Persistent Hash Map Persistent Transactional Data Structures Live Demonstration ReferencesIntroduction Persistent Hash Map Persistent Transactional Data Structures Live Demonstration References Overview Introduction Data Structures Design Goals Methodology Performance Results Live Demonstration A Persistent Hash Map for Graph Processing Workloads and a Methodology for Persistent Transactional Data Structures 2In 2IntroductionIntroduction Persistent Hash Map Persistent Transactional Data Structures Live Demonstration References Introduction Persistent Memory ▶ Persistent Memory is positioned as a new tier in the

search is now O (log N)! Awesome!!!Problems (Not really, more like caveats …) Like all tree data structures, not really cache friendly. ● Can always represent the tree as a heap but you still jump around

List-like data structures std::vector std::list std::dequestd::vector C++ version of the array-list data structure Backed by a C-style array Automatically allocates a new backing array when inserting

supercomputer? Introduce PGAS Model, RDMA Building Remote Pointer Types Building Distributed Data Structures Extending to GPUsThis Talk Background: how do we write a program for a supercomputer? Introduce Introduce PGAS Model, RDMA Building Remote Pointer Types Building Distributed Data Structures Extending to GPUsThis Talk Background: how do we write a program for a supercomputer? Introduce PGAS Model Model, RDMA Building Remote Pointer Types Building Distributed Data Structures Extending to GPUsThis Talk Background: how do we write a program for a supercomputer? Introduce PGAS Model, RDMA Building

0 GPU Tile 1 Tile 0 Xe LinkProject Goals - Offer high-level, standard C++ distributed data structures - Support distributed algorithms - Achieve high performance for both multi-GPU, NUMA, and (Ranges, Parallelism, Distributed Data Structures) - Distributed Ranges (Concepts) - Implementation (Algorithms and views) - Complex Data Structures (Dense and sparse matrices) - Lessons (Ranges, Parallelism, Distributed Data Structures) - Distributed Ranges (Concepts) - Implementation (Algorithms and views) - Complex Data Structures (Dense and sparse matrices) - Lessons

Stack/Queue Live Demonstration Design and Implementation of Highly Scalable Quantifiable Data Structures in C++ 2MotivationMotivation Quantifiability Vector Space Entropy Measurement Design and Implementation of atoms in the universe is 1082 Design and Implementation of Highly Scalable Quantifiable Data Structures in C++ 4Motivation Quantifiability Vector Space Entropy Measurement Design and Implementation of takes effect in real-time order. Design and Implementation of Highly Scalable Quantifiable Data Structures in C++ 5Motivation Quantifiability Vector Space Entropy Measurement Design and Implementation of

name: "optional square") 2 let sideLength = optionalSquare?.sideLength ​ Enumerations and Structures Use enum to create an enumeration. Like classes and all other named types, enumerations can have structure. Structures support many of the same behaviors as classes, including methods and initializers. One of the most important differences between structures and classes is that structures are always 4) You can make generic forms of functions and methods, as well as classes, enumerations, and structures. 1 // Reimplement the Swift standard library's optional type 2 enum OptionalValue { 3

ResearchMotivation std::simd Overview Example: Image Processing Programming Models Outlook Summary Data structures are the main challenge for efficient data-parallel execution. • Translating an inherently data-parallel ResearchMotivation std::simd Overview Example: Image Processing Programming Models Outlook Summary Data structures are the main challenge for efficient data-parallel execution. • Translating an inherently data-parallel Matthias Kretz CppCon ’23 GSI Helmholtz Center for Heavy Ion ResearchAppendix More Motivation Data Structures std::simd 1998 2000 2002 2004 2006 2008 2010 2012 2014 2016 2018 024 8 16 32 64 16× (Xeon)

// We use Offset-based pointers instead of raw pointers. This approach allows us to create data structures that are memcopyable, movable, and relocatable. Fanchen Su, XOffsetDatastructure, CppCon 2024 pointers. This approach allows us to create data structures that are memcopyable, movable, and relocatable. • Why do we need memcopyable structures? • Intra processes & inter processes • Intra devices Division1.1 XOffsetDatastructure • X + Offset + Datastructure • Data Structures • XOffsetDatastructure is a collection of data structures, including: • Base Types, Custom Types, Different Containers