![[High-Performance C++ Engine #1] Why Legacy Win32/MFC Trading Systems Freeze at the 9:00 AM Market Open](/images/cpp_hts_market_data_engine_series/img_part1_legacy_hts_ui_freezing_bottlenecks.webp)
Why Legacy Win32/MFC Trading Systems Freeze at the 9:00 AM Market Open
An architectural dissection of why multi-decade Win32/MFC desktop trading platforms suffer from severe UI freezing during the 09:00 AM market open packet surge.
CPP 17
Chronological index of published articles, technical notes, and essays in CPP.
![[High-Performance C++ Engine #2] Zero-Mutex Market Data Engine — Symbol Hash Sharding & Lock-Free RCU/CoW](/images/cpp_hts_market_data_engine_series/img_part2_sharded_ingestion_lockfree_rcu.webp)
Zero-Mutex Market Data Engine — Symbol Hash Sharding & Lock-Free RCU/CoW
How we implemented symbol-hash worker sharding and Lock-Free Read-Copy-Update (RCU) snapshot slots with Copy-on-Write so tens of thousands of real-time mar…
![[High-Performance C++ Engine #3] Multi-Exchange (Primary + ATS) Real-Time 10-Level OrderBook Synthesis & Out-of-Order Determinism](/images/cpp_hts_market_data_engine_series/img_part3_multi_exchange_state_projection.webp)
Multi-Exchange (Primary + ATS) Real-Time 10-Level OrderBook Synthesis & Out-of-Order Determinism
How we deterministically synthesize Primary Exchange and Alternative Exchange (ATS) orderbooks in real time, and prevent out-of-order races between Expecte…
![[High-Performance C++ Engine #4] Let the UI Thread Only Paint — ScreenWorker Background Formatting & 64MB Ring-Buffer Virtual Grid](/images/cpp_hts_market_data_engine_series/img_part4_screen_worker_virtual_grid.webp)
Let the UI Thread Only Paint — ScreenWorker Background Formatting & 64MB Ring-Buffer Virtual Grid
How we offloaded 28 display field formatting operations to background ScreenWorkers with Double Dirty Coalescing, built an O(1) 64MB ring-buffer VirtualGri…
![[High-Performance C++ Engine #5] 1% CPU & 1-Second Lag War Stories (Message Storms, ActiveX Batching, 60-Cell Clipping)](/images/cpp_hts_market_data_engine_series/img_part5_micro_optimizations_troubleshooting.webp)
1% CPU & 1-Second Lag War Stories (Message Storms, ActiveX Batching, 60-Cell Clipping)
How we hunted down and eliminated three subtle production bottlenecks—423/s Win32 message storms, ActiveX COM per-cell redraw overhead, and a 1-second quot…
![[High-Performance C++ Engine #6] Production Scorecard (UI Freeze 1,531ms → 15ms) & Zero-Downtime Dual-Path Rollout](/images/cpp_hts_market_data_engine_series/img_part6_production_metrics_dual_path.webp)
Production Scorecard (UI Freeze 1,531ms → 15ms) & Zero-Downtime Dual-Path Rollout
The complete 540-second market open benchmark scorecard comparing AS-IS vs. TO-BE, alongside our Dual-Path rollout architecture and engineering lessons fro…
![[C++] Tracking & Resolving Zombie Process Bugs in Large-Scale MFC HTS Architecture](/images/cpp_mfc_hts_zombie_process_fix/img_mfc_zombie_process_architecture.webp)
Tracking & Resolving Zombie Process Bugs in Large-Scale MFC HTS Architecture
Enterprise financial Home Trading Systems (HTS) operate on massive C++/MFC codebases spanning decades of development. Following the integration of a new hi…
![[C++] How C++ Static Reflection Will Transform Serialization Architecture](/images/cpp26_static_reflection_serialization/img_cpp26_reflection_vs_legacy_serialization.webp)
How C++ Static Reflection Will Transform Serialization Architecture
Serializing objects to disk, network packets, or JSON format in C++ has traditionally been a painful compromise. Developers were forced to inject invasive …
![[C++] C++26 Flat Containers & Hazard Pointers: Ultra Low-Latency Data Pipeline Design](/images/cpp26_flat_containers_hazard_pointer/img_cpp26_map_vs_flat_map_cache_locality.webp)
C++26 Flat Containers & Hazard Pointers: Ultra Low-Latency Data Pipeline Design
In financial HTS and High-Frequency Trading (HFT) platforms, order book snapshots and market quotes reside on the nanosecond-critical read path. Traditiona…
![[C++] std::execution & Senders/Receivers: Foundations of High-Performance Concurrency](/images/cpp26_std_execution_senders_receivers/img_cpp26_execution_vs_legacy_futures.webp)
std::execution & Senders/Receivers: Foundations of High-Performance Concurrency
Asynchronous and parallel programming in C++ has historically been burdened with fragmented primitives. std::thread, std::future, and std::promise introduc…