[ET-VK] 4/n Split dispatches between multiple command buffers. Removing flush function call from submit_current_cmd_and_wait.

This diff removes the `flush` function call from `submit_current_cmd_and_wait` and instead adds it to the `encode_prepack` method.

This change will allow better control over flush which is needed in follow up diffs.

Differential Revision: [D78360036](https://our.internmc.facebook.com/intern/diff/D78360036/)

ghstack-source-id: 296431501
Pull Request resolved: #12525

Author: trivedivivek

backends/vulkan/runtime/graph/ComputeGraph.cpp

@@ -764,8 +764,6 @@ void ComputeGraph::submit_current_cmd_and_wait(const bool final_use) {
   context_->submit_cmd_to_gpu(fence.get_submit_handle(), final_use);
   fence.wait();
   context_->fences().return_fence(fence);
-
-  context_->flush();
 }
 
 void ComputeGraph::encode_prepack() {
@@ -794,6 +792,7 @@ void ComputeGraph::run_prepack() {
                                  : config_.prepack_initial_threshold_nbytes;
     if (not_terminal && staging_nbytes_in_cmd_ > threshold) {
       submit_current_cmd_and_wait(/*final_use=*/true);
+      context_->flush();
       staging_nbytes_in_cmd_ = 0;
       context_->set_cmd();
       submitted = true;
@@ -803,6 +802,7 @@ void ComputeGraph::run_prepack() {
     i++;
   }
   submit_current_cmd_and_wait(/*final_use=*/true);
+  context_->flush();
   staging_nbytes_in_cmd_ = 0;
 }
 

backends/vulkan/runtime/graph/ComputeGraph.h

@@ -821,8 +821,7 @@ class ComputeGraph final {
 
   /*
    * Submits the current command buffer in the Context to the GPU for execution,
-   * and wait for it to complete before returning. This function will also flush
-   * the Context after execution.
+   * and wait for it to complete before returning.
    */
   void submit_current_cmd_and_wait(const bool final_use = false);