detectors/rocm: automatically override HSA_OVERRIDE_GFX_VERSION for couple of known chipsets

docker/rocm/rootfs/etc/s6-overlay/s6-rc.d/compile-rocm-models/run

@@ -2,6 +2,13 @@
 # shellcheck shell=bash
 # Compile YoloV8 ONNX files into ROCm MIGraphX files
 
+OVERRIDE=$(cd /opt/frigate && python3 -c 'import frigate.detectors.plugins.rocm as rocm; print(rocm.auto_override_gfx_version())')
+
+if ! test -z "$OVERRIDE"; then
+  echo "Using HSA_OVERRIDE_GFX_VERSION=${OVERRIDE}"
+  export HSA_OVERRIDE_GFX_VERSION=$OVERRIDE
+fi
+
 for onnx in /config/model_cache/yolov8/*.onnx
 do
   mxr="${onnx%.onnx}.mxr"

frigate/detectors/plugins/rocm.py

@@ -7,7 +7,7 @@ import ctypes
 from pydantic import Field
 from typing_extensions import Literal
 import glob
-import cv2
+import subprocess
 
 from frigate.detectors.detection_api import DetectionApi
 from frigate.detectors.detector_config import BaseDetectorConfig
@@ -18,14 +18,41 @@ logger = logging.getLogger(__name__)
 
 DETECTOR_KEY = "rocm"
 
+def detect_gfx_version():
+    return subprocess.getoutput("unset HSA_OVERRIDE_GFX_VERSION && /opt/rocm/bin/rocminfo | grep gfx |head -1|awk '{print $2}'")
+
+def auto_override_gfx_version():
+    # If environment varialbe already in place, do not override
+    gfx_version = detect_gfx_version()
+    old_override = os.getenv('HSA_OVERRIDE_GFX_VERSION')
+    if old_override not in (None, ''):
+        logger.warning(f"AMD/ROCm: detected {gfx_version} but HSA_OVERRIDE_GFX_VERSION already present ({old_override}), not overriding!")
+        return old_override
+    mapping = {
+        'gfx90c': '9.0.0',
+        'gfx1031': '10.3.0',
+        'gfx1103': '11.0.0',
+    }
+    override = mapping.get(gfx_version)
+    if override is not None:
+        logger.warning(f"AMD/ROCm: detected {gfx_version}, overriding HSA_OVERRIDE_GFX_VERSION={override}")
+        os.putenv('HSA_OVERRIDE_GFX_VERSION', override)
+        return override
+    return ''
+
+
 class ROCmDetectorConfig(BaseDetectorConfig):
     type: Literal[DETECTOR_KEY]
     conserve_cpu: bool = Field(default=True, title="Conserve CPU at the expense of latency (and reduced max throughput)")
+    auto_override_gfx: bool = Field(default=True, title="Automatically detect and override gfx version")
 
 class ROCmDetector(DetectionApi):
     type_key = DETECTOR_KEY
 
     def __init__(self, detector_config: ROCmDetectorConfig):
+        if detector_config.auto_override_gfx:
+            auto_override_gfx_version()
+
         try:
             sys.path.append("/opt/rocm/lib")
             import migraphx