

The image below shows a zoom into one frame’s timeline, from CPU start to GPU end. In the screenshot above, you can see an ID3D11DeviceContext::Map call that takes ~15 ms to return, during which the application's main thread does nothing.
#Copy paste queue civ 3 driver#
Graphics Trace Analyzer also shows the time spent processing each Direct3D* 11 API call (i.e., application -> runtime -> driver and back).

Hence, there is opportunity to improve performance, i.e. visual fidelity and/or fps.īefore Profiling: Frame time = ~21 ms Less than 1 frame queued Gaps in the GPU queue Very long Map call If the GPU queue is not fully loaded by the CPU, it will have gaps, causing the application to fail to leverage the visible idle time. The GPU queue has several gaps within and between frames, with less than one frame's worth of work queued up at any time. The screenshot below is a trace capture from the game (without v-sync) before improvements were made. We started the rendering performance analysis with Intel® Graphics Performance Analyzers' Graphics Trace Analyzer (formerly Platform Analyzer). This article describes the issue and the fix and emphasizes the importance of using performance analysis tools during development, while keeping their strengths and limitations in mind. One of the big performance improvements made was the removal of several CPU-GPU sync stalls that were responsible for losing some parallelism between the CPU and GPU. During the early access and beta periods, we profiled and analyzed the rendering performance of the game. Galactic Civilizations* 3 (GC3) is a turn-based 4X strategy game developed and published by Stardock Entertainment that released on May 14th, 2015. This case study will guide game devs through the profiling process documenting the profiling that was done to optimize Galactic Civilizations* 3 before it's release in 2015.ĭownload Document (Note: In this document Graphics Trace Analyzer was referred to as Platform Analyzer.) While Intel® GPA tools have been updated since this article was written, the following process is relevant and can be referenced as a case study to understand the advantages of incorporating profiling into your development process. Follow along on the profiling journey, seeing how the Intel® GPA tool suite was used to find these bottlenecks and detail the importance of using profiling tools during game development. It is showcases how 2 of the Intel® GPA tools, Graphics Trace Analyzer and Graphics Frame Analyzer are used to identify performance issues within the GPU queue, visualizing activity in the GPU queue and the CPU cores.

This article details how Intel® GPA was used to improve the Galactic Civilizations video game.
