Dockerfile - Bug fix for rocm docker build and deploy (#598)

**Description**
Bug fix for rocm docker build and deploy.

.github/workflows/build-image.yml

@@ -108,7 +108,7 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       - name: Pull cache image
-        run: sudo docker pull ${{ steps.metadata.outputs.tags }}
+        run: sudo docker pull $(cut -d, -f1 <<<${{ steps.metadata.outputs.tags }})
         continue-on-error: true
       - name: Login to the GitHub Container Registry
         uses: docker/login-action@v1

dockerfile/rocm5.7.x.dockerfile

@@ -17,6 +17,7 @@ RUN apt-get update && \
     apt-get -q install -y --no-install-recommends  \
     autoconf \
     automake \
+    bc \
     build-essential \
     curl \
     dmidecode \
@@ -27,6 +28,7 @@ RUN apt-get update && \
     libaio-dev \
     libboost-program-options-dev \
     libcap2 \
+    libcurl4-openssl-dev \
     libnuma-dev \
     libpci-dev \
     libssl-dev \
@@ -38,6 +40,7 @@ RUN apt-get update && \
     openssh-client \
     openssh-server \
     pciutils \
+    python3-mpi4py \
     rsync \
     sudo \
     util-linux \
@@ -46,11 +49,11 @@ RUN apt-get update && \
     && \
     rm -rf /tmp/*
 
-ARG NUM_MAKE_JOBS=16
+ARG NUM_MAKE_JOBS=
 
 # Check if CMake is installed and its version
 RUN cmake_version=$(cmake --version 2>/dev/null | grep -oP "(?<=cmake version )(\d+\.\d+)" || echo "0.0") && \
-    required_version="3.26.4" && \
+    required_version="3.24.1" && \
     if [ "$(printf "%s\n" "$required_version" "$cmake_version" | sort -V | head -n 1)" != "$required_version" ]; then \
     echo "existing cmake version is ${cmake_version}" && \
     cd /tmp && \
@@ -100,21 +103,9 @@ RUN if ! command -v ofed_info >/dev/null 2>&1; then \
     rm -rf MLNX_OFED_LINUX-${OFED_VERSION}* ; \
     fi
 
-# Install UCX
-ENV UCX_VERSION=1.14.1
-RUN if [ -z "$(ls -A /opt/ucx)" ]; then \
-    echo "/opt/ucx is empty. Installing UCX..."; \
-    cd /tmp && \
-    git clone https://github.com/openucx/ucx.git -b v${UCX_VERSION} && \
-    cd ucx && \
-    ./autogen.sh && \
-    mkdir build && \
-    cd build && \
-    ../configure -prefix=$UCX_DIR --with-rocm=/opt/rocm --without-knem && \
-    make -j $(nproc) && make -j $(nproc) install && rm -rf /tmp/ucx-${UCX_VERSION} ; \
-    else \
-    echo "/opt/ucx is not empty. Skipping UCX installation."; \
-    fi
+# Add target file to help determine which device(s) to build for
+ENV ROCM_PATH=/opt/rocm
+RUN bash -c 'echo -e "gfx90a:xnack-\ngfx90a:xnac+\ngfx940\ngfx941\ngfx942\ngfx1030\ngfx1100\ngfx1101\ngfx1102\n" >> ${ROCM_PATH}/bin/target.lst'
 
 # Install OpenMPI
 ENV OPENMPI_VERSION=4.1.x
@@ -127,7 +118,7 @@ RUN [ -d /usr/local/bin/mpirun ] || { \
     ./autogen.pl && \
     mkdir build && \
     cd build && \
-    ../configure --prefix=/usr/local  --enable-orterun-prefix-by-default  --enable-mpirun-prefix-by-default  --enable-prte-prefix-by-default --enable-mca-no-build=btl-uct --with-ucx=/opt/ucx --with-rocm=/opt/rocm && \
+    ../configure --prefix=/usr/local  --enable-orterun-prefix-by-default  --enable-mpirun-prefix-by-default  --enable-prte-prefix-by-default --with-rocm=/opt/rocm && \
     make -j $(nproc) && \
     make -j $(nproc) install && \
     ldconfig && \
@@ -148,12 +139,14 @@ RUN cd /opt/ &&  \
     cd rccl && \
     mkdir build && \
     cd build && \
-    CXX=/opt/rocm/bin/hipcc cmake -DCMAKE_PREFIX_PATH=/opt/rocm/ .. && \
+    CXX=/opt/rocm/bin/hipcc cmake -DHIP_COMPILER=clang -DCMAKE_BUILD_TYPE=Release -DCMAKE_VERBOSE_MAKEFILE=1 \
+        -DCMAKE_PREFIX_PATH="${ROCM_PATH}/hsa;${ROCM_PATH}/hip;${ROCM_PATH}/share/rocm/cmake/;${ROCM_PATH}" \
+        .. && \
     make -j${NUM_MAKE_JOBS}
 
 ENV PATH="/opt/superbench/bin:/usr/local/bin/:/opt/rocm/hip/bin/:/opt/rocm/bin/:${PATH}" \
     LD_PRELOAD="/opt/rccl/build/librccl.so:$LD_PRELOAD" \
-    LD_LIBRARY_PATH="/opt/ucx/lib:/usr/local/lib/:/opt/rocm/lib:${LD_LIBRARY_PATH}" \
+    LD_LIBRARY_PATH="/usr/local/lib/:/opt/rocm/lib:${LD_LIBRARY_PATH}" \
     SB_HOME=/opt/superbench \
     SB_MICRO_PATH=/opt/superbench \
     ANSIBLE_DEPRECATION_WARNINGS=FALSE \
@@ -163,13 +156,17 @@ RUN echo PATH="$PATH" > /etc/environment && \
     echo LD_LIBRARY_PATH="$LD_LIBRARY_PATH" >> /etc/environment && \
     echo SB_MICRO_PATH="$SB_MICRO_PATH" >> /etc/environment
 
+RUN apt install rocm-cmake -y && \
+    python3 -m pip install --upgrade pip wheel setuptools==65.7
+
 WORKDIR ${SB_HOME}
 
+ADD third_party third_party
+RUN make RCCL_HOME=/opt/rccl/build/ MPI_HOME=/usr/local ROCBLAS_BRANCH=release/rocm-rel-5.7.1.1 HIPBLASLT_BRANCH=release-staging/rocm-rel-5.7 ROCM_VER=rocm-5.5.0 -C third_party rocm -o cpu_hpl -o cpu_stream -o megatron_lm
+
 ADD . .
-RUN apt install rocm-cmake -y && \
-    python3 -m pip install --upgrade pip wheel setuptools==65.7 && \
-    python3 -m pip install .[amdworker]  && \
+#ENV USE_HIPBLASLT_DATATYPE=1
+ENV CXX=/opt/rocm/bin/hipcc
+RUN python3 -m pip install .[amdworker]  && \
+    make cppbuild  && \
     make postinstall
-RUN make cppbuild
-ADD third_party third_party
-RUN make RCCL_HOME=/opt/rccl/build/ ROCBLAS_BRANCH=release/rocm-rel-5.7.1.1 HIPBLASLT_BRANCH=release-staging/rocm-rel-5.7 ROCM_VER=rocm-5.5.0 -C third_party rocm -o cpu_hpl -o cpu_stream -o megatron_lm

superbench/benchmarks/micro_benchmarks/rocm_common.cmake

@@ -45,8 +45,7 @@ message(STATUS "CMAKE HIP ARCHITECTURES: ${CMAKE_HIP_ARCHITECTURES}")
 
 if(EXISTS ${HIP_PATH})
     # Search for hip in common locations
-    list(APPEND CMAKE_PREFIX_PATH ${HIP_PATH} ${ROCM_PATH})
-    set(CMAKE_PREFIX_PATH /opt/rocm ROCM_PATH)
+    list(APPEND CMAKE_PREFIX_PATH ${HIP_PATH} ${ROCM_PATH} ${ROCM_PATH}/hsa ${ROCM_PATH}/hip ${ROCM_PATH}/share/rocm/cmake/)
     set(CMAKE_CXX_COMPILER "${HIP_PATH}/bin/hipcc")
     set(CMAKE_MODULE_PATH "${HIP_PATH}/cmake" ${CMAKE_MODULE_PATH})
     set(CMAKE_MODULE_PATH "${HIP_PATH}/lib/cmake/hip" ${CMAKE_MODULE_PATH})

superbench/runner/playbooks/deploy.yaml

@@ -100,7 +100,7 @@
         docker run -itd --name={{ container }} \
           --privileged --net=host --ipc=host \
           {{ '--gpus=all' if nvidia_gpu_exist else '' }} \
-          {{ '--security-opt seccomp=unconfined --group-add video' if amd_gpu_exist else '' }} \
+          {{ '--security-opt seccomp=unconfined --group-add video --device=/dev/kfd --device=/dev/dri --cap-add=SYS_PTRACE --shm-size=16G' if amd_gpu_exist else '' }} \
           -w /root -v {{ workspace }}:/root -v /mnt:/mnt \
           -v /var/run/docker.sock:/var/run/docker.sock \
           --entrypoint /bin/bash {{ docker_image }} && \

third_party/Makefile

@@ -12,13 +12,13 @@ CUDA_VER ?= $(shell nvcc --version | grep 'release' | awk '{print $$6}' | cut -c
 ROCBLAS_BRANCH ?= rocm-$(shell dpkg -l | grep 'rocm-dev ' | awk '{print $$3}' | cut -d '.' -f1-3)
 HIPBLASLT_BRANCH ?= rocm-$(shell dpkg -l | grep 'rocm-dev ' | awk '{print $$3}' | cut -d '.' -f1-3)
 
-.PHONY: all cuda_with_msccl cuda rocm common cuda_cutlass cuda_bandwidthTest cuda_nccl_tests cuda_perftest cuda_msccl rocm_perftest fio rocm_rccl_tests rocm_rocblas rocm_bandwidthTest gpcnet cuda_gpuburn cpu_stream cpu_hpl directx_amf_encoding_latency directx_amd rocm_hipblaslt megatron_lm megatron_deepspeed
+.PHONY: all cuda_with_msccl cuda rocm common cuda_cutlass cuda_bandwidthTest cuda_nccl_tests cuda_perftest cuda_msccl rocm_perftest fio rocm_rccl_tests rocm_rocblas rocm_bandwidthTest gpcnet cuda_gpuburn cpu_stream cpu_hpl directx_amf_encoding_latency directx_amd rocm_hipblaslt megatron_lm megatron_deepspeed apex_rocm
 
 # Build all targets.
 all: cuda rocm
 cuda_with_msccl: cuda cuda_msccl
 cuda: common cuda_cutlass cuda_bandwidthTest cuda_nccl_tests cuda_perftest gpcnet cuda_gpuburn megatron_lm megatron_deepspeed
-rocm: common rocm_perftest rocm_rccl_tests rocm_rocblas rocm_bandwidthTest rocm_hipblaslt megatron_deepspeed
+rocm: common rocm_perftest rocm_rccl_tests rocm_rocblas rocm_bandwidthTest rocm_hipblaslt megatron_deepspeed apex_rocm
 cpu: common cpu_perftest
 common: cpu_hpl cpu_stream fio
 directx_amd: directx_amf_encoding_latency
@@ -86,11 +86,11 @@ ifneq (,$(wildcard fio/Makefile))
 	cd ./fio && ./configure --prefix=$(SB_MICRO_PATH) --disable-native && make -j && make install
 endif
 
-# Build rccl-tests from commit 2a18737 of default branch.
+# Build rccl-tests from commit 46375b1 of default branch.
 rocm_rccl_tests: sb_micro_path
 ifneq (, $(wildcard rccl-tests/Makefile))
-	cd ./rccl-tests && make MPI=1 MPI_HOME=$(MPI_HOME) HIP_HOME=$(HIP_HOME) RCCL_HOME=$(RCCL_HOME) -j
-	cp -v ./rccl-tests/build/* $(SB_MICRO_PATH)/bin/
+	cd ./rccl-tests && make MPI=1 MPI_HOME=$(MPI_HOME) -j
+	cp -v -r ./rccl-tests/build/* $(SB_MICRO_PATH)/bin/
 endif
 
 # Build rocblas-bench.
@@ -192,6 +192,26 @@ megatron_deepspeed:
 	python -m pip install -r requirements.txt && \
 	python -m pip install DeepSpeed
 
+# Instal apex of ROCm due to dependency of Megatron
+apex_rocm:
+	$(eval TORCH_VERSION ?= $(shell python -c "import torch; print(torch.__version__)"))
+	$(eval TORCH_MAJOR_VERSION ?= $(word 1,$(subst ., ,$(TORCH_VERSION))))
+	$(eval TORCH_MINOR_VERSION ?= $(word 2,$(subst ., ,$(TORCH_VERSION))))
+	if [ ! -d "apex" ]; then \
+		git clone https://github.com/ROCmSoftwarePlatform/apex.git ; \
+	fi
+	cd apex && \
+	if [ "$$(expr $(TORCH_MAJOR_VERSION) \> 2)" -eq 1 ] && [ "$$(expr $(TORCH_MINOR_VERSION) \> 1)" -eq 1 ]; then \
+		git checkout master ; \
+	elif [ "$$(expr $(TORCH_MAJOR_VERSION) == 2)" -eq 1 ] && [ "$$(expr $(TORCH_MINOR_VERSION) == 1)" -eq 1 ]; then \
+		git checkout release/1.1.0 ; \
+	elif [ "$$(expr $(TORCH_MAJOR_VERSION) == 2)" -eq 1 ] && [ "$$(expr $(TORCH_MINOR_VERSION) == 0)" -eq 1 ]; then \
+		git checkout release/1.0.0 ; \
+	elif [ "$$(expr $(TORCH_MAJOR_VERSION) == 1)" -eq 1 ]; then \
+	    git checkout release/1.0.0 ; \
+	fi
+	pip install -v --disable-pip-version-check --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./apex
+
 # Build MSCCL for CUDA
 cuda_msccl: sb_micro_path
 ifneq (,$(wildcard msccl/executor/msccl-executor-nccl/Makefile))

rccl-tests @ 46375b1c

-Subproject commit 2a18737dc681e03ce82c046caa71b28db65017b5
+Subproject commit 46375b1c527b2e3afe80fdd6dd136151bd939675