OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

anv: add a third memory type for LLC configuration

Browse Source 
Commit 582bf4d9 turned on write-combining for most (all?) memory
allocations.  This caused a fairly large performance drop in some of
our VMware tests (application traces, such as Windows Metro Paint).

This patch adds a third memory type configuration: DEVICE_LOCAL,
HOST_VISIBLE, HOST_COHERENT.  This is uncached.  Then, in
anv_AllocateMemory() we only use write-combining for this uncached
type.  This memory type is found in the Intel Windows Vulkan driver.
And according to
https://asawicki.info/news_1740_vulkan_memory_types_on_pc_and_how_to_use_them
uncached memory correlates to write-combined memory.

This fixes our performance regression (and actually produced the
fastest ever results for our test suite).

Signed-off-by: Brian Paul <brianp@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20770>
This commit is contained in:
Brian Paul
2023-01-18 09:01:15 -07:00
committed by Marge Bot
parent 15e19d04f0
commit fbd32a04da
1 changed files with 21 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/intel/vulkan/anv_device.c
View File

@@ -514,19 +514,28 @@ anv_physical_device_init_heaps(struct anv_physical_device *device, int fd)
* But some game engines can't handle single type well
* https://gitlab.freedesktop.org/mesa/mesa/-/issues/7360#note_1719438
*
* And Intel on Windows uses 3 types so it's better to add extra one here
* The second memory type w/out HOST_CACHED_BIT will get write-combining.
* See anv_AllocateMemory()).
*
* The Intel Vulkan driver for Windows also advertises these memory types.
*/
device->memory.type_count = 2;
device->memory.type_count = 3;
device->memory.types[0] = (struct anv_memory_type) {
.propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
.heapIndex = 0,
.propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
.heapIndex = 0,
};
device->memory.types[1] = (struct anv_memory_type) {
.propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
VK_MEMORY_PROPERTY_HOST_CACHED_BIT,
.heapIndex = 0,
.propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_BIT,
.heapIndex = 0,
};
device->memory.types[2] = (struct anv_memory_type) {
.propertyFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
VK_MEMORY_PROPERTY_HOST_CACHED_BIT,
.heapIndex = 0,
};
} else {
device->memory.heap_count = 1;
@@ -3819,7 +3828,7 @@ VkResult anv_AllocateMemory(
return vk_error(device, VK_ERROR_OUT_OF_DEVICE_MEMORY);
assert(pAllocateInfo->memoryTypeIndex < pdevice->memory.type_count);
struct anv_memory_type *mem_type =
const struct anv_memory_type *mem_type =
&pdevice->memory.types[pAllocateInfo->memoryTypeIndex];
assert(mem_type->heapIndex < pdevice->memory.heap_count);
struct anv_memory_heap *mem_heap =
@@ -3914,9 +3923,10 @@ VkResult anv_AllocateMemory(
alloc_flags |= ANV_BO_ALLOC_NO_LOCAL_MEM;
/* If the allocated buffer might end up in local memory and it's host
* visible, make CPU writes are combined, it should be faster.
* visible and uncached, enable CPU write-combining. It should be faster.
*/
if (!(alloc_flags & ANV_BO_ALLOC_NO_LOCAL_MEM) &&
(mem_type->propertyFlags & VK_MEMORY_PROPERTY_HOST_CACHED_BIT) == 0 &&
(mem_type->propertyFlags & VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT))
alloc_flags |= ANV_BO_ALLOC_WRITE_COMBINE;