From 49e4ad327810916e5175f942a34970b6d7a41fb7 Mon Sep 17 00:00:00 2001 From: Illia Silin <98187287+illsilin@users.noreply.github.com> Date: Mon, 14 Apr 2025 16:41:47 -0700 Subject: [PATCH] Upgrade default docker image to ROCm6.4 release. (#2082) * upgrade to rocm6.4 * fix gfx10 generic target syntax * use gfx1101 target for unit tests * use gfx1201 target for unit tests * do not use generic targets until 6.4.1 release * update target list and dockerfile.compiler [ROCm/composable_kernel commit: d55c9cb313ed7c38afb58ad182a809d055f9d99d] --- Dockerfile | 15 +++++++-------- Dockerfile.compiler | 2 +- Jenkinsfile | 14 +++++++------- 3 files changed, 15 insertions(+), 16 deletions(-) diff --git a/Dockerfile b/Dockerfile index 17800d92d5..2a8fb707c9 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,6 +1,6 @@ FROM ubuntu:22.04 ARG DEBIAN_FRONTEND=noninteractive -ARG ROCMVERSION=6.3 +ARG ROCMVERSION=6.4 ARG compiler_version="" ARG compiler_commit="" ARG CK_SCCACHE="" @@ -13,15 +13,15 @@ RUN set -xe && \ apt-get update && apt-get install -y --allow-unauthenticated apt-utils wget gnupg2 curl && \ curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor -o /etc/apt/trusted.gpg.d/rocm-keyring.gpg -RUN if [ "$ROCMVERSION" != "6.4" ]; then \ - sh -c "wget https://repo.radeon.com/amdgpu-install/$ROCMVERSION/ubuntu/focal/amdgpu-install_6.3.60300-1_all.deb --no-check-certificate" && \ +RUN if [ "$ROCMVERSION" != "6.5" ]; then \ + sh -c "wget https://repo.radeon.com/amdgpu-install/$ROCMVERSION/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb --no-check-certificate" && \ apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --allow-unauthenticated ./amdgpu-install_6.3.60300-1_all.deb && \ wget -qO - http://repo.radeon.com/rocm/rocm.gpg.key | apt-key add - && \ - sh -c "echo deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] $DEB_ROCM_REPO focal main > /etc/apt/sources.list.d/rocm.list" && \ - sh -c 'echo deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] https://repo.radeon.com/amdgpu/$ROCMVERSION/ubuntu focal main > /etc/apt/sources.list.d/amdgpu.list'; \ + sh -c "echo deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] $DEB_ROCM_REPO jammy main > /etc/apt/sources.list.d/rocm.list" && \ + sh -c 'echo deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] https://repo.radeon.com/amdgpu/$ROCMVERSION/ubuntu jammy main > /etc/apt/sources.list.d/amdgpu.list'; \ fi -RUN sh -c "echo deb http://mirrors.kernel.org/ubuntu focal main universe | tee -a /etc/apt/sources.list" && \ +RUN sh -c "echo deb http://mirrors.kernel.org/ubuntu jammy main universe | tee -a /etc/apt/sources.list" && \ amdgpu-install -y --usecase=rocm --no-dkms ## Sccache binary built from source for ROCm, only install if CK_SCCACHE is defined @@ -51,7 +51,6 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --allow- mpich \ net-tools \ pkg-config \ - python \ python3 \ python3-dev \ python3-pip \ @@ -99,7 +98,7 @@ RUN pip install --upgrade cmake==3.27.5 && \ dpkg -i dumb-init_*.deb && rm dumb-init_*.deb && \ # Install packages for processing the performance results pip3 install --upgrade pip && \ - pip3 install --upgrade pytest sqlalchemy==2.0.36 pymysql pandas==2.2.3 setuptools-rust setuptools>=75 sshtunnel==0.4.0 && \ + pip3 install --upgrade pytest sqlalchemy==2.0.36 pymysql pandas==2.2.3 setuptools-rust setuptools sshtunnel==0.4.0 && \ # Add render group groupadd -f render && \ # Install the new rocm-cmake version diff --git a/Dockerfile.compiler b/Dockerfile.compiler index a22103b96b..f4aa12f356 100644 --- a/Dockerfile.compiler +++ b/Dockerfile.compiler @@ -1,4 +1,4 @@ -ARG BASE_DOCKER="rocm/composable_kernel:ck_ub22.04_rocm6.3" +ARG BASE_DOCKER="rocm/composable_kernel:ck_ub22.04_rocm6.4" FROM $BASE_DOCKER ARG compiler_version="" ARG compiler_commit="" diff --git a/Jenkinsfile b/Jenkinsfile index d105e385ab..e6256fc3d8 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -39,7 +39,7 @@ def getBaseDockerImageName(){ } else{ def ROCM_numeric = "${params.ROCMVERSION}" as float - if ( ROCM_numeric < 6.4 ){ + if ( ROCM_numeric < 6.5 ){ img = "${env.CK_DOCKERHUB}:ck_ub22.04_rocm${params.ROCMVERSION}" } else{ @@ -519,13 +519,13 @@ def Build_CK(Map conf=[:]){ else if ( runShell('grep -n "gfx942" rocminfo.log') ) { arch_type = 2 } - else if ( runShell('grep -n "gfx1030" rocminfo.log') ) { + else if ( runShell('grep -n "gfx10" rocminfo.log') ) { arch_type = 3 } - else if ( runShell('grep -n "gfx1101" rocminfo.log') ) { + else if ( runShell('grep -n "gfx11" rocminfo.log') ) { arch_type = 4 } - else if ( runShell('grep -n "gfx1201" rocminfo.log') ) { + else if ( runShell('grep -n "gfx12" rocminfo.log') ) { arch_type = 5 } else if ( runShell('grep -n "gfx908" rocminfo.log') ) { @@ -744,8 +744,8 @@ def process_results(Map conf=[:]){ } //launch develop branch daily at 23:00 UT in FULL_QA mode and at 19:00 UT with latest staging compiler version -CRON_SETTINGS = BRANCH_NAME == "develop" ? '''0 23 * * * % RUN_FULL_QA=true;DISABLE_DL_KERNELS=true;ROCMVERSION=6.3;RUN_CK_TILE_FMHA_TESTS=true;RUN_CK_TILE_GEMM_TESTS=true - 0 21 * * * % ROCMVERSION=6.3;hipTensor_test=true;RUN_CODEGEN_TESTS=true;BUILD_GFX908=true; +CRON_SETTINGS = BRANCH_NAME == "develop" ? '''0 23 * * * % RUN_FULL_QA=true;DISABLE_DL_KERNELS=true;ROCMVERSION=6.4;RUN_CK_TILE_FMHA_TESTS=true;RUN_CK_TILE_GEMM_TESTS=true + 0 21 * * * % ROCMVERSION=6.4;hipTensor_test=true;RUN_CODEGEN_TESTS=true;BUILD_GFX908=true; 0 19 * * * % BUILD_DOCKER=true;COMPILER_VERSION=amd-staging;BUILD_COMPILER=/llvm-project/build/bin/clang++;USE_SCCACHE=false;NINJA_BUILD_TRACE=true 0 17 * * * % BUILD_DOCKER=true;COMPILER_VERSION=amd-mainline;BUILD_COMPILER=/llvm-project/build/bin/clang++;USE_SCCACHE=false;NINJA_BUILD_TRACE=true 0 15 * * * % BUILD_INSTANCES_ONLY=true;RUN_PERFORMANCE_TESTS=false;USE_SCCACHE=false @@ -770,7 +770,7 @@ pipeline { description: 'If you want to use a custom docker image, please specify it here (default: leave blank).') string( name: 'ROCMVERSION', - defaultValue: '6.3', + defaultValue: '6.4', description: 'Specify which ROCM version to use: 6.3 (default).') string( name: 'COMPILER_VERSION',