About memory_order_relaxed? ● Just a load, just a store: Full control, excellent efficiency and scalability! ○ Assuming aligned machine-sized atomic objects, that is…What is Not to Like About memory_order_relaxed memory_order_relaxed? ● Just a load, just a store: Full control, excellent efficiency and scalability! ○ Assuming aligned machine-sized atomic objects, that is… ● Small problems: Out of thin air (OOTA) & read About memory_order_relaxed? ● Just a load, just a store: Full control, excellent efficiency and scalability! ○ Assuming aligned machine-sized atomic objects, that is… ● Small problems: Out of thin air

locks and therefore parallel task execution with near zero contention between threads ● Excellent Scalability: ○ Over 40x higher throughput than the fastest MPMC queue at scale ○ Over 100x higher throughput locks and therefore parallel task execution with near zero contention between threads ● Excellent Scalability: ○ Over 40x higher throughput than the fastest MPMC queue at scale ○ Over 100x higher throughput locks and therefore parallel task execution with near zero contention between threads ● Excellent Scalability: ○ Over 40x higher throughput than the fastest MPMC queue at scale ○ Over 100x higher throughput

All rvalue (reference)s go through the second overload, others through the first • Key problem: scalability • Two definitions • Scales poorly to multiple arguments (T mentioned in the returned type) constexpr a move happens if needed •The additional T() is either a move ctor call OR a no-op, as needed •Scalability problem remains • T still mentioned in the returned type • We can’t return arbitrary expressions

(PETRA) Design Goals ▶ High Performance ▶ Low overheads added to achieve durability ▶ High Scalability ▶ Performance scaling well with increasing number of processes ▶ Non-Blocking ▶ There is guaranteed Demonstration References Persistent Transactional Data System for Linked Data Structures (PETRA) High Scalability ▶ Transactional synchronization for conflicts on nodes ▶ Logical rollback when a semantic conflict

Robust! Useful and Robust! Tricky! • Correlations imply dependencies (with implications for scalability and side-effects) • Assumptions may be invalid for your scenarioCharley Bay - charleyb123 at gmail Robust! Useful and Robust! Tricky! • Correlations imply dependencies (with implications for scalability and side-effects) • Assumptions may be invalid for your scenario Knowing “something” can be more

Software Engineerhttps://www.linkedin.com/in/sakverma Functional, concurrent language built for scalability. Ideal for managing large-scale cloud applications. Built on the Erlang VM, ensuring resilience

Machines Behavior Trees Learning curve more familiar it needs some practice Concurrency no yes Scalability poor better Readability scales very poorly better Behavior Trees VS Hierarchical State Machines"Tick"

Path Penetration Performance Qualification Ramp Recovery Regression Requirements Sanity Scalability Scenario Security Smoke Stability Statement Static Storage Stress Structural System integration

atomic operations in your coroutines • They generally won’t hurt • They generally enable more scalability • Alternatively, consider lock-less implementations© 2023 Intel Corporation and Jeffrey E. Erickson

Schrödinger’s Zoo and Werner Heisenberg’s advice 2.Increase uncertainty to get performance and scalability 3.So Procrastinate away! Use Structured Deferral 4.Shared_ptr vs atomic_shared_ptr vs hazard pointers