UCX 1.15 upgrade (#9824)

* UCX 1.15 upgrade Signed-off-by: Alessandro Bellina <[email protected]> * Also update scala 2.13 --------- Signed-off-by: Alessandro Bellina <[email protected]>
NVIDIA · Nov 22, 2023 · cd3f85f · cd3f85f
1 parent 908e986
commit cd3f85f
Show file tree

Hide file tree

Showing 8 changed files with 41 additions and 27 deletions.
diff --git a/docs/additional-functionality/shuffle-docker-examples/Dockerfile.rocky_no_rdma b/docs/additional-functionality/shuffle-docker-examples/Dockerfile.rocky_no_rdma
@@ -17,23 +17,26 @@
 #
 # The parameters are: 
 #   - CUDA_VER: 11.8.0 by default
-#   - UCX_VER and UCX_CUDA_VER: these are used to pick a package matching a specific UCX version and
-#                               CUDA runtime from the UCX github repo.
-#                               See: https://github.com/openucx/ucx/releases/
+#   - UCX_VER, UCX_CUDA_VER, and UCX_ARCH: 
+#       Used to pick a package matching a specific UCX version and
+#       CUDA runtime from the UCX github repo.
+#       See: https://github.com/openucx/ucx/releases/
 #   - ROCKY_VER: Rocky Linux OS version
 
 ARG CUDA_VER=11.8.0
-ARG UCX_VER=1.14.0
+ARG UCX_VER=1.15.0
 ARG UCX_CUDA_VER=11
+ARG UCX_ARCH=x86_64
 ARG ROCKY_VER=8
 FROM nvidia/cuda:${CUDA_VER}-runtime-rockylinux${ROCKY_VER}
 ARG UCX_VER
 ARG UCX_CUDA_VER
+ARG UCX_ARCH
 
 RUN yum update -y && yum install -y wget bzip2 numactl-libs libgomp
 RUN ls /usr/lib
 RUN mkdir /tmp/ucx_install && cd /tmp/ucx_install && \
-  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-centos8-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
+  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-centos8-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
   tar -xvf *.bz2 && \
   rpm -i ucx-$UCX_VER*.rpm && \
   rpm -i ucx-cuda-$UCX_VER*.rpm --nodeps && \

diff --git a/docs/additional-functionality/shuffle-docker-examples/Dockerfile.rocky_rdma b/docs/additional-functionality/shuffle-docker-examples/Dockerfile.rocky_rdma
@@ -17,22 +17,25 @@
 #
 # The parameters are: 
 #   - CUDA_VER: 11.8.0 by default
-#   - UCX_VER and UCX_CUDA_VER: these are used to pick a package matching a specific UCX version and
-#                               CUDA runtime from the UCX github repo.
-#                               See: https://github.com/openucx/ucx/releases/
+#   - UCX_VER, UCX_CUDA_VER, and UCX_ARCH: 
+#       Used to pick a package matching a specific UCX version and
+#       CUDA runtime from the UCX github repo.
+#       See: https://github.com/openucx/ucx/releases/
 #   - ROCKY_VER: Rocky Linux OS version
 
 ARG CUDA_VER=11.8.0
-ARG UCX_VER=1.14.0
+ARG UCX_VER=1.15.0
 ARG UCX_CUDA_VER=11
+ARG UCX_ARCH=x86_64
 ARG ROCKY_VER=8
 FROM nvidia/cuda:${CUDA_VER}-runtime-rockylinux${ROCKY_VER}
 ARG UCX_VER
 ARG UCX_CUDA_VER
+ARG UCX_ARCH
 
 RUN yum update -y && yum install -y wget bzip2 rdma-core numactl-libs libgomp libibverbs librdmacm
 RUN mkdir /tmp/ucx_install && cd /tmp/ucx_install && \
-  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-centos8-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
+  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-centos8-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
   tar -xvf *.bz2 && \
   rpm -i ucx-$UCX_VER*.rpm && \
   rpm -i ucx-cuda-$UCX_VER*.rpm --nodeps && \

diff --git a/docs/additional-functionality/shuffle-docker-examples/Dockerfile.ubuntu_no_rdma b/docs/additional-functionality/shuffle-docker-examples/Dockerfile.ubuntu_no_rdma
@@ -17,21 +17,24 @@
 #
 # The parameters are: 
 #   - CUDA_VER: 11.8.0 by default
-#   - UCX_VER and UCX_CUDA_VER: these are used to pick a package matching a specific UCX version and 
-#                               CUDA runtime from the UCX github repo.
-#                               See: https://github.com/openucx/ucx/releases/
+#   - UCX_VER, UCX_CUDA_VER, and UCX_ARCH: 
+#       Used to pick a package matching a specific UCX version and
+#       CUDA runtime from the UCX github repo.
+#       See: https://github.com/openucx/ucx/releases/
 #   - UBUNTU_VER: 20.04 by default
 #
 
 ARG CUDA_VER=11.8.0
-ARG UCX_VER=1.14.0
+ARG UCX_VER=1.15.0
 ARG UCX_CUDA_VER=11
+ARG UCX_ARCH=x86_64
 ARG UBUNTU_VER=20.04
 
 FROM nvidia/cuda:${CUDA_VER}-runtime-ubuntu${UBUNTU_VER}
 ARG UCX_VER
 ARG UCX_CUDA_VER
 ARG UBUNTU_VER
+ARG UCX_ARCH
 
 RUN apt-get update && apt-get install -y gnupg2
 # https://forums.developer.nvidia.com/t/notice-cuda-linux-repository-key-rotation/212771
@@ -41,7 +44,7 @@ RUN CUDA_UBUNTU_VER=`echo "$UBUNTU_VER"| sed -s 's/\.//'` && \
 RUN apt update
 RUN apt-get install -y wget
 RUN mkdir /tmp/ucx_install && cd /tmp/ucx_install && \
-  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
-  tar -xvf ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
+  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
+  tar -xvf ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
   apt install -y /tmp/ucx_install/*.deb && \
   rm -rf /tmp/ucx_install
diff --git a/docs/additional-functionality/shuffle-docker-examples/Dockerfile.ubuntu_rdma b/docs/additional-functionality/shuffle-docker-examples/Dockerfile.ubuntu_rdma
@@ -20,9 +20,10 @@
 #   - RDMA_CORE_VERSION: Set to 32.1 to match the rdma-core line in the latest 
 #                        released MLNX_OFED 5.x driver
 #   - CUDA_VER: 11.8.0 by default
-#   - UCX_VER and UCX_CUDA_VER: these are used to pick a package matching a specific UCX version and
-#                               CUDA runtime from the UCX github repo.
-#                               See: https://github.com/openucx/ucx/releases/
+#   - UCX_VER, UCX_CUDA_VER, and UCX_ARCH: 
+#       Used to pick a package matching a specific UCX version and
+#       CUDA runtime from the UCX github repo.
+#       See: https://github.com/openucx/ucx/releases/
 #   - UBUNTU_VER: 20.04 by default
 #
 # The Dockerfile first fetches and builds `rdma-core` to satisfy requirements for
@@ -34,15 +35,17 @@
 
 ARG RDMA_CORE_VERSION=32.1
 ARG CUDA_VER=11.8.0
-ARG UCX_VER=1.14.0
+ARG UCX_VER=1.15.0
 ARG UCX_CUDA_VER=11
+ARG UCX_ARCH=x86_64
 ARG UBUNTU_VER=20.04
 
 # Throw away image to build rdma_core
 FROM ubuntu:${UBUNTU_VER} as rdma_core
 ARG RDMA_CORE_VERSION
 ARG UBUNTU_VER
 ARG CUDA_VER
+ARG UCX_ARCH
 
 RUN apt-get update && apt-get install -y gnupg2
 # https://forums.developer.nvidia.com/t/notice-cuda-linux-repository-key-rotation/212771
@@ -61,6 +64,7 @@ RUN tar -xvf *.tar.gz && cd rdma-core*/ && dpkg-buildpackage -b -d
 FROM nvidia/cuda:${CUDA_VER}-runtime-ubuntu${UBUNTU_VER}
 ARG UCX_VER
 ARG UCX_CUDA_VER
+ARG UCX_ARCH
 ARG UBUNTU_VER
 
 RUN mkdir /tmp/ucx_install
@@ -70,7 +74,7 @@ COPY --from=rdma_core /*.deb /tmp/ucx_install/
 RUN apt update
 RUN apt-get install -y wget
 RUN cd /tmp/ucx_install && \
-  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
-  tar -xvf ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER.tar.bz2 && \
+  wget https://github.com/openucx/ucx/releases/download/v$UCX_VER/ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
+  tar -xvf ucx-$UCX_VER-ubuntu$UBUNTU_VER-mofed5-cuda$UCX_CUDA_VER-$UCX_ARCH.tar.bz2 && \
   apt install -y /tmp/ucx_install/*.deb && \
   rm -rf /tmp/ucx_install
diff --git a/jenkins/Dockerfile-blossom.multi b/jenkins/Dockerfile-blossom.multi
@@ -26,7 +26,7 @@
 
 ARG CUDA_VER=11.8.0
 ARG UBUNTU_VER=20.04
-ARG UCX_VER=1.15.0-rc6
+ARG UCX_VER=1.15.0
 # multi-platform build with: docker buildx build --platform linux/arm64,linux/amd64 <ARGS> on either amd64 or arm64 host
 # check available official arm-based docker images at https://hub.docker.com/r/nvidia/cuda/tags (OS/ARCH)
 FROM --platform=$TARGETPLATFORM nvidia/cuda:${CUDA_VER}-runtime-ubuntu${UBUNTU_VER}

diff --git a/jenkins/Dockerfile-blossom.ubuntu b/jenkins/Dockerfile-blossom.ubuntu
@@ -27,13 +27,14 @@
 
 ARG CUDA_VER=11.0.3
 ARG UBUNTU_VER=20.04
-ARG UCX_VER=1.14.0
+ARG UCX_VER=1.15.0
 ARG UCX_CUDA_VER=11
 FROM nvidia/cuda:${CUDA_VER}-runtime-ubuntu${UBUNTU_VER}
 ARG CUDA_VER
 ARG UBUNTU_VER
 ARG UCX_VER
 ARG UCX_CUDA_VER
+ARG UCX_ARCH=x86_64
 
 # https://forums.developer.nvidia.com/t/notice-cuda-linux-repository-key-rotation/212771
 RUN UB_VER=$(echo ${UBUNTU_VER} | tr -d '.') && \
@@ -65,7 +66,7 @@ RUN apt install -y inetutils-ping expect wget libnuma1 libgomp1
 
 RUN mkdir -p /tmp/ucx && \
     cd /tmp/ucx && \
-    wget https://github.com/openucx/ucx/releases/download/v${UCX_VER}/ucx-${UCX_VER}-ubuntu${UBUNTU_VER}-mofed5-cuda${UCX_CUDA_VER}.tar.bz2 && \
+    wget https://github.com/openucx/ucx/releases/download/v${UCX_VER}/ucx-${UCX_VER}-ubuntu${UBUNTU_VER}-mofed5-cuda${UCX_CUDA_VER}-${UCX_ARCH}.tar.bz2 && \
     tar -xvf *.bz2 && \
     dpkg -i *.deb && \
     rm -rf /tmp/ucx

diff --git a/pom.xml b/pom.xml
@@ -648,7 +648,7 @@
         https://github.com/openjdk/jdk17/blob/4afbcaf55383ec2f5da53282a1547bac3d099e9d/src/jdk.compiler/share/classes/com/sun/tools/javac/resources/compiler.properties#L1993-L1994
         -->
         <scala.javac.args>-Xlint:all,-serial,-path,-try,-processing|-Werror</scala.javac.args>
-        <ucx.version>1.14</ucx.version>
+        <ucx.version>1.15.0</ucx.version>
         <rapids.compressed.artifact>true</rapids.compressed.artifact>
         <rapids.default.jar.excludePattern/>
         <rapids.default.jar.phase>package</rapids.default.jar.phase>

diff --git a/scala2.13/pom.xml b/scala2.13/pom.xml
@@ -648,7 +648,7 @@
         https://github.com/openjdk/jdk17/blob/4afbcaf55383ec2f5da53282a1547bac3d099e9d/src/jdk.compiler/share/classes/com/sun/tools/javac/resources/compiler.properties#L1993-L1994
         -->
         <scala.javac.args>-Xlint:all,-serial,-path,-try,-processing|-Werror</scala.javac.args>
-        <ucx.version>1.14</ucx.version>
+        <ucx.version>1.15.0</ucx.version>
         <rapids.compressed.artifact>true</rapids.compressed.artifact>
         <rapids.default.jar.excludePattern/>
         <rapids.default.jar.phase>package</rapids.default.jar.phase>