diff --git a/superbench/benchmarks/model_benchmarks/pytorch_base.py b/superbench/benchmarks/model_benchmarks/pytorch_base.py
index d99218460..0497dd750 100644
--- a/superbench/benchmarks/model_benchmarks/pytorch_base.py
+++ b/superbench/benchmarks/model_benchmarks/pytorch_base.py
@@ -174,6 +174,7 @@ def _postprocess(self):
 
         try:
             if self._args.distributed_impl == DistributedImpl.DDP:
+                torch.distributed.barrier()
                 torch.distributed.destroy_process_group()
         except BaseException as e:
             self._result.set_return_code(ReturnCode.DISTRIBUTED_SETTING_DESTROY_FAILURE)
diff --git a/superbench/runner/playbooks/deploy.yaml b/superbench/runner/playbooks/deploy.yaml
index 0eec00ace..3437b9366 100644
--- a/superbench/runner/playbooks/deploy.yaml
+++ b/superbench/runner/playbooks/deploy.yaml
@@ -101,7 +101,7 @@
           {{ '--security-opt seccomp=unconfined --group-add video' if amd_gpu_exist else '' }} \
           -w /root -v {{ workspace }}:/root -v /mnt:/mnt \
           -v /var/run/docker.sock:/var/run/docker.sock \
-          {{ docker_image }} bash && \
+          --entrypoint /bin/bash {{ docker_image }} && \
         docker exec {{ container }} bash -c \
           "chown -R root:root ~ && \
           sed -i 's/[# ]*Port.*/Port {{ ssh_port }}/g' /etc/ssh/sshd_config && \
diff --git a/third_party/Makefile b/third_party/Makefile
index b9e0a5523..ee243a92a 100755
--- a/third_party/Makefile
+++ b/third_party/Makefile
@@ -8,7 +8,6 @@ MPI_HOME ?= /usr/local/mpi
 HIP_HOME ?= /opt/rocm/hip
 RCCL_HOME ?= /opt/rocm/rccl
 ROCM_VERSION ?= rocm-$(shell dpkg -l | grep 'rocm-dev ' | awk '{print $$3}' | cut -d '.' -f1-3)
-ROCM_ARCH ?= $(shell rocminfo | grep " gfx" | uniq | awk '{print $$2}')
 
 .PHONY: all cuda rocm common cuda_cutlass cuda_bandwidthTest cuda_nccl_tests cuda_perftest rocm_perftest fio rocm_rccl_tests rocm_rocblas rocm_bandwidthTest
 
@@ -81,12 +80,7 @@ rocm_rocblas: sb_micro_path
 ifeq (, $(wildcard $(SB_MICRO_PATH)/bin/rocblas-bench))
 	if [ -d rocBLAS ]; then rm -rf rocBLAS; fi
 	git clone -b ${ROCM_VERSION} https://github.com/ROCmSoftwarePlatform/rocBLAS.git ./rocBLAS
-ifeq (${ROCM_VERSION}, rocm-4.0.0)
-	sed -i '/CMAKE_MATCH_1/a\      get_filename_component(HIP_CLANG_ROOT "$${HIP_CLANG_ROOT}" DIRECTORY)'  /opt/rocm/hip/lib/cmake/hip/hip-config.cmake
-	cd ./rocBLAS && HIPCC_COMPILE_FLAGS_APPEND="-D_OPENMP=201811 -O3 -Wno-format-nonliteral -DCMAKE_HAVE_LIBC_PTHREAD -parallel-jobs=2" HIPCC_LINK_FLAGS_APPEND="-lpthread -O3 -parallel-jobs=2" ./install.sh -idc -a ${ROCM_ARCH}
-else 
-	cd ./rocBLAS && ./install.sh -idc
-endif
+	cd ./rocBLAS && ./install.sh --dependencies --clients-only
 	cp -v ./rocBLAS/build/release/clients/staging/rocblas-bench $(SB_MICRO_PATH)/bin/
 endif