masahi commented on a change in pull request #7833:
URL: https://github.com/apache/tvm/pull/7833#discussion_r613741111
##########
File path: src/runtime/vulkan/vulkan.cc
##########
@@ -990,57 +1058,59 @@ Module
VulkanModuleCreate(std::unordered_map<std::string, VulkanShader> smap,
VulkanThreadEntry* VulkanThreadEntry::ThreadLocal() { return
VulkanThreadStore::Get(); }
-VulkanStagingBuffer* VulkanThreadEntry::StagingBuffer(int device_id, size_t
size) {
- if (!staging_buffers_[device_id]) {
- staging_buffers_[device_id] = std::unique_ptr<VulkanStagingBuffer>(new
VulkanStagingBuffer());
+VulkanHostVisibleBuffer* GetOrAllocate(
Review comment:
ok I wrote something but as I wrote, I realized that I didn't really
understand this issue deeply. My main confusion point is: if we want to make
sure that old tasks get finished before we delete the buffer they use,
shouldn't we sync before we call `DeleteHostVisibleBuffer`? Or
`DeleteHostVisibleBuffer` itself, that calls `vkFreeMemory` etc, is async and
it only records the commands to the queue (so sync after
`DeleteHostVisibleBuffer` as in this PR makes sense)?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
