vulkan: use graphics queue on AMD (ggml-org#20551)

* vulkan: use graphics queue on AMD for slightly better performance

* disable async transfer queue on AMD

Author: 0cc4m

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -4981,8 +4981,10 @@ static vk_device ggml_vk_get_device(size_t idx) {
         std::vector<vk::QueueFamilyProperties> queue_family_props = device->physical_device.getQueueFamilyProperties();
 
         // Try to find a non-graphics compute queue and transfer-focused queues
-        const uint32_t compute_queue_family_index = ggml_vk_find_queue_family_index(queue_family_props, vk::QueueFlagBits::eCompute, vk::QueueFlagBits::eGraphics, -1, 1);
-        const uint32_t transfer_queue_family_index = ggml_vk_find_queue_family_index(queue_family_props, vk::QueueFlagBits::eTransfer, vk::QueueFlagBits::eCompute | vk::QueueFlagBits::eGraphics, compute_queue_family_index, 1);
+        // On AMD, the graphics queue seems to be faster, so don't avoid it
+        const vk::QueueFlagBits graphics_flag = device->vendor_id == VK_VENDOR_ID_AMD ? (vk::QueueFlagBits)0 : vk::QueueFlagBits::eGraphics;
+        const uint32_t compute_queue_family_index = ggml_vk_find_queue_family_index(queue_family_props, vk::QueueFlagBits::eCompute, graphics_flag, -1, 1);
+        const uint32_t transfer_queue_family_index = ggml_vk_find_queue_family_index(queue_family_props, vk::QueueFlagBits::eTransfer, vk::QueueFlagBits::eCompute | graphics_flag, compute_queue_family_index, 1);
 
         const float priorities[] = { 1.0f, 1.0f };
         device->single_queue = compute_queue_family_index == transfer_queue_family_index && queue_family_props[compute_queue_family_index].queueCount == 1;
@@ -5441,13 +5443,11 @@ static vk_device ggml_vk_get_device(size_t idx) {
 
         ggml_vk_load_shaders(device);
 
-        const bool prefers_transfer_queue = device->vendor_id == VK_VENDOR_ID_AMD && device->architecture != AMD_GCN;
-
         if (!device->single_queue) {
             const uint32_t transfer_queue_index = compute_queue_family_index == transfer_queue_family_index ? 1 : 0;
             ggml_vk_create_queue(device, device->transfer_queue, transfer_queue_family_index, transfer_queue_index, { vk::PipelineStageFlagBits::eTransfer }, true);
 
-            device->async_use_transfer_queue = prefers_transfer_queue || (getenv("GGML_VK_ASYNC_USE_TRANSFER_QUEUE") != nullptr);
+            device->async_use_transfer_queue = (getenv("GGML_VK_ASYNC_USE_TRANSFER_QUEUE") != nullptr);
         } else {
             // TODO: Use pointer or reference to avoid copy
             device->transfer_queue.copyFrom(device->compute_queue);