masahi commented on a change in pull request #7833:
URL: https://github.com/apache/tvm/pull/7833#discussion_r612772705
##########
File path: src/runtime/vulkan/vulkan.cc
##########
@@ -60,35 +91,21 @@ class VulkanThreadEntry {
pool.reset();
streams_.clear();
for (const auto& kv : staging_buffers_) {
- if (!kv.second) {
- continue;
- }
- auto& buf = *(kv.second);
- if (buf.host_addr != nullptr) {
- vkUnmapMemory(buf.device, buf.memory);
- }
- if (buf.memory != VK_NULL_HANDLE) {
- vkFreeMemory(buf.device, buf.memory, nullptr);
- }
- if (buf.buffer != VK_NULL_HANDLE) {
- vkDestroyBuffer(buf.device, buf.buffer, nullptr);
- }
+ DeleteHostVisibleBuffer(kv.second.get());
Review comment:
> BTW, we might want to confirm what is the behavior of writing to the
same piece of memory from the host after a previous pipeline that reads the
same memory has been submitted
Interesting, this was not an issue when I was making UBO per pipeline. We
could still do per pipeline UBO, per thread entry if this is problematic.
--
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]
