[GPU] Request guest memory barriers through the recording buffer

src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.CachedImages.cs

@@ -1048,6 +1048,8 @@ internal static unsafe partial class VulkanVideoPresenter
                     continue;
                 }
 
+                _commandBuffer = BeginBatchedGuestCommands();
+
                 var initialized = texture.HostMoviePlane == 0 ? _hostMovieImageInitialized : _hostMovieChromaImageInitialized;
                 var toTransfer = new ImageMemoryBarrier2
                 {

src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.CommandStream.cs

@@ -541,6 +541,12 @@ internal static unsafe partial class VulkanVideoPresenter
             }
 
             EndRendering();
+            if (BatchBarriers)
+            {
+                RequestGuestMemoryBarrier(GlobalMemoryBarrier);
+                return;
+            }
+
             RecordGlobalBarrier(BeginBatchedGuestCommands());
         }
 

src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Descriptors.cs

@@ -842,7 +842,7 @@ internal static unsafe partial class VulkanVideoPresenter
             using var profileScope = RenderPhaseProfile.MeasureDetail(RenderPhaseProfile.Phase.DescriptorCommit);
             var preparation = RequirePreparation();
             var entry = RequirePipelineEntry(in pipeline);
-            var command = BeginBatchedGuestCommands();
+            var command = BeginBatchedGuestStateCommands();
             _commandBuffer = command;
             var writeCount = 0;
             var bufferCount = 0;

src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.GuestSubmissions.cs

@@ -47,13 +47,32 @@ internal static unsafe partial class VulkanVideoPresenter
         private CommandBuffer BeginBatchedGuestCommands()
         {
             var commandBuffer = CurrentRecordingBuffer();
+            OpenGuestBatch();
+            return commandBuffer;
+        }
+
+        private CommandBuffer BeginBatchedGuestStateCommands()
+        {
+            var recording = CurrentRecording();
+            OpenGuestBatch();
+            return new CommandBuffer(recording.StateHandle);
+        }
+
+        private void RequestGuestMemoryBarrier(in MemoryBarrierRequest request)
+        {
+            var recording = CurrentRecording();
+            OpenGuestBatch();
+            _scheduler.MemoryBarrierRecorder ??= RecordRequestedMemoryBarrier;
+            recording.RequestMemoryBarrier(request);
+        }
+
+        private void OpenGuestBatch()
+        {
             if (!_batchOpen)
             {
                 _batchOpen = true;
                 _batchDrawCount = 0;
             }
-
-            return commandBuffer;
         }
 
         // Submits the current recording buffer with everything the batch lists own.

src/SharpEmu.Libs/VideoOut/VulkanVideoPresenter.Rendering.cs

@@ -856,12 +856,17 @@ internal static unsafe partial class VulkanVideoPresenter
             }
 
             EndRendering();
-            var command = BeginBatchedGuestCommands();
-            _commandBuffer = command;
-            if (DeferGlobalBarriers)
+            if (DeferGlobalBarriers && BatchBarriers)
             {
                 // A guest cache flush inside this scope may be deferred to its end; this keeps
                 // everything recorded before the scope ordered before its draws either way.
+                RequestGuestMemoryBarrier(GlobalMemoryBarrier);
+            }
+
+            var command = BeginBatchedGuestCommands();
+            _commandBuffer = command;
+            if (DeferGlobalBarriers && !BatchBarriers)
+            {
                 RecordGlobalBarrier(command);
             }
 
@@ -986,7 +991,7 @@ internal static unsafe partial class VulkanVideoPresenter
         public void BindPipeline(PipelineBindPoint bindPoint, in PipelineHandle pipeline)
         {
             var entry = RequirePipelineEntry(in pipeline);
-            var command = BeginBatchedGuestCommands();
+            var command = BeginBatchedGuestStateCommands();
             if (bindPoint == PipelineBindPoint.Graphics)
             {
                 _boundGraphicsPipeline = entry;
@@ -1149,9 +1154,24 @@ internal static unsafe partial class VulkanVideoPresenter
             return true;
         }
 
+        private static readonly bool BatchBarriers =
+            Environment.GetEnvironmentVariable("SHARPEMU_BATCH_BARRIERS") != "0";
+
+        private static readonly MemoryBarrierRequest GlobalMemoryBarrier = new(
+            PipelineStageFlags.AllCommandsBit,
+            PipelineStageFlags.AllCommandsBit,
+            AccessFlags.MemoryWriteBit,
+            AccessFlags.MemoryReadBit | AccessFlags.MemoryWriteBit);
+
         private void RecordMemoryBarrier(PipelineStageFlags sourceStages, PipelineStageFlags destinationStages, AccessFlags sourceAccess, AccessFlags destinationAccess)
         {
             EndRendering();
+            if (BatchBarriers)
+            {
+                RequestGuestMemoryBarrier(new MemoryBarrierRequest(sourceStages, destinationStages, sourceAccess, destinationAccess));
+                return;
+            }
+
             var command = BeginBatchedGuestCommands();
             var barrier = new MemoryBarrier2
             {