Refactor ROCm Support (#21132)

* Remove gfx 900 support and only keep ROCm build with all variants by default

* Include C++ for JIT header compilation

.github/workflows/ci.yml

@@ -136,7 +136,6 @@ jobs:
             *.cache-to=type=registry,ref=${{ steps.setup.outputs.cache-name }}-tensorrt,mode=max
       - name: AMD/ROCm general build
         env:
-          AMDGPU: gfx
           HSA_OVERRIDE: 0
         uses: docker/bake-action@v6
         with:

docker/rocm/Dockerfile

@@ -3,7 +3,6 @@
 # https://askubuntu.com/questions/972516/debian-frontend-environment-variable
 ARG DEBIAN_FRONTEND=noninteractive
 ARG ROCM=1
-ARG AMDGPU=gfx900
 ARG HSA_OVERRIDE_GFX_VERSION
 ARG HSA_OVERRIDE
 
@@ -11,7 +10,6 @@ ARG HSA_OVERRIDE
 FROM wget AS rocm
 
 ARG ROCM
-ARG AMDGPU
 
 RUN apt update -qq && \
     apt install -y wget gpg && \
@@ -36,7 +34,10 @@ FROM deps AS deps-prelim
 COPY docker/rocm/debian-backports.sources /etc/apt/sources.list.d/debian-backports.sources
 RUN apt-get update && \
     apt-get install -y libnuma1 && \
-    apt-get install -qq -y -t bookworm-backports mesa-va-drivers mesa-vulkan-drivers
+    apt-get install -qq -y -t bookworm-backports mesa-va-drivers mesa-vulkan-drivers && \
+    # Install C++ standard library headers for HIPRTC kernel compilation fallback
+    apt-get install -qq -y libstdc++-12-dev && \
+    rm -rf /var/lib/apt/lists/*
 
 WORKDIR /opt/frigate
 COPY --from=rootfs / /
@@ -54,12 +55,14 @@ RUN pip3 uninstall -y onnxruntime \
 FROM scratch AS rocm-dist
 
 ARG ROCM
-ARG AMDGPU
 
 COPY --from=rocm /opt/rocm-$ROCM/bin/rocminfo /opt/rocm-$ROCM/bin/migraphx-driver /opt/rocm-$ROCM/bin/
-COPY --from=rocm /opt/rocm-$ROCM/share/miopen/db/*$AMDGPU* /opt/rocm-$ROCM/share/miopen/db/
+# Copy MIOpen database files for gfx10xx and gfx11xx only (RDNA2/RDNA3)
-COPY --from=rocm /opt/rocm-$ROCM/share/miopen/db/*gfx908* /opt/rocm-$ROCM/share/miopen/db/
+COPY --from=rocm /opt/rocm-$ROCM/share/miopen/db/*gfx10* /opt/rocm-$ROCM/share/miopen/db/
-COPY --from=rocm /opt/rocm-$ROCM/lib/rocblas/library/*$AMDGPU* /opt/rocm-$ROCM/lib/rocblas/library/
+COPY --from=rocm /opt/rocm-$ROCM/share/miopen/db/*gfx11* /opt/rocm-$ROCM/share/miopen/db/
+# Copy rocBLAS library files for gfx10xx and gfx11xx only
+COPY --from=rocm /opt/rocm-$ROCM/lib/rocblas/library/*gfx10* /opt/rocm-$ROCM/lib/rocblas/library/
+COPY --from=rocm /opt/rocm-$ROCM/lib/rocblas/library/*gfx11* /opt/rocm-$ROCM/lib/rocblas/library/
 COPY --from=rocm /opt/rocm-dist/ /
 
 #######################################################################

docker/rocm/rocm.hcl

@@ -1,6 +1,3 @@
-variable "AMDGPU" {
-  default = "gfx900"
-}
 variable "ROCM" {
   default = "7.1.1"
 }
@@ -38,7 +35,6 @@ target rocm {
   }
   platforms = ["linux/amd64"]
   args = {
-    AMDGPU = AMDGPU,
     ROCM = ROCM,
     HSA_OVERRIDE_GFX_VERSION = HSA_OVERRIDE_GFX_VERSION,
     HSA_OVERRIDE = HSA_OVERRIDE

docker/rocm/rocm.mk

@@ -1,53 +1,15 @@
 BOARDS += rocm
 
-# AMD/ROCm is chunky so we build couple of smaller images for specific chipsets
-ROCM_CHIPSETS:=gfx900:9.0.0 gfx1030:10.3.0 gfx1100:11.0.0
-
 local-rocm: version
-	$(foreach chipset,$(ROCM_CHIPSETS), \
-		AMDGPU=$(word 1,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE_GFX_VERSION=$(word 2,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE=1 \
-		docker buildx bake --file=docker/rocm/rocm.hcl rocm \
-			--set rocm.tags=frigate:latest-rocm-$(word 1,$(subst :, ,$(chipset))) \
-			--load \
-	&&) true
-	
-	unset HSA_OVERRIDE_GFX_VERSION && \
-	HSA_OVERRIDE=0 \
-	AMDGPU=gfx \
 	docker buildx bake --file=docker/rocm/rocm.hcl rocm \
 		--set rocm.tags=frigate:latest-rocm \
 		--load
 
 build-rocm: version
-	$(foreach chipset,$(ROCM_CHIPSETS), \
-		AMDGPU=$(word 1,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE_GFX_VERSION=$(word 2,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE=1 \
-		docker buildx bake --file=docker/rocm/rocm.hcl rocm \
-			--set rocm.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-rocm-$(chipset) \
-	&&) true
-
-	unset HSA_OVERRIDE_GFX_VERSION && \
-	HSA_OVERRIDE=0 \
-	AMDGPU=gfx \
 	docker buildx bake --file=docker/rocm/rocm.hcl rocm \
 		--set rocm.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-rocm
 
 push-rocm: build-rocm
-	$(foreach chipset,$(ROCM_CHIPSETS), \
-		AMDGPU=$(word 1,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE_GFX_VERSION=$(word 2,$(subst :, ,$(chipset))) \
-		HSA_OVERRIDE=1 \
-		docker buildx bake --file=docker/rocm/rocm.hcl rocm \
-			--set rocm.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-rocm-$(chipset) \
-			--push \
-	&&) true
-
-	unset HSA_OVERRIDE_GFX_VERSION && \
-	HSA_OVERRIDE=0 \
-	AMDGPU=gfx \
 	docker buildx bake --file=docker/rocm/rocm.hcl rocm \
 		--set rocm.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-rocm \
 		--push