High-Performance Network Fabrics and Libraries

Not long ago, high-performance network fabrics like InfiniBand, HPE Slingshot, or Intel Omni-Path (now CORNELIS) were primarily found in supercomputers or high-performance computing (HPC) clusters aimed at scientific applications. These fabrics…

Visual Guide to Distribution Patterns for Arrays in MPI, NCCL

Parquet, Orc, Avro, CSV and JSON

We encounter data in many different formats. Some common examples are CSV, JSON, XML, Text, and Binary…

Introduction to UCX Network Programming

Network programming is always a hassle; on the bright side, as developers, we rarely get…

High-performance Computing for Modern Data Applications — An Introduction

Data-driven computing coupled with artificial intelligence (AI) is the crown jewel of modern computing. From the 1980s to around…

Scalability of IO-Intensive Applications

Modern computing applications can be divided into broader categories: IO-intensive and…

The Three Core Concepts behind Data Frameworks

The three most important aspect of a data framework…

Table Abstractions for Data Processing

Table abstractions are a great way to represent heterogeneous and structured data in memory. In data analytics, a table is a structured data collection organized into rows and columns. Each row represents a unique record, and each column represents a field in…

In-Memory Data Structures for Data Operations

Every program deals with data structures. Whether it is a distributed program running on thousands of computers or a serial program running on a laptop, we can find data structures everywhere. Data structures are built using primitive types such as…

Arrays & Tensors for Data Processing

Vectors and matrices are two foundational structures in computations. A vector is an ordered…