Merge pull request #2554 from hpe-dev-incubator/cms/platform/dragonhpc/home

Create Platforms “dragonhpc/home”

Author: choukden

content/blog/3-ways-a-data-fabric-enables-a-data-first-approach.md

@@ -7,6 +7,7 @@ disable: false
 tags:
   - hpe-ezmeral-data-fabric
   - hpe-ezmeral
+  - dragonhpc
 ---
 **Editor’s note: This article was originally posted on HPE Enterprise.nxt on March 15, 2022**
 
@@ -34,10 +35,8 @@ Data motion is a key issue in large-scale data systems. Data motion can include
 
 At one extreme, people may have an ingrained assumption that data motion is not a viable option, based on legacy systems that lack any provision for moving data. Without motion, data that could have value if put into a more global context may be discarded instead.
 
-
 ![Block text](/img/3waysadatafabric-enablesadatafirstapproach-quote.png "Block text")
 
-
 At other companies, the pendulum has swung radically to the opposite extreme, with a policy that all data to be analyzed must be moved to a central data center, either on premises or in the cloud. Unfortunately, the costs of data motion mount up, and where large amounts of data are at issue, only a tiny fraction of all possible data will be moved. Once again, data you could analyze is simply discarded.
 
 Fortunately, a new middle ground is emerging. In telecommunications, finance, media, manufacturing, and other business sectors, far more data is collected than could possibly be moved back to headquarters. Data is partially processed in situ before extracts and summaries are moved to a central location or a regional sub-center for further analysis on aggregates from many edge sources. This edge processing strategy commonly uses pattern recognition to pull out the interesting bits or anomalies for transfer.
@@ -81,8 +80,8 @@ Having the right data infrastructure lets you focus on the decisions that will m
 ### Lessons for leaders
 
 * A data fabric is a highly scalable data infrastructure designed to store, manage, and move data as a unifying layer across an enterprise from edge to data center, on premises or in the cloud.  
-* A well-engineered modern data fabric allows DevOps and other teams to access data in the way they prefer.   
-* Making wrong assumptions about data motion is one of the most common ways businesses inadvertently give up their ability to extract value from data. 
+* A well-engineered modern data fabric allows DevOps and other teams to access data in the way they prefer.
+* Making wrong assumptions about data motion is one of the most common ways businesses inadvertently give up their ability to extract value from data.
 
 <br />
 

content/opensource/dragonhpc.md

@@ -0,0 +1,11 @@
+---
+title: DragonHPC
+active: true
+category: Cloud Native
+link: /platform/dragonhpc/home/
+description: DragonHPC is a programmable distributed runtime for HPC & AI workflows.
+priority: 17
+Featured: true
+image: /img/opensource/Kubedirector.svg
+---
+DragonHPC is a programmable distributed runtime for HPC & AI workflows.

content/platform/dragonhpc/home.md

@@ -0,0 +1,36 @@
+---
+title: DragonHPC
+version: 1.0.0
+description: DragonHPC is a programmable distributed runtime for HPC & AI workflows.
+image: /img/platforms/dragon_deployment.jpg
+width: large
+priority: 4
+active: true
+tags:
+  - dragonhpc
+---
+DragonHPC is a programmable distributed runtime for HPC & AI workflows. The DragonHPC distributed runtime will power complex post-exascale workflows that can scale, that are cloud-native, that can access data efficiently, that can span multiple systems, and that can be used with multiple languages on heterogeneous hardware.
+
+## Key advantages of using DragonHPC
+
+Among other frameworks and libraries, DragonHPC addresses much of the friction developers and scientists face when approaching a computational problem:
+
+* Program across widely distributed resources (e.g., laptops, servers, cloud, supercomputers) as if they were all one computer.
+
+* Implement applications and workflows across Python, C, C++, and Fortran with interoperable high-performance objects instead of being locked into a single language.
+
+* Implement Python-based applications and workflows using the standard multiprocessing API instead of non-standard interfaces.
+
+* Develop applications and highly dynamic workflows without the limitations of static execution graphs.
+
+* Orchestrate individual or collections of Python functions, binaries, and MPI processes.
+
+* Leverage RDMA and leading-edge HPC communication techniques through simple high-level interfaces and communication objects instead of communication through a filesystem.
+
+Users can also access DragonHPC at any level of its architecture. This allows users to develop new components within Dragon that natively interoperate with existing components. Flexibility, composability, and the ability to adopt DragonHPC for applications, tools, and workflows with strict performance requirements dramatically improves user productivity.
+
+## Online resources for getting up and running with DragonHPC
+
+[Public open source code repository with example use cases ![](Github)](https://github.com/DragonHPC/dragon)
+
+[Public open source code repository ![](Github)](https://dragonhpc.github.io/dragon/doc/_build/html/index.html)

gatsby-config.js

@@ -429,6 +429,7 @@ module.exports = {
           "determined-ai",
           "cray",
           "swarm-learning",
+          "dragonhpc",
           "hpe-nonstop"
           ]}}}, sort: {frontmatter: {date: DESC}}) {
             nodes {
@@ -493,6 +494,7 @@ module.exports = {
     paginatedCollection('determined-ai-posts', 'determined-ai'),
     paginatedCollection('cray-posts', 'cray'),
     paginatedCollection('swarm-posts', 'swarm-learning'),
+    paginatedCollection('dragonhpc-posts', 'dragonhpc'),
     paginatedCollection('hpe-nonstop-posts', 'hpe-nonstop'),
     paginatedCollection('dscc-posts', 'data-services-cloud-console'),
     {

gatsby-node.js

@@ -201,13 +201,14 @@ exports.createPages = async ({ graphql, actions }) => {
     paginatedCollectionQuery('smartsim-posts'),
   );
 
-  const crayQueryResult = await graphql(
-    paginatedCollectionQuery('cray-posts'),
-  );
+  const crayQueryResult = await graphql(paginatedCollectionQuery('cray-posts'));
 
   const swarmQueryResult = await graphql(
     paginatedCollectionQuery('swarm-posts'),
   );
+  const dragonhpcQueryResult = await graphql(
+    paginatedCollectionQuery('dragonhpc-posts'),
+  );
 
   const hpeNonStopQueryResult = await graphql(
     paginatedCollectionQuery('hpe-nonstop-posts'),
@@ -242,41 +243,42 @@ exports.createPages = async ({ graphql, actions }) => {
   setPagination(smartsimQueryResult);
   setPagination(crayQueryResult);
   setPagination(swarmQueryResult);
+  setPagination(dragonhpcQueryResult);
   setPagination(hpeNonStopQueryResult);
   setPagination(othersQueryResult);
 
-  return graphql(
-    `
-      {
-        allMarkdownRemark(
-          filter: { frontmatter: { disable: { ne: true } } }
-          sort: {frontmatter: {date: DESC}}
-          limit: 1000
-        ) {
-          edges {
-            node {
-              fields {
-                slug
-                sourceInstanceName
-              }
-              frontmatter {
-                title
-                disable
-                tags
-                isAside
-              }
+  return graphql(`
+    {
+      allMarkdownRemark(
+        filter: { frontmatter: { disable: { ne: true } } }
+        sort: { frontmatter: { date: DESC } }
+        limit: 1000
+      ) {
+        edges {
+          node {
+            fields {
+              slug
+              sourceInstanceName
+            }
+            frontmatter {
+              title
+              disable
+              tags
+              isAside
             }
           }
         }
-        tagsGroup: allMarkdownRemark(limit: 2000,
-          filter:{frontmatter:{disable:{ne:true}}}) {
-          group(field: {frontmatter: {tags: SELECT}}) {
-            fieldValue
-          }
+      }
+      tagsGroup: allMarkdownRemark(
+        limit: 2000
+        filter: { frontmatter: { disable: { ne: true } } }
+      ) {
+        group(field: { frontmatter: { tags: SELECT } }) {
+          fieldValue
         }
       }
-    `,
-  ).then((result) => {
+    }
+  `).then((result) => {
     if (result.errors) {
       throw result.errors;
     }

src/components/BlogTabs/index.js

@@ -116,6 +116,10 @@ function BlogTabs({ data, columns }) {
       label: 'HPE Swarm Learning',
       count: data?.swarmBlogsCount?.totalCount || 0,
     },
+    dragonhpcBlogs: {
+      label: 'DragonHPC',
+      count: data?.dragonhpcCount?.totalCount || 0,
+    },
     hpeNonstopBlogs: {
       label: 'HPE NonStop',
       count: data?.hpeNonstopBlogsCount?.totalCount || 0,
@@ -147,6 +151,10 @@ function BlogTabs({ data, columns }) {
       label: 'SmartSim',
       count: data.smartSimBlogsCount?.totalCount || 0,
     },
+    dragonhpcBlogs: {
+      label: 'Dragonhpc',
+      count: data.dragonhpcBlogsCount?.totalCount || 0,
+    },
   };
 
   const platformsMenuItems = Object.entries(data)
@@ -416,6 +424,7 @@ BlogTabs.propTypes = {
     dsccBlogsCount: PropTypes.objectOf(PropTypes.number),
     crayBlogsCount: PropTypes.objectOf(PropTypes.number),
     swarmBlogsCount: PropTypes.objectOf(PropTypes.number),
+    dragonhpcBlogsCount: PropTypes.objectOf(PropTypes.number),
     hpeNonstopBlogsCount: PropTypes.objectOf(PropTypes.number),
     othersBlogsCount: PropTypes.objectOf(PropTypes.number),
   }).isRequired,

src/components/Header/index.js

@@ -16,7 +16,6 @@ import { AppContext } from '../../providers/AppProvider';
 import { ButtonLink } from '..';
 import { UserMenu } from './UserMenu';
 
-
 const TextAlignLeft = styled(Box)`
   & > a {
     text-align: left;