VK: scale auto shader compiler workers on wide CPUs

rpcs3/Emu/RSX/VK/VKPipelineCompiler.cpp

@@ -216,16 +216,27 @@ namespace vk
 		return {};
 	}
 
-	void initialize_pipe_compiler(int num_worker_threads)
-	{
-		if (num_worker_threads == 0)
-		{
-			// Select optimal number of compiler threads
-			const auto hw_threads = utils::get_thread_count();
-			if (hw_threads > 12)
-			{
-				num_worker_threads = 6;
-			}
+	void initialize_pipe_compiler(int num_worker_threads)
+	{
+		if (num_worker_threads == 0)
+		{
+			// Select a conservative but modern default for async pipeline compilation.
+			// Older heuristics topped out too early on high-core CPUs and left large
+			// shader bursts queued longer than necessary.
+			const auto hw_threads = utils::get_thread_count();
+
+			if (hw_threads >= 24)
+			{
+				num_worker_threads = 12;
+			}
+			else if (hw_threads >= 16)
+			{
+				num_worker_threads = 8;
+			}
+			else if (hw_threads > 12)
+			{
+				num_worker_threads = 6;
+			}
 			else if (hw_threads > 8)
 			{
 				num_worker_threads = 4;
@@ -234,11 +245,14 @@ namespace vk
 			{
 				num_worker_threads = 2;
 			}
-			else
-			{
-				num_worker_threads = 1;
-			}
-		}
+			else
+			{
+				num_worker_threads = 1;
+			}
+
+			rsx_log.notice("Async pipeline compiler auto-selected %d worker(s) for %u host thread(s).",
+				num_worker_threads, hw_threads);
+		}
 
 		ensure(num_worker_threads >= 1);
 		ensure(g_render_device); // "Cannot initialize pipe compiler before creating a logical device"