diff --git a/Dockerfile b/Dockerfile
index bcae24647d..59a6a60453 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,7 +12,8 @@ RUN apt-get install -y wget gnupg
 RUN wget -qO - http://repo.radeon.com/rocm/rocm.gpg.key | apt-key add -
 RUN sh -c "echo deb [arch=amd64] $DEB_ROCM_REPO ubuntu main > /etc/apt/sources.list.d/rocm.list"
 RUN wget --no-check-certificate -qO - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | apt-key add -
-RUN sh -c "echo deb https://apt.kitware.com/ubuntu/ bionic main | tee -a /etc/apt/sources.list"
+#RUN sh -c "echo deb https://apt.kitware.com/ubuntu/ bionic main | tee -a /etc/apt/sources.list"
+RUN sh -c "echo deb http://mirrors.kernel.org/ubuntu focal main universe | tee -a /etc/apt/sources.list"
 
 # Install dependencies
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --allow-unauthenticated \
@@ -68,7 +69,6 @@ ENV UBSAN_OPTIONS=print_stacktrace=1
 
 ENV LC_ALL=C.UTF-8
 ENV LANG=C.UTF-8
-ADD dev-requirements.txt dev-requirements.txt
 RUN groupadd -f render
 
 # Install the new rocm-cmake version
diff --git a/Jenkinsfile b/Jenkinsfile
index 8440c2f1dd..62f53e04c2 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -42,7 +42,6 @@ def build_compiler(){
 def getDockerImage(Map conf=[:]){
     env.DOCKER_BUILDKIT=1
     def prefixpath = conf.get("prefixpath", "/opt/rocm") // prefix:/opt/rocm
-    def gpu_arch = conf.get("gpu_arch", "gfx908") // prebuilt dockers should have all the architectures enabled so one image can be used for all stages
     def no_cache = conf.get("no_cache", false)
     def dockerArgs = "--build-arg BUILDKIT_INLINE_CACHE=1 --build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' "
     if(env.CCACHE_HOST)
@@ -154,6 +153,10 @@ def cmake_build(Map conf=[:]){
     }else{
         setup_args = " -DCMAKE_BUILD_TYPE=release" + setup_args
     }
+    if(env.CCACHE_HOST)
+    {
+        setup_args = " -DCMAKE_CXX_COMPILER_LAUNCHER='ccache' -DCMAKE_C_COMPILER_LAUNCHER='ccache' " + setup_args
+    }
 
     def pre_setup_cmd = """
             echo \$HSA_ENABLE_SDMA
@@ -191,15 +194,13 @@ def buildHipClangJob(Map conf=[:]){
         env.HSA_ENABLE_SDMA=0
         checkout scm
 
-        def image = "composable_kernels_${params.COMPILER_VERSION}"
+        def image = getDockerImageName() 
         def prefixpath = conf.get("prefixpath", "/opt/rocm")
-        def gpu_arch = conf.get("gpu_arch", "gfx908")
 
         // Jenkins is complaining about the render group 
-        // def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --group-add render --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
-        def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
+        def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --group-add render --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
         if (conf.get("enforce_xnack_on", false)) {
-            dockerOpts = dockerOpts + " --env HSA_XNACK=1 --env GPU_ARCH='${gpu_arch}' "
+            dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
         }
         def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' "
         if (params.COMPILER_VERSION != "release"){
@@ -281,16 +282,13 @@ def runCKProfiler(Map conf=[:]){
         env.HSA_ENABLE_SDMA=0
         checkout scm
 
-
-        def image = "composable_kernels_${params.COMPILER_VERSION}"
+        def image = getDockerImageName()
         def prefixpath = conf.get("prefixpath", "/opt/rocm")
-        def gpu_arch = conf.get("gpu_arch", "gfx908")
 
         // Jenkins is complaining about the render group 
-        // def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --group-add render --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
-        def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
+        def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --group-add render --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
         if (conf.get("enforce_xnack_on", false)) {
-            dockerOpts = dockerOpts + " --env HSA_XNACK=1 --env GPU_ARCH='${gpu_arch}' "
+            dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
         }
         def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' "
         if (params.COMPILER_VERSION != "release"){
@@ -302,7 +300,6 @@ def runCKProfiler(Map conf=[:]){
 
         gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
             try {
-                //retimage = docker.build("${image}", dockerArgs + '.')
                 (retimage, image) = getDockerImage(conf)
                 withDockerContainer(image: image, args: dockerOpts) {
                     timeout(time: 5, unit: 'MINUTES'){
@@ -338,48 +335,57 @@ def runCKProfiler(Map conf=[:]){
             withDockerContainer(image: image, args: dockerOpts + ' -v=/var/jenkins/:/var/jenkins') {
                 timeout(time: 24, unit: 'HOURS')
                 {
-                    cmake_build(conf)
+                    //cmake_build(conf)
+                    //instead of building, just unstash the ckProfiler and install it
+                    sh """
+                        rm -rf build
+                        mkdir build
+                    """
+                    dir("build"){
+                        unstash 'ckProfiler.tar.gz'
+                        sh 'tar -xvf ckProfiler.tar.gz'
+                    }
+
 					dir("script"){
                         if (params.RUN_FULL_QA){
-                            def qa_log = "qa_${gpu_arch}.log"
-                            sh "./run_full_performance_tests.sh 1 QA_${params.COMPILER_VERSION} ${gpu_arch} ${env.BRANCH_NAME} ${NODE_NAME}"
-                            archiveArtifacts "perf_gemm_${gpu_arch}.log"
-                            archiveArtifacts "perf_resnet50_N256_${gpu_arch}.log"
-                            archiveArtifacts "perf_resnet50_N4_${gpu_arch}.log"
-                            archiveArtifacts "perf_batched_gemm_${gpu_arch}.log"
-                            archiveArtifacts "perf_grouped_gemm_${gpu_arch}.log"
-                            archiveArtifacts "perf_conv_fwd_${gpu_arch}.log"
-                            archiveArtifacts "perf_conv_bwd_data_${gpu_arch}.log"
-                            archiveArtifacts "perf_gemm_bilinear_${gpu_arch}.log"
-                            archiveArtifacts "perf_reduction_${gpu_arch}.log"
-                            archiveArtifacts "perf_splitK_gemm_${gpu_arch}.log"
-                            archiveArtifacts "perf_onnx_gemm_${gpu_arch}.log"
+                            sh "./run_full_performance_tests.sh 1 QA_${params.COMPILER_VERSION} ${env.BRANCH_NAME} ${NODE_NAME}"
+                            archiveArtifacts "perf_gemm.log"
+                            archiveArtifacts "perf_resnet50_N256.log"
+                            archiveArtifacts "perf_resnet50_N4.log"
+                            archiveArtifacts "perf_batched_gemm.log"
+                            archiveArtifacts "perf_grouped_gemm.log"
+                            archiveArtifacts "perf_conv_fwd.log"
+                            archiveArtifacts "perf_conv_bwd_data.log"
+                            archiveArtifacts "perf_gemm_bilinear.log"
+                            archiveArtifacts "perf_reduction.log"
+                            archiveArtifacts "perf_splitK_gemm_verify.log"
+                            archiveArtifacts "perf_splitK_gemm.log"
+                            archiveArtifacts "perf_onnx_gemm.log"
                            // stash perf files to master
-                            stash name: "perf_gemm_${gpu_arch}.log"
-                            stash name: "perf_resnet50_N256_${gpu_arch}.log"
-                            stash name: "perf_resnet50_N4_${gpu_arch}.log"
-                            stash name: "perf_batched_gemm_${gpu_arch}.log"
-                            stash name: "perf_grouped_gemm_${gpu_arch}.log"
-                            stash name: "perf_conv_fwd_${gpu_arch}.log"
-                            stash name: "perf_conv_bwd_data_${gpu_arch}.log"
-                            stash name: "perf_gemm_bilinear_${gpu_arch}.log"
-                            stash name: "perf_reduction_${gpu_arch}.log"
-                            stash name: "perf_splitK_gemm_${gpu_arch}.log"
-                            stash name: "perf_onnx_gemm_${gpu_arch}.log"
+                            stash name: "perf_gemm.log"
+                            stash name: "perf_resnet50_N256.log"
+                            stash name: "perf_resnet50_N4.log"
+                            stash name: "perf_batched_gemm.log"
+                            stash name: "perf_grouped_gemm.log"
+                            stash name: "perf_conv_fwd.log"
+                            stash name: "perf_conv_bwd_data.log"
+                            stash name: "perf_gemm_bilinear.log"
+                            stash name: "perf_reduction.log"
+                            stash name: "perf_splitK_gemm.log"
+                            stash name: "perf_onnx_gemm.log"
                             //we will process results on the master node
                         }
                         else{
-                            sh "./run_performance_tests.sh 0 CI_${params.COMPILER_VERSION} ${gpu_arch} ${env.BRANCH_NAME} ${NODE_NAME}"
-                            archiveArtifacts "perf_gemm_${gpu_arch}.log"
-                            archiveArtifacts "perf_resnet50_N256_${gpu_arch}.log"
-                            archiveArtifacts "perf_resnet50_N4_${gpu_arch}.log"
+                            sh "./run_performance_tests.sh 0 CI_${params.COMPILER_VERSION} ${env.BRANCH_NAME} ${NODE_NAME}"
+                            archiveArtifacts "perf_gemm.log"
+                            archiveArtifacts "perf_resnet50_N256.log"
+                            archiveArtifacts "perf_resnet50_N4.log"
                             // stash perf files to master
-                            stash name: "perf_gemm_${gpu_arch}.log"
-                            stash name: "perf_resnet50_N256_${gpu_arch}.log"
-                            stash name: "perf_resnet50_N4_${gpu_arch}.log"
+                            stash name: "perf_gemm.log"
+                            stash name: "perf_resnet50_N256.log"
+                            stash name: "perf_resnet50_N4.log"
                             //we will process the results on the master node
                         }
-
 					}
                 }
             }
@@ -403,17 +409,104 @@ def runPerfTest(Map conf=[:]){
     }
 }
 
+def Build_CK(Map conf=[:]){
+        show_node_info()
+
+        env.HSA_ENABLE_SDMA=0
+        checkout scm
+
+        def image = getDockerImageName() 
+        def prefixpath = conf.get("prefixpath", "/opt/rocm")
+
+        // Jenkins is complaining about the render group 
+        def dockerOpts="--device=/dev/kfd --device=/dev/dri --group-add video --group-add render --cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
+        if (conf.get("enforce_xnack_on", false)) {
+            dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
+        }
+        def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' "
+        if (params.COMPILER_VERSION != "release"){
+            dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
+        }
+
+        def variant = env.STAGE_NAME
+        def retimage
+
+        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
+            try {
+                (retimage, image) = getDockerImage(conf)
+                withDockerContainer(image: image, args: dockerOpts) {
+                    timeout(time: 5, unit: 'MINUTES'){
+                        sh 'PATH="/opt/rocm/opencl/bin:/opt/rocm/opencl/bin/x86_64:$PATH" clinfo | tee clinfo.log'
+                        if ( runShell('grep -n "Number of devices:.*. 0" clinfo.log') ){
+                            throw new Exception ("GPU not found")
+                        }
+                        else{
+                            echo "GPU is OK"
+                        }
+                    }
+                }
+            }
+            catch (org.jenkinsci.plugins.workflow.steps.FlowInterruptedException e){
+                echo "The job was cancelled or aborted"
+                throw e
+            }
+            catch(Exception ex) {
+                retimage = docker.build("${image}", dockerArgs + " --no-cache .")
+                withDockerContainer(image: image, args: dockerOpts) {
+                    timeout(time: 5, unit: 'MINUTES'){
+                        sh 'PATH="/opt/rocm/opencl/bin:/opt/rocm/opencl/bin/x86_64:$PATH" clinfo |tee clinfo.log'
+                        if ( runShell('grep -n "Number of devices:.*. 0" clinfo.log') ){
+                            throw new Exception ("GPU not found")
+                        }
+                        else{
+                            echo "GPU is OK"
+                        }
+                    }
+                }
+            }
+            withDockerContainer(image: image, args: dockerOpts + ' -v=/var/jenkins/:/var/jenkins') {
+                timeout(time: 24, unit: 'HOURS')
+                {
+                    cmake_build(conf)
+                    dir("build"){
+                        //run tests and examples
+                        sh 'make -j check'
+                        //we only need the ckProfiler to run the performance tests, so we pack and stash it
+                        sh 'tar -zcvf ckProfiler.tar.gz bin/ckProfiler'
+                        stash "ckProfiler.tar.gz"
+                    }
+                }
+            }
+        }
+        return retimage
+}
+
+def Build_CK_and_Reboot(Map conf=[:]){
+    try{
+        Build_CK(conf)
+    }
+    catch(e){
+        echo "throwing error exception while building CK"
+        echo 'Exception occurred: ' + e.toString()
+        throw e
+    }
+    finally{
+        if (!conf.get("no_reboot", false)) {
+            reboot()
+        }
+    }
+}
+
 def process_results(Map conf=[:]){
     env.HSA_ENABLE_SDMA=0
     checkout scm
-    def image = "composable_kernels_${params.COMPILER_VERSION}"
+    def image = getDockerImageName() 
     def prefixpath = "/opt/rocm"
-    def gpu_arch = conf.get("gpu_arch", "gfx908")
 
     // Jenkins is complaining about the render group 
     def dockerOpts="--cap-add=SYS_PTRACE --security-opt seccomp=unconfined"
     if (conf.get("enforce_xnack_on", false)) {
-        dockerOpts = dockerOpts + " --env HSA_XNACK=1 --env GPU_ARCH='${gpu_arch}' "
+        dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
     }
     def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='release' "
 
@@ -422,7 +515,6 @@ def process_results(Map conf=[:]){
 
     gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
         try {
-            //retimage = docker.build("${image}", dockerArgs + '.')
             (retimage, image) = getDockerImage(conf)
         }
         catch (org.jenkinsci.plugins.workflow.steps.FlowInterruptedException e){
@@ -437,25 +529,25 @@ def process_results(Map conf=[:]){
                 dir("script"){
                     if (params.RUN_FULL_QA){
                         // unstash perf files to master
-                        unstash "perf_gemm_${gpu_arch}.log"
-                        unstash "perf_resnet50_N256_${gpu_arch}.log"
-                        unstash "perf_resnet50_N4_${gpu_arch}.log"
-                        unstash "perf_batched_gemm_${gpu_arch}.log"
-                        unstash "perf_grouped_gemm_${gpu_arch}.log"
-                        unstash "perf_conv_fwd_${gpu_arch}.log"
-                        unstash "perf_conv_bwd_data_${gpu_arch}.log"
-                        unstash "perf_gemm_bilinear_${gpu_arch}.log"
-                        unstash "perf_reduction_${gpu_arch}.log"
-                        unstash "perf_splitK_gemm_${gpu_arch}.log"
-                        unstash "perf_onnx_gemm_${gpu_arch}.log"
-                        sh "./process_qa_data.sh ${gpu_arch}"
+                        unstash "perf_gemm.log"
+                        unstash "perf_resnet50_N256.log"
+                        unstash "perf_resnet50_N4.log"
+                        unstash "perf_batched_gemm.log"
+                        unstash "perf_grouped_gemm.log"
+                        unstash "perf_conv_fwd.log"
+                        unstash "perf_conv_bwd_data.log"
+                        unstash "perf_gemm_bilinear.log"
+                        unstash "perf_reduction.log"
+                        unstash "perf_splitK_gemm.log"
+                        unstash "perf_onnx_gemm.log"
+                        sh "./process_qa_data.sh"
                     }
                     else{
                         // unstash perf files to master
-                        unstash "perf_gemm_${gpu_arch}.log"
-                        unstash "perf_resnet50_N256_${gpu_arch}.log"
-                        unstash "perf_resnet50_N4_${gpu_arch}.log"
-                        sh "./process_perf_data.sh ${gpu_arch}"
+                        unstash "perf_gemm.log"
+                        unstash "perf_resnet50_N256.log"
+                        unstash "perf_resnet50_N4.log"
+                        sh "./process_perf_data.sh"
                     }
                 }
             }
@@ -562,41 +654,29 @@ pipeline {
                 }
             }
         }
-		stage("Tests")
+    
+		stage("Build CK and run Tests")
         {
-            when {
-                beforeAgent true
-                expression { !params.TEST_NODE_PERFORMANCE.toBoolean() }
-            }
             parallel
             {
-                stage("Run Tests: gfx908")
+                stage("Build CK and run Tests")
                 {
-                    agent{ label rocmnode("gfx908")}
+                    agent{ label rocmnode("gfx908 || gfx90a") }
                     environment{
-                        setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -DBUILD_DEV=On """ : """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3 " -DBUILD_DEV=On """}"
+                        setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -D CMAKE_CXX_FLAGS="--offload-arch=gfx908 --offload-arch=gfx90a -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" """ : """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -D CMAKE_CXX_FLAGS="--offload-arch=gfx908 --offload-arch=gfx90a -O3 " """ }"
+                        execute_args = "${params.COMPILER_VERSION == "ck-9110" ? """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 --offload-arch=gfx90a -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ : """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 --offload-arch=gfx90a -O3" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ }"
                     }
                     steps{
-                        buildHipClangJobAndReboot(setup_args:setup_args, config_targets: "check", no_reboot:true, build_type: 'Release', gpu_arch: "gfx908")
-                    }
-                }
-                stage("Run Tests: gfx90a")
-                {
-                    when {
-                        beforeAgent true
-                        expression { params.RUN_FULL_QA.toBoolean() }
-                    }
-                    options { retry(2) }
-                    agent{ label rocmnode("gfx90a")}
-                    environment{
-                        setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx90a -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -DBUILD_DEV=On """ : """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx90a -O3 " -DBUILD_DEV=On """}"
-                    }
-                    steps{
-                        buildHipClangJobAndReboot(setup_args:setup_args, config_targets: "check", no_reboot:true, build_type: 'Release', gpu_arch: "gfx90a")
+                        Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
                     }
                 }
             }
         }
+
+ 		/*
+        //at present this stage only builds binaries. 
+        //we will now build all binaries in a separate stage.
+        //once we have some tests to run in this stage, we can enable it again.
         stage("Client App")
         {
             when {
@@ -611,7 +691,6 @@ pipeline {
                     environment{
                         setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -D CMAKE_CXX_FLAGS="--offload-arch=gfx908 -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" """ : """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -D CMAKE_CXX_FLAGS="--offload-arch=gfx908 -O3 " """ }"
                         execute_args = "${params.COMPILER_VERSION == "ck-9110" ? """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ : """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ }"
-
                     }
                     steps{
                         buildHipClangJobAndReboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -619,23 +698,24 @@ pipeline {
                 }
             }
         }
+        */
         stage("Performance Tests")
         {
             parallel
             {
-                stage("Run ckProfiler: gfx908")
+                stage("Run ckProfiler: gfx908 or gfx90a")
                 {
                     when {
                         beforeAgent true
                         expression { !params.RUN_FULL_QA.toBoolean() && !params.TEST_NODE_PERFORMANCE.toBoolean() }
                     }
                     options { retry(2) }
-                    agent{ label rocmnode("gfx908")}
+                    agent{ label rocmnode("gfx908 || gfx90a")}
                     environment{
                         setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -DBUILD_DEV=On """ : """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx908 -O3 " -DBUILD_DEV=On """}"
                    }
                     steps{
-                        runPerfTest(setup_args:setup_args, config_targets: "ckProfiler", no_reboot:true, build_type: 'Release', gpu_arch: "gfx908")
+                        runPerfTest(setup_args:setup_args, config_targets: "ckProfiler", no_reboot:true, build_type: 'Release')
                     }
                 }
                 stage("Run ckProfiler: gfx90a")
@@ -650,7 +730,7 @@ pipeline {
                         setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx90a -O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -DBUILD_DEV=On """ : """ -D CMAKE_CXX_FLAGS=" --offload-arch=gfx90a -O3 " -DBUILD_DEV=On """}"
                     }
                     steps{
-                        runPerfTest(setup_args:setup_args, config_targets: "ckProfiler", no_reboot:true, build_type: 'Release', gpu_arch: "gfx90a")
+                        runPerfTest(setup_args:setup_args, config_targets: "ckProfiler", no_reboot:true, build_type: 'Release')
                     }
                 }
             }
@@ -659,24 +739,10 @@ pipeline {
         {
             parallel
             {
-                stage("Process results for gfx908"){
-                    when {
-                        beforeAgent true
-                        expression { !params.RUN_FULL_QA.toBoolean() && !params.TEST_NODE_PERFORMANCE.toBoolean() }
-                    }
+                stage("Process results"){
                     agent { label 'mici' }
                     steps{
-                        process_results(gpu_arch: "gfx908")
-                    }
-                }
-                stage("Process results for gfx90a"){
-                    when {
-                        beforeAgent true
-                        expression { params.RUN_FULL_QA.toBoolean() || params.TEST_NODE_PERFORMANCE.toBoolean() }
-                    }
-                    agent { label 'mici' }
-                    steps{
-                        process_results(gpu_arch: "gfx90a")
+                        process_results()
                     }
                 }
             }
diff --git a/dev-requirements.txt b/dev-requirements.txt
index 5d123edb85..9134ecebe1 100644
--- a/dev-requirements.txt
+++ b/dev-requirements.txt
@@ -1,3 +1,2 @@
 ROCmSoftwarePlatform/rocm-recipes
 # 1.90+
-danmar/cppcheck@dd05839a7e63ef04afd34711cb3e1e0ef742882f
\ No newline at end of file
diff --git a/script/process_perf_data.sh b/script/process_perf_data.sh
index b68a7c1b2f..15fc5cb15f 100755
--- a/script/process_perf_data.sh
+++ b/script/process_perf_data.sh
@@ -2,15 +2,14 @@
 #
 # in order to run this script you'd need the following python packages:
 
-pip3 install --upgrade pip
-pip3 install sqlalchemy pymysql pandas sshtunnel
+#pip3 install --upgrade pip
+#pip3 install sqlalchemy pymysql pandas sshtunnel
 
 # you would also need to set up some environment variables in order to 
 # post your new test results to the database and compare them to the baseline
 # please contact Illia.Silin@amd.com for more details
 
 #process results
-gpu_arch=$1
-python3 process_perf_data.py perf_gemm_"$gpu_arch".log
-python3 process_perf_data.py perf_resnet50_N256_"$gpu_arch".log
-python3 process_perf_data.py perf_resnet50_N4_"$gpu_arch".log
+python3 process_perf_data.py perf_gemm.log
+python3 process_perf_data.py perf_resnet50_N256.log
+python3 process_perf_data.py perf_resnet50_N4.log
diff --git a/script/process_qa_data.sh b/script/process_qa_data.sh
index 917305e916..abf1e6234e 100755
--- a/script/process_qa_data.sh
+++ b/script/process_qa_data.sh
@@ -10,15 +10,14 @@
 # please contact Illia.Silin@amd.com for more details
 
 #process results
-gpu_arch=$1
-python3 process_perf_data.py perf_gemm_"$gpu_arch".log
-python3 process_perf_data.py perf_resnet50_N256_"$gpu_arch".log
-python3 process_perf_data.py perf_resnet50_N4_"$gpu_arch".log
-python3 process_perf_data.py perf_batched_gemm_"$gpu_arch".log
-python3 process_perf_data.py perf_grouped_gemm_"$gpu_arch".log
-python3 process_perf_data.py perf_conv_fwd_"$gpu_arch".log
-python3 process_perf_data.py perf_conv_bwd_data_"$gpu_arch".log
-python3 process_perf_data.py perf_gemm_bilinear_"$gpu_arch".log
-python3 process_perf_data.py perf_reduction_"$gpu_arch".log
-python3 process_perf_data.py perf_splitK_gemm_"$gpu_arch".log
-python3 process_perf_data.py perf_onnx_gemm_"$gpu_arch".log
+python3 process_perf_data.py perf_gemm.log
+python3 process_perf_data.py perf_resnet50_N256.log
+python3 process_perf_data.py perf_resnet50_N4.log
+python3 process_perf_data.py perf_batched_gemm.log
+python3 process_perf_data.py perf_grouped_gemm.log
+python3 process_perf_data.py perf_conv_fwd.log
+python3 process_perf_data.py perf_conv_bwd_data.log
+python3 process_perf_data.py perf_gemm_bilinear.log
+python3 process_perf_data.py perf_reduction.log
+python3 process_perf_data.py perf_splitK_gemm.log
+python3 process_perf_data.py perf_onnx_gemm.log
diff --git a/script/run_full_performance_tests.sh b/script/run_full_performance_tests.sh
index 1626b7f28d..eae334ae2d 100755
--- a/script/run_full_performance_tests.sh
+++ b/script/run_full_performance_tests.sh
@@ -5,12 +5,11 @@
 # post your new test results to the database and compare them to the baseline
 # please contact Illia.Silin@amd.com for more details
 #
-# run the script as "./run_full_performance_tests.sh <verification> <tag for your test environment> <gpu_arch> <branch name> < node name>
+# run the script as "./run_full_performance_tests.sh <verification> <tag for your test environment> <branch name> < node name>
 # input arguments: 
 # verification = 0 : do not verify result correctness on CPU
 #              = 1 : verifuy correctness on CPU (may take a long time)
 # environment tag  : a string describing the specifics of your test environment
-# gpu_arch         : a string for GPU architecture, e.g. "gfx908" or "gfx90a".
 # branch name      : name of the branch in git repo (git status | grep -e 'On branch')
 # node name        : $hostname
 
@@ -19,11 +18,9 @@ export verify=$1
 echo 'Verification: ' $verify
 export env_type=$2
 echo 'Environment type: ' $env_type
-export gpu_arch=$3
-echo 'GPU architecture: ' $gpu_arch
-export branch=$4
+export branch=$3
 echo 'Branch name: ' $branch
-export host_name=$5
+export host_name=$4
 echo 'Host name: ' $host_name
 function print_log_header(){
 	rm -f $1;
@@ -38,7 +35,7 @@ function print_log_header(){
 }
 
 #run gemm tests
-export gemm_log="perf_gemm_${gpu_arch}.log"
+export gemm_log="perf_gemm.log"
 print_log_header $gemm_log $env_type $branch $host_name
 ./profile_gemm.sh gemm 0 0 $verify 1 0 1 2>&1 | tee -a $gemm_log
 ./profile_gemm.sh gemm 1 0 $verify 1 0 1 2>&1 | tee -a $gemm_log
@@ -58,7 +55,7 @@ print_log_header $gemm_log $env_type $branch $host_name
 ./profile_gemm.sh gemm 3 3 $verify 1 0 1 2>&1 | tee -a $gemm_log
 
 #run batched_gemm tests
-export batched_gemm_log="perf_batched_gemm_${gpu_arch}.log"
+export batched_gemm_log="perf_batched_gemm.log"
 print_log_header $batched_gemm_log $env_type $branch $host_name
 ./profile_batched_gemm.sh batched_gemm 0 0 $verify 1 0 1 2>&1 | tee -a $batched_gemm_log
 ./profile_batched_gemm.sh batched_gemm 0 1 $verify 1 0 1 2>&1 | tee -a $batched_gemm_log
@@ -78,7 +75,7 @@ print_log_header $batched_gemm_log $env_type $branch $host_name
 ./profile_batched_gemm.sh batched_gemm 3 3 $verify 1 0 1 2>&1 | tee -a $batched_gemm_log
 
 #run grouped_gemm tests
-export grouped_gemm_log="perf_grouped_gemm_${gpu_arch}.log"
+export grouped_gemm_log="perf_grouped_gemm.log"
 print_log_header $grouped_gemm_log $env_type $branch $host_name
 ./profile_grouped_gemm.sh grouped_gemm 1 0 $verify 1 0 1 2>&1 | tee -a $grouped_gemm_log
 ./profile_grouped_gemm.sh grouped_gemm 1 1 $verify 1 0 1 2>&1 | tee -a $grouped_gemm_log
@@ -86,7 +83,7 @@ print_log_header $grouped_gemm_log $env_type $branch $host_name
 ./profile_grouped_gemm.sh grouped_gemm 1 3 $verify 1 0 1 2>&1 | tee -a $grouped_gemm_log
 
 #run GEMM+Bilinear tests
-export gemm_bilinear_log="perf_gemm_bilinear_${gpu_arch}.log"
+export gemm_bilinear_log="perf_gemm_bilinear.log"
 print_log_header $gemm_bilinear_log $env_type $branch $host_name
 ./profile_gemm_bilinear.sh gemm_bilinear 1 0 $verify 1 0 1 2>&1 | tee -a $gemm_bilinear_log
 ./profile_gemm_bilinear.sh gemm_bilinear 1 1 $verify 1 0 1 2>&1 | tee -a $gemm_bilinear_log
@@ -94,7 +91,7 @@ print_log_header $gemm_bilinear_log $env_type $branch $host_name
 ./profile_gemm_bilinear.sh gemm_bilinear 1 3 $verify 1 0 1 2>&1 | tee -a $gemm_bilinear_log
 
 #run conv_fwd tests
-export conv_fwd_log="perf_conv_fwd_${gpu_arch}.log"
+export conv_fwd_log="perf_conv_fwd.log"
 print_log_header $conv_fwd_log $env_type $branch $host_name
 ./profile_conv_fwd.sh conv_fwd 0 1 $verify 1 0 1 256 2>&1 | tee -a $conv_fwd_log
 ./profile_conv_fwd.sh conv_fwd 1 1 $verify 1 0 1 256 2>&1 | tee -a $conv_fwd_log
@@ -102,7 +99,7 @@ print_log_header $conv_fwd_log $env_type $branch $host_name
 ./profile_conv_fwd.sh conv_fwd 3 1 $verify 1 0 1 256 2>&1 | tee -a $conv_fwd_log
 
 #run conv_bwd_data tests
-export conv_bwd_data_log="perf_conv_bwd_data_${gpu_arch}.log"
+export conv_bwd_data_log="perf_conv_bwd_data.log"
 print_log_header $conv_bwd_data_log $env_type $branch $host_name
 ./profile_conv_bwd_data.sh conv_bwd_data 0 1 $verify 1 0 1 256 2>&1 | tee -a $conv_bwd_data_log
 ./profile_conv_bwd_data.sh conv_bwd_data 1 1 $verify 1 0 1 256 2>&1 | tee -a $conv_bwd_data_log
@@ -110,33 +107,43 @@ print_log_header $conv_bwd_data_log $env_type $branch $host_name
 ./profile_conv_bwd_data.sh conv_bwd_data 3 1 $verify 1 0 1 256 2>&1 | tee -a $conv_bwd_data_log
 
 #run resnet50 tests
-export resnet256_log="perf_resnet50_N256_${gpu_arch}.log"
+export resnet256_log="perf_resnet50_N256.log"
 print_log_header $resnet256_log $env_type $branch $host_name
 ./profile_resnet50.sh conv_fwd_bias_relu 1 1 1 1 $verify 1 0 1 256 2>&1 | tee -a $resnet256_log
-export resnet4_log="perf_resnet50_N4_${gpu_arch}.log"
+export resnet4_log="perf_resnet50_N4.log"
 print_log_header $resnet4_log $env_type $branch $host_name
 ./profile_resnet50.sh conv_fwd_bias_relu 1 1 1 1 $verify 1 0 1 4 2>&1 | tee -a $resnet4_log
 
 #run reduction tests
-export reduction_log="perf_reduction_${gpu_arch}.log"
+export reduction_log="perf_reduction.log"
 print_log_header $reduction_log $env_type $branch $host_name
 ./profile_reduce_with_index.sh $verify 2 10 --half 2>&1 | tee -a $reduction_log
 ./profile_reduce_no_index.sh $verify 2 10 --half 2>&1 | tee -a $reduction_log
 
-#run splitK_gemm tests
-export splitK_gemm_log="perf_splitK_gemm_${gpu_arch}.log"
+#run splitK_gemm tests, first correctness verification, then performance
+export splitK_gemm_ver_log="perf_splitK_gemm_verify.log"
+print_log_header $splitK_gemm_ver_log $env_type $branch $host_name
+./profile_splitK_gemm.sh gemm_splitk 0 0 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 0 1 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 0 2 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 0 3 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 1 0 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 1 1 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 1 2 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+./profile_splitK_gemm.sh gemm_splitk 1 3 $verify 1 0 0 4 2>&1 | tee -a $splitK_gemm_ver_log
+export splitK_gemm_log="perf_splitK_gemm.log"
 print_log_header $splitK_gemm_log $env_type $branch $host_name
-./profile_splitK_gemm.sh gemm_splitk 0 0 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 0 1 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 0 2 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 0 3 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 1 0 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 1 1 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 1 2 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
-./profile_splitK_gemm.sh gemm_splitk 1 3 $verify 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 0 0 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 0 1 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 0 2 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 0 3 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 1 0 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 1 1 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 1 2 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
+./profile_splitK_gemm.sh gemm_splitk 1 3 0 1 0 1 4 2>&1 | tee -a $splitK_gemm_log
 
 #run ONNX gemm tests
-export onnx_log="perf_onnx_gemm_${gpu_arch}.log"
+export onnx_log="perf_onnx_gemm.log"
 print_log_header $onnx_log $env_type $branch $host_name
 ./profile_onnx_gemm.sh gemm 0 0 $verify 1 0 1 2>&1 | tee -a $onnx_log
 ./profile_onnx_gemm.sh gemm 1 0 $verify 1 0 1 2>&1 | tee -a $onnx_log
diff --git a/script/run_performance_tests.sh b/script/run_performance_tests.sh
index f8ec2cbe49..4e3a6fc8eb 100755
--- a/script/run_performance_tests.sh
+++ b/script/run_performance_tests.sh
@@ -1,12 +1,11 @@
 #!/bin/bash 
 #
 # in order to run this script you'd first need to build the ckProfiler executable in ../build/bin/
-# run the script as "./run_performance_tests.sh <verification> <tag for your test environment> <gpu_arch> <branch name> < node name>
+# run the script as "./run_performance_tests.sh <verification> <tag for your test environment> <branch name> < node name>
 # input arguments: 
 # verification = 0 : do not verify result correctness on CPU
 #              = 1 : verify correctness on CPU (may take a long time)
 # environment tag  : a string describing the specifics of your test environment
-# gpu_arch         : a string for GPU architecture, e.g. "gfx908" or "gfx90a".
 # branch name      : name of the branch in git repo (git status | grep -e 'On branch')
 # node name        : $hostname
 
@@ -15,11 +14,9 @@ export verify=$1
 echo 'Verification: ' $verify
 export env_type=$2
 echo 'Environment type: ' $env_type
-export gpu_arch=$3
-echo 'GPU architecture: ' $gpu_arch
-export branch=$4
+export branch=$3
 echo 'Branch name: ' $branch
-export host_name=$5
+export host_name=$4
 echo 'Host name: ' $host_name
 
 function print_log_header(){
@@ -35,7 +32,7 @@ function print_log_header(){
 }
 
 #run gemm tests
-export gemm_log="perf_gemm_${gpu_arch}.log"
+export gemm_log="perf_gemm.log"
 print_log_header $gemm_log $env_type $branch $host_name
 ./profile_gemm.sh gemm 0 0 $verify 1 0 1 | tee -a $gemm_log
 ./profile_gemm.sh gemm 1 0 $verify 1 0 1 | tee -a $gemm_log
@@ -55,9 +52,9 @@ print_log_header $gemm_log $env_type $branch $host_name
 ./profile_gemm.sh gemm 3 3 $verify 1 0 1 | tee -a $gemm_log
 
 #run resnet50 tests
-export resnet256_log="perf_resnet50_N256_${gpu_arch}.log"
+export resnet256_log="perf_resnet50_N256.log"
 print_log_header $resnet256_log $env_type $branch $host_name
 ./profile_resnet50.sh conv_fwd_bias_relu 1 1 1 1 $verify 1 0 1 256 | tee -a $resnet256_log
-export resnet4_log="perf_resnet50_N4_${gpu_arch}.log"
+export resnet4_log="perf_resnet50_N4.log"
 print_log_header $resnet4_log $env_type $branch $host_name
 ./profile_resnet50.sh conv_fwd_bias_relu 1 1 1 1 $verify 1 0 1 4 | tee -a $resnet4_log