl

@@ -0,0 +1,3 @@
+{"timestamp": "2026-06-22T13:04:21.864329+00:00", "mode": "all", "hostname": "Mac.lan", "gpu_backend": "simulated (8 GPUs)", "gpu_count_real": 0, "simulated": true, "call_breakdown": [{"call_name": "nvmlDeviceGetMemoryInfo", "used_by_monitor": false, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetTemperature", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetPowerUsage", "used_by_monitor": false, "simulated_latency_us": 45}, {"call_name": "nvmlDeviceGetTotalEnergyConsumption", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetUtilizationRates", "used_by_monitor": true, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetComputeMode", "used_by_monitor": false, "simulated_latency_us": 35}, {"call_name": "nvmlDeviceGetComputeRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}, {"call_name": "nvmlDeviceGetGraphicsRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}], "method_benchmarks": [{"method": "get_gpu_details", "gpu_count": 8, "nvml_calls_per_second": 64, "nvml_calls_unused_per_second": 56, "latency_per_call_ms": {"count": 200, "min_ms": 12.55650000530295, "max_ms": 67.93629100138787, "mean_ms": 13.547916884053848, "p50_ms": 12.920312496135011, "p95_ms": 15.044183352438257}, "latency_per_second_ms": 12.920312496135011}, {"method": "get_gpu_utilization_list", "gpu_count": 8, "nvml_calls_per_second": 8, "nvml_calls_unused_per_second": 0, "latency_per_call_ms": {"count": 200, "min_ms": 0.5256250005913898, "max_ms": 0.6670419970760122, "mean_ms": 0.5427240101562347, "p50_ms": 0.5367710036807694, "p95_ms": 0.5937666595855262}, "latency_per_second_ms": 0.5367710036807694}], "projections": [{"metric": "Per-second monitoring overhead", "heavy_path_ms": 12.920312496135011, "lightweight_path_ms": 0.5367710036807694, "savings_ms": 12.383541492454242, "savings_pct": 95.8, "unit": "ms/s"}, {"metric": "Per-minute monitoring overhead", "heavy_path_ms": 775.2187497681007, "lightweight_path_ms": 32.20626022084616, "savings_ms": 743.0124895472545, "savings_pct": 95.8, "unit": "ms/min"}, {"metric": "Per-hour monitoring overhead", "heavy_path_ms": 46513.12498608604, "lightweight_path_ms": 1932.3756132507697, "savings_ms": 44580.74937283527, "savings_pct": 95.8, "unit": "ms/hr"}, {"metric": "Per-day monitoring overhead (24h)", "heavy_path_ms": 1116314.999666065, "lightweight_path_ms": 46377.01471801847, "savings_ms": 1069937.9849480465, "savings_pct": 95.8, "unit": "ms/day"}, {"metric": "Unnecessary NVML calls per second", "heavy_path_value": 56, "lightweight_path_value": 0, "savings_value": 56, "unit": "calls/s"}, {"metric": "Unnecessary NVML calls per hour (on 8 GPUs)", "heavy_path_value": 201600, "lightweight_path_value": 0, "savings_value": 201600, "unit": "calls/hr"}], "result": ""}
+{"timestamp": "2026-06-22T13:04:31.008513+00:00", "mode": "all", "hostname": "Mac.lan", "gpu_backend": "simulated (1 GPU)", "gpu_count_real": 0, "simulated": true, "call_breakdown": [{"call_name": "nvmlDeviceGetMemoryInfo", "used_by_monitor": false, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetTemperature", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetPowerUsage", "used_by_monitor": false, "simulated_latency_us": 45}, {"call_name": "nvmlDeviceGetTotalEnergyConsumption", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetUtilizationRates", "used_by_monitor": true, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetComputeMode", "used_by_monitor": false, "simulated_latency_us": 35}, {"call_name": "nvmlDeviceGetComputeRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}, {"call_name": "nvmlDeviceGetGraphicsRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}], "method_benchmarks": [{"method": "get_gpu_details", "gpu_count": 1, "nvml_calls_per_second": 8, "nvml_calls_unused_per_second": 7, "latency_per_call_ms": {"count": 200, "min_ms": 1.5633330040145665, "max_ms": 1.9456660083960742, "mean_ms": 1.6176056357653579, "p50_ms": 1.605146004294511, "p95_ms": 1.665493459586287}, "latency_per_second_ms": 1.605146004294511}, {"method": "get_gpu_utilization_list", "gpu_count": 1, "nvml_calls_per_second": 1, "nvml_calls_unused_per_second": 0, "latency_per_call_ms": {"count": 200, "min_ms": 0.06458298594225198, "max_ms": 0.14504100545309484, "mean_ms": 0.06767040984414052, "p50_ms": 0.06535449210787192, "p95_ms": 0.0750916529796086}, "latency_per_second_ms": 0.06535449210787192}], "projections": [{"metric": "Per-second monitoring overhead", "heavy_path_ms": 1.605146004294511, "lightweight_path_ms": 0.06535449210787192, "savings_ms": 1.539791512186639, "savings_pct": 95.9, "unit": "ms/s"}, {"metric": "Per-minute monitoring overhead", "heavy_path_ms": 96.30876025767066, "lightweight_path_ms": 3.921269526472315, "savings_ms": 92.38749073119834, "savings_pct": 95.9, "unit": "ms/min"}, {"metric": "Per-hour monitoring overhead", "heavy_path_ms": 5778.525615460239, "lightweight_path_ms": 235.2761715883389, "savings_ms": 5543.2494438719, "savings_pct": 95.9, "unit": "ms/hr"}, {"metric": "Per-day monitoring overhead (24h)", "heavy_path_ms": 138684.61477104574, "lightweight_path_ms": 5646.628118120134, "savings_ms": 133037.9866529256, "savings_pct": 95.9, "unit": "ms/day"}, {"metric": "Unnecessary NVML calls per second", "heavy_path_value": 7, "lightweight_path_value": 0, "savings_value": 7, "unit": "calls/s"}, {"metric": "Unnecessary NVML calls per hour (on 1 GPU)", "heavy_path_value": 25200, "lightweight_path_value": 0, "savings_value": 25200, "unit": "calls/hr"}], "result": ""}
+{"timestamp": "2026-07-02T03:54:32.856813+00:00", "mode": "all", "hostname": "Mac.lan", "gpu_backend": "simulated (1 GPU)", "gpu_count_real": 0, "simulated": true, "call_breakdown": [{"call_name": "nvmlDeviceGetMemoryInfo", "used_by_monitor": false, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetTemperature", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetPowerUsage", "used_by_monitor": false, "simulated_latency_us": 45}, {"call_name": "nvmlDeviceGetTotalEnergyConsumption", "used_by_monitor": false, "simulated_latency_us": 40}, {"call_name": "nvmlDeviceGetUtilizationRates", "used_by_monitor": true, "simulated_latency_us": 50}, {"call_name": "nvmlDeviceGetComputeMode", "used_by_monitor": false, "simulated_latency_us": 35}, {"call_name": "nvmlDeviceGetComputeRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}, {"call_name": "nvmlDeviceGetGraphicsRunningProcesses", "used_by_monitor": false, "simulated_latency_us": 500}], "method_benchmarks": [{"method": "get_gpu_details", "gpu_count": 1, "nvml_calls_per_second": 8, "nvml_calls_unused_per_second": 7, "latency_per_call_ms": {"count": 200, "min_ms": 1.4970839984016493, "max_ms": 1.756750003551133, "mean_ms": 1.6207081100947107, "p50_ms": 1.6159379993041512, "p95_ms": 1.666629193641711}, "latency_per_second_ms": 1.6159379993041512}, {"method": "get_gpu_utilization_list", "gpu_count": 1, "nvml_calls_per_second": 1, "nvml_calls_unused_per_second": 0, "latency_per_call_ms": {"count": 200, "min_ms": 0.062167004216462374, "max_ms": 0.13416699948720634, "mean_ms": 0.06766192989744013, "p50_ms": 0.0667294989398215, "p95_ms": 0.07051039865473285}, "latency_per_second_ms": 0.0667294989398215}], "projections": [{"metric": "Per-second monitoring overhead", "heavy_path_ms": 1.6159379993041512, "lightweight_path_ms": 0.0667294989398215, "savings_ms": 1.5492085003643297, "savings_pct": 95.9, "unit": "ms/s"}, {"metric": "Per-minute monitoring overhead", "heavy_path_ms": 96.95627995824907, "lightweight_path_ms": 4.00376993638929, "savings_ms": 92.95251002185978, "savings_pct": 95.9, "unit": "ms/min"}, {"metric": "Per-hour monitoring overhead", "heavy_path_ms": 5817.376797494944, "lightweight_path_ms": 240.2261961833574, "savings_ms": 5577.150601311587, "savings_pct": 95.9, "unit": "ms/hr"}, {"metric": "Per-day monitoring overhead (24h)", "heavy_path_ms": 139617.04313987866, "lightweight_path_ms": 5765.428708400577, "savings_ms": 133851.61443147808, "savings_pct": 95.9, "unit": "ms/day"}, {"metric": "Unnecessary NVML calls per second", "heavy_path_value": 7, "lightweight_path_value": 0, "savings_value": 7, "unit": "calls/s"}, {"metric": "Unnecessary NVML calls per hour (on 1 GPU)", "heavy_path_value": 25200, "lightweight_path_value": 0, "savings_value": 25200, "unit": "calls/hr"}], "result": ""}

codecarbon/core/gpu.py

@@ -137,6 +137,23 @@ def get_gpu_details(self) -> List:
             logger.warning("Failed to retrieve gpu information", exc_info=True)
             return []
 
+    def get_gpu_utilization_list(self) -> List:
+        """Lightweight alternative to :meth:`get_gpu_details` for the 1s
+        monitoring hot path. Returns only ``gpu_index`` and
+        ``gpu_utilization`` per device, skipping heavyweight queries
+        (memory, temperature, compute mode, process lists).
+
+        >>> get_gpu_utilization_list()
+        [
+            {"gpu_index": 0, "gpu_utilization": 0},
+        ]
+        """
+        try:
+            return [d.get_gpu_utilization_lightweight() for d in self.devices]
+        except Exception:
+            logger.warning("Failed to retrieve gpu utilization", exc_info=True)
+            return []
+
     def get_delta(self, last_duration: Time) -> List:
         """Get difference since last time this function was called
         >>> get_delta()

codecarbon/core/gpu_device.py

@@ -101,6 +101,20 @@ def get_gpu_details(self) -> Dict[str, Any]:
         }
         return device_details
 
+    def get_gpu_utilization_lightweight(self) -> Dict[str, Any]:
+        """
+        Lightweight alternative to :meth:`get_gpu_details` for the hot path
+        (``_monitor_power`` which runs every 1s).
+
+        Only queries the GPU utilization — avoids heavyweight calls like
+        memory info, temperature, compute mode, and process lists which are
+        not consumed by the tracker's monitoring loop.
+        """
+        return {
+            "gpu_index": self.gpu_index,
+            "gpu_utilization": self._get_gpu_utilization(),
+        }
+
     def _to_utf8(self, str_or_bytes) -> Any:
         if hasattr(str_or_bytes, "decode"):
             return str_or_bytes.decode("utf-8", errors="replace")

codecarbon/emissions_tracker.py

@@ -1147,15 +1147,16 @@ def _monitor_power(self) -> None:
         self._ram_utilization_history.append(psutil.virtual_memory().percent)
         self._ram_used_history.append(psutil.virtual_memory().used / (1024**3))
 
-        # Collect GPU utilization metrics
+        # Collect GPU utilization metrics (lightweight path — skips
+        # heavyweight calls like process lists, memory, temperature).
         for hardware in self._hardware:
             if isinstance(hardware, GPU):
                 gpu_ids_to_monitor = hardware.gpu_ids
-                gpu_details = hardware.devices.get_gpu_details()
-                for gpu_index, gpu_detail in enumerate(gpu_details):
-                    resolved_gpu_index = gpu_detail.get("gpu_index", gpu_index)
+                for gpu_detail in hardware.devices.get_gpu_utilization_list():
+                    resolved_gpu_index = gpu_detail.get("gpu_index")
                     if (
-                        resolved_gpu_index in gpu_ids_to_monitor
+                        resolved_gpu_index is not None
+                        and resolved_gpu_index in gpu_ids_to_monitor
                         and "gpu_utilization" in gpu_detail
                     ):
                         self._gpu_utilization_history.append(