1 Profiling 2 ========= 3 4 OpenSWR contains built-in profiling which can be enabled 5 at build time to provide insight into performance tuning. 6 7 To enable this, uncomment the following line in ``rasterizer/core/knobs.h`` and rebuild: :: 8 9 //#define KNOB_ENABLE_RDTSC 10 11 Running an application will result in a ``rdtsc.txt`` file being 12 created in current working directory. This file contains profile 13 information captured between the ``KNOB_BUCKETS_START_FRAME`` and 14 ``KNOB_BUCKETS_END_FRAME`` (see knobs section). 15 16 The resulting file will contain sections for each thread with a 17 hierarchical breakdown of the time spent in the various operations. 18 For example: :: 19 20 Thread 0 (API) 21 %Tot %Par Cycles CPE NumEvent CPE2 NumEvent2 Bucket 22 0.00 0.00 28370 2837 10 0 0 APIClearRenderTarget 23 0.00 41.23 11698 1169 10 0 0 |-> APIDrawWakeAllThreads 24 0.00 18.34 5202 520 10 0 0 |-> APIGetDrawContext 25 98.72 98.72 12413773688 29957 414380 0 0 APIDraw 26 0.36 0.36 44689364 107 414380 0 0 |-> APIDrawWakeAllThreads 27 96.36 97.62 12117951562 9747 1243140 0 0 |-> APIGetDrawContext 28 0.00 0.00 19904 995 20 0 0 APIStoreTiles 29 0.00 7.88 1568 78 20 0 0 |-> APIDrawWakeAllThreads 30 0.00 25.28 5032 251 20 0 0 |-> APIGetDrawContext 31 1.28 1.28 161344902 64 2486370 0 0 APIGetDrawContext 32 0.00 0.00 50368 2518 20 0 0 APISync 33 0.00 2.70 1360 68 20 0 0 |-> APIDrawWakeAllThreads 34 0.00 65.27 32876 1643 20 0 0 |-> APIGetDrawContext 35 36 37 Thread 1 (WORKER) 38 %Tot %Par Cycles CPE NumEvent CPE2 NumEvent2 Bucket 39 83.92 83.92 13198987522 96411 136902 0 0 FEProcessDraw 40 24.91 29.69 3918184840 167 23410158 0 0 |-> FEFetchShader 41 11.17 13.31 1756972646 75 23410158 0 0 |-> FEVertexShader 42 8.89 10.59 1397902996 59 23410161 0 0 |-> FEPAAssemble 43 19.06 22.71 2997794710 384 7803387 0 0 |-> FEClipTriangles 44 11.67 61.21 1834958176 235 7803387 0 0 |-> FEBinTriangles 45 0.00 0.00 0 0 187258 0 0 |-> FECullZeroAreaAndBackface 46 0.00 0.00 0 0 60051033 0 0 |-> FECullBetweenCenters 47 0.11 0.11 17217556 2869592 6 0 0 FEProcessStoreTiles 48 15.97 15.97 2511392576 73665 34092 0 0 WorkerWorkOnFifoBE 49 14.04 87.95 2208687340 9187 240408 0 0 |-> WorkerFoundWork 50 0.06 0.43 9390536 13263 708 0 0 |-> BELoadTiles 51 0.00 0.01 293020 182 1609 0 0 |-> BEClear 52 12.63 89.94 1986508990 949 2093014 0 0 |-> BERasterizeTriangle 53 2.37 18.75 372374596 177 2093014 0 0 |-> BETriangleSetup 54 0.42 3.35 66539016 31 2093014 0 0 |-> BEStepSetup 55 0.00 0.00 0 0 21766 0 0 |-> BETrivialReject 56 1.05 8.33 165410662 79 2071248 0 0 |-> BERasterizePartial 57 6.06 48.02 953847796 1260 756783 0 0 |-> BEPixelBackend 58 0.20 3.30 31521202 41 756783 0 0 |-> BESetup 59 0.16 2.69 25624304 33 756783 0 0 |-> BEBarycentric 60 0.18 2.92 27884986 36 756783 0 0 |-> BEEarlyDepthTest 61 0.19 3.20 30564174 41 744058 0 0 |-> BEPixelShader 62 0.26 4.30 41058646 55 744058 0 0 |-> BEOutputMerger 63 1.27 20.94 199750822 32 6054264 0 0 |-> BEEndTile 64 0.33 2.34 51758160 23687 2185 0 0 |-> BEStoreTiles 65 0.20 60.22 31169500 28807 1082 0 0 |-> B8G8R8A8_UNORM 66 0.00 0.00 302752 302752 1 0 0 WorkerWaitForThreadEvent 67 68
