Differences

This shows you the differences between two versions of the page.

--- skill-tree:k:1:1:b [2020/06/24 17:02] – kai_h
+++ skill-tree:k:1:1:b [2022/10/21 14:53] (current) – ruben.kellner
@@ Line 2: / Line 2: @@
 # Background
-An HPC cluster is built out of a few to many servers that are connected by a high
+An HPC cluster is built out of a few up to many servers that are connected by a high-performance communication network.
-performance communication network. The servers are called nodes. HPC clusters use
+The servers are called nodes.
-batch systems for running compute jobs. Interactive access is usually limited to a few
+HPC clusters use batch systems for running compute jobs.
-nodes.
+Interactive access is usually limited to a few nodes.
+A typical cluster contains of these parts:
-# Aim
-  * To provide knowledge about the hardware components of an HPC cluster and their functions
-# Outcomes
   * various system-, hardware-, and I/O-architectures used for supercomputers, i.e. shared memory systems, distributed systems, and cluster systems
   * physical hardware; chassis/rack, computer system units, interconnect, power., compute node architecture with memory, local disk, and sockets
   * typical architecture of cluster systems consisting of nodes with different roles (e.g. so-called head, management, login, compute, interactive, visualization nodes, etc.)
-  * Comprehend there are nodes with several functions
+Which are functioning as:
-    * **Login or gateway nodes** where you are on after logging into the cluster and where you can work interactively
+* **Login or gateway nodes** where you are on after logging into the cluster and where you can work interactively
     * **Compute nodes** that are the workhorses of a cluster
     * **Admin or system nodes** that work in the background necessary for the operation of the cluster, e.g. for running the batch service, or starting and shutting down compute nodes
@@ Line 21: / Line 18: @@
     * **Special nodes** e.g. for data movement, visualization, or pre- and post-processing of large data sets
     * **Head nodes** which can mean login or admin nodes used for management either by a user or an administrator
-  * Comprehend that nodes are connected by a high performance communication network
+# Aim
+  * To provide knowledge about the hardware components of an HPC cluster and their functions.
+# Outcomes
+  * Comprehend there are nodes with several functions
+  * Comprehend that nodes are connected by a high-performance communication network
   * Comprehend that global file systems are available on all nodes of the cluster and are convenient because their files can be accessed directly on all nodes
     * Quantitatively, parallel file systems offer higher I/O performance than classic network file systems
     * Qualitatively, they allow several processes to write into the same file
   * Comprehend the two purposes of the communication network
-    * enabling high speed data communication for parallel applications running on multiple nodes
+    * Enabling high-speed data communication for parallel applications running on multiple nodes
-    * providing a high speed connection to the disk systems in the cluster
+    * Providing a high-speed connection to the disk systems in the cluster
 # Subskills
   * [[skill-tree:k:1:1:1:b]]