![nsight opengl 4.6 nsight opengl 4.6](https://docs.nvidia.com/nsight-visual-studio-edition/2020.1/analysis-tools/graphics/analysis-activity-advanced-options.01.png)
Similar thing can be done in Apitrace (for the cases when you change call parameters in the main interface), but I do not know whether long profile times would make it usable. When you change something (like shader code, directx states etc), you can reprofile and see the difference in numbers.
![nsight opengl 4.6 nsight opengl 4.6](https://devblogs.nvidia.com/wp-content/uploads/2018/11/Figure-7.-Nsight-Range-Profiler-tooltip-showing-PerfWorks-metric-names-and-descriptions.-1.png)
There is however a feature that can be brought to Apitrace profiling. For those who are interested: recently there was proposed a project of creating frame-analysis tool based on Apitrace, and it is being discussed quite actively on the mailing list. This could be implemented later on the basis of what is already done. Anyway, I do not think I am dealing with this in the scope of my project. I do not even know if this is actually possible to implement in the current state. Initially I was not even thinking about Apitrace as an individual frame analyzer. Also the set of available metrics differs from the one used in traces (I had pretty much nothing on my Intel HD 3000). Metrics collection works differently for these set of tasks (details here ). The tool gives the ability to analyze both individual calls (ergs in GPA terminology) and group of calls (grouped by render target). In reality, this option grays out everything except the selected object (and objects connected to it, neighbors in the timeline), so that some numbers in the statistics pane (bottom one) are recalculated.įrame Analyzer offers many options, but I will focus on profiling. So, for example, you could filter by specific call (or call types, like draw calls), and easily find them in the timeline. I thought it filters out everything but the objects of the type selected. I think this is a nice visualization and it could be implemented in Apitrace, though I am not sure if per-call metrics can be displayed in such a way.īy the way, you can have a look at what metrics are supported here: Īlso there is a filtering option. What is interesting here – GPU metrics are displayed as separate graphs in the timeline along other data (screens below). Among others there are cpu/gpu frame bounds, gpu usage, DirectX tasks by thread.
![nsight opengl 4.6 nsight opengl 4.6](https://images-na.ssl-images-amazon.com/images/I/71bDuYpQ1DL._AC_UL600_SR600,600_.jpg)
Trace files can be opened in Platform Analyzer. You can have arbitrary many of them, and all the data displayed is also included in the trace capture file when you save one. This is the tool that connects to your current session and displays performance graphs in realtime. In the options (screen above) you are limited to selecting only 4 counters (probably because more would not fit into HUD), but you can extend this number by using System Analyzer. Also note, that there is no replay functionality (as in Apitrace), all performance data is collected per frame (there is actually a more fine-grained option) and at the same time timeline is made (when application is run). Graphics Monitor is simply used to display HUD and collect data (one frame snapshot or a trace for some fixed duration) from applications by setting up some triggers or manually using hotkeys (which almost never work as analyzed applications trap all keystrokes). The toolset consists of several applications: Graphics Monitor, System Analyzer, Platform Analyzer, Frame Analyzer. Also I was told that Core OpenGL profile is being developed. Intel GPA (DirectX): Platform Analyzer + Frame AnalyzerĬurrently supported Apis include DirectX and OpenGL ES (with linux toolkit available), but not OpenGL.
Nsight opengl 4.6 windows#
Do not be surprised by the look of Windows UI and DirectX api names.ġ. Sadly enough, not all of these tools are available on Linux (on linux you have Visual Profiler for CUDA and AMD CodeXL for OpenCL, that is all I’ve found) and not all of them do support OpenGL profiling. I had a look at Intel GPA (as a part of Intel INDE ’15), AMD PerfStudio (3.2.18.0), NVIDIA Nsight (4.6) and CUDA Visual Profiler (7.0). This is certainly not a detailed review, I was primarily focusing on profiling and applications to Apitrace. Recently I was experimenting with existing similar software. As you probably know, I will be adding some performance counters and enhancing the profiling view of Apitrace this GSoC summer.