[Profile] Attribute render thread GPU waits to their call sites

src/SharpEmu.Libs/Gpu/Vulkan/VulkanAsyncReadback.cs

@@ -172,10 +172,13 @@ internal sealed unsafe class VulkanAsyncReadback : IDisposable
                 PSemaphores = &semaphore,
                 PValues = &signalValue,
             };
+            var waitStart = VideoOut.GpuWaitSiteProfile.Begin();
             using (VideoOut.RenderPhaseProfile.MeasureDetail(VideoOut.RenderPhaseProfile.Phase.GpuCompletionWait))
             {
                 Require(vk.WaitSemaphores(_device.Device, &waitInfo, ulong.MaxValue), "vkWaitSemaphores(readback)");
             }
+
+            VideoOut.GpuWaitSiteProfile.End(waitStart);
         }
         finally
         {

src/SharpEmu.Libs/Gpu/Vulkan/VulkanTickDevice.cs

@@ -220,10 +220,13 @@ internal sealed unsafe class VulkanTickDevice : IGpuTickDevice
             PValues = &tick,
         };
         Result result;
+        var waitStart = GpuWaitSiteProfile.Begin();
         using (RenderPhaseProfile.MeasureDetail(RenderPhaseProfile.Phase.GpuCompletionWait))
         {
             result = _vk.WaitSemaphores(_device, &waitInfo, ulong.MaxValue);
         }
+
+        GpuWaitSiteProfile.End(waitStart);
         failure = result.ToString();
         return result == Result.Success && WaitRetired(tick);
     }

src/SharpEmu.Libs/VideoOut/GpuWaitSiteProfile.cs

@@ -0,0 +1,96 @@
+// Copyright (C) 2026 SharpEmu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+using System.Diagnostics;
+
+namespace SharpEmu.Libs.VideoOut;
+
+internal static class GpuWaitSiteProfile
+{
+    private const int SiteFrames = 5;
+
+    private static readonly object _gate = new();
+    private static readonly Dictionary<string, (long Count, long Ticks)> _sites = new(StringComparer.Ordinal);
+
+    private static readonly HashSet<string> PlumbingTypes = new(StringComparer.Ordinal)
+    {
+        "GpuWaitSiteProfile",
+        "TickTimeline",
+        "SubmissionScheduler",
+        "VulkanTickDevice",
+        "VulkanAsyncReadback",
+        "GpuWorkerRelay",
+        "GpuWaitSpin",
+    };
+
+    public static long Begin() => RenderPhaseProfile.DetailMeasurementsEnabled ? Stopwatch.GetTimestamp() : 0;
+
+    public static void End(long start)
+    {
+        if (start == 0)
+        {
+            return;
+        }
+
+        var elapsed = Stopwatch.GetTimestamp() - start;
+        var site = Site();
+        lock (_gate)
+        {
+            _sites.TryGetValue(site, out var entry);
+            _sites[site] = (entry.Count + 1, entry.Ticks + elapsed);
+        }
+    }
+
+    private static string Site()
+    {
+        var names = new List<string>(SiteFrames);
+        foreach (var frame in new StackTrace(2, false).GetFrames())
+        {
+            if (frame.GetMethod() is not { } method)
+            {
+                continue;
+            }
+
+            var type = method.DeclaringType;
+            while (type is { DeclaringType: not null } && type.Name.StartsWith('<'))
+            {
+                type = type.DeclaringType;
+            }
+
+            var typeName = type?.Name ?? "?";
+            if (PlumbingTypes.Contains(typeName) || method.Name.StartsWith('<'))
+            {
+                continue;
+            }
+
+            names.Add($"{typeName}.{method.Name}");
+            if (names.Count == SiteFrames)
+            {
+                break;
+            }
+        }
+
+        return string.Join(" < ", names);
+    }
+
+    public static void Report()
+    {
+        List<KeyValuePair<string, (long Count, long Ticks)>> ranked;
+        lock (_gate)
+        {
+            if (_sites.Count == 0)
+            {
+                return;
+            }
+
+            ranked = _sites.OrderByDescending(pair => pair.Value.Ticks).Take(12).ToList();
+            _sites.Clear();
+        }
+
+        foreach (var (site, (count, ticks)) in ranked)
+        {
+            Console.Error.WriteLine(
+                $"[PERF][GPU_WAIT_SITE] ms={ticks * 1000.0 / Stopwatch.Frequency:F1} n={count} site={site}");
+        }
+    }
+}

src/SharpEmu.Libs/VideoOut/RenderPhaseProfile.cs

@@ -465,6 +465,7 @@ internal static class RenderPhaseProfile
             $"[PERF][RENDER_MS] window_s={seconds:F1} frames={frames} " +
             string.Join(" ", parts.Select(part => $"{part.Phase}={part.Milliseconds:F2}ms/n{part.Entries}")));
 
+        GpuWaitSiteProfile.Report();
         ReportImageUploads();
         BufferUploadProfile.Report();
         Console.Error.WriteLine(SharpEmu.ShaderCompiler.Resources.ResourceMaterializationCache.TakeReport());