radv: Change memory type order for GPUs without dedicated VRAM

Put the uncached GTT type at a higher index than the visible VRAM type,
rather than having GTT first.

When we don't have dedicated VRAM, we don't have a non-visible VRAM
type, and the property flags for GTT and visible VRAM are identical.
According to the spec, for types with identical flags, we should give
the one with better performance a lower index.

Previously, apps which follow the spec guidance for choosing a memory
type would have picked the GTT type in preference to visible VRAM (all
Feral games will do this), and end up with lower performance.

On a Ryzen 5 2500U laptop (Raven Ridge), this improves average FPS in
the Rise of the Tomb Raider benchmark by up to ~30%. Tested a couple of
other (Feral) games and saw similar improvement on those as well.

Signed-off-by: Alex Smith <asmith@feralinteractive.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Cc: 19.2 <mesa-stable@lists.freedesktop.org>
(Bas: CCing this to 19.2-rc due to high impact and limited complexity)

diff --git a/src/amd/vulkan/radv_device.c b/src/amd/vulkan/radv_device.c
index 39d87b5b5756f882d745cad337318cdb577f3536..34e65f11e0a18505c7d7ddc4d051539cc03fc73b 100644 (file)
--- a/src/amd/vulkan/radv_device.c
+++ b/src/amd/vulkan/radv_device.c
@@ -173,12 +173,11 @@ radv_physical_device_init_mem_types(struct radv_physical_device *device)
                        .heapIndex = vram_index,
                };
        }
-       if (gart_index >= 0) {
+       if (gart_index >= 0 && device->rad_info.has_dedicated_vram) {
                device->mem_type_indices[type_count] = RADV_MEM_TYPE_GTT_WRITE_COMBINE;
                device->memory_properties.memoryTypes[type_count++] = (VkMemoryType) {
                        .propertyFlags = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
-                       VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
-                       (device->rad_info.has_dedicated_vram ? 0 : VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT),
+                       VK_MEMORY_PROPERTY_HOST_COHERENT_BIT,
                        .heapIndex = gart_index,
                };
        }
@@ -191,6 +190,19 @@ radv_physical_device_init_mem_types(struct radv_physical_device *device)
                        .heapIndex = visible_vram_index,
                };
        }
+       if (gart_index >= 0 && !device->rad_info.has_dedicated_vram) {
+               /* Put GTT after visible VRAM for GPUs without dedicated VRAM
+                * as they have identical property flags, and according to the
+                * spec, for types with identical flags, the one with greater
+                * performance must be given a lower index. */
+               device->mem_type_indices[type_count] = RADV_MEM_TYPE_GTT_WRITE_COMBINE;
+               device->memory_properties.memoryTypes[type_count++] = (VkMemoryType) {
+                       .propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
+                       VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+                       VK_MEMORY_PROPERTY_HOST_COHERENT_BIT,
+                       .heapIndex = gart_index,
+               };
+       }
        if (gart_index >= 0) {
                device->mem_type_indices[type_count] = RADV_MEM_TYPE_GTT_CACHED;
                device->memory_properties.memoryTypes[type_count++] = (VkMemoryType) {