Updated docs for 0.4.0 release

README.md

@@ -95,22 +95,22 @@ int main() {
         { tensorA, tensorB }, 
         std::vector<char>(shader.begin(), shader.end()));
 
+    // 4.1. Before submitting sequence batch we wait for the async operation
+    mgr.evalOpAwaitDefault();
+
     // 5. Create managed sequence to submit batch operations to the CPU
     std::shared_ptr<kp::Sequence> sq = mgr.getOrCreateManagedSequence("seq").lock();
 
-    // Explicitly begin recording batch commands
+    // 5.1. Explicitly begin recording batch commands
     sq->begin();
 
-    // Record batch commands
+    // 5.2. Record batch commands
     sq->record<kp::OpTensorSyncLocal({ tensorA });
     sq->record<kp::OpTensorSyncLocal({ tensorB });
 
-    // Explicitly stop recording batch commands
+    // 5.3. Explicitly stop recording batch commands
     sq->end();
 
-    // Before submitting sequence batch we wait for the previous async operation
-    mgr.evalOpAwaitDefault();
-
     // 6. Map data back to host by running the sequence of batch operations
     sq->eval();
 
@@ -134,6 +134,7 @@ int main() {
 ### End-to-end examples
 
 * [Machine Learning Logistic Regression Implementation](https://towardsdatascience.com/machine-learning-and-data-processing-in-the-gpu-with-vulkan-kompute-c9350e5e5d3a)
+* [Parallelizing GPU-intensive Workloads via Multi-Queue Operations](https://towardsdatascience.com/parallelizing-heavy-gpu-workloads-via-multi-queue-operations-50a38b15a1dc)
 * [Android NDK Mobile Kompute ML Application](https://towardsdatascience.com/gpu-accelerated-machine-learning-in-your-mobile-applications-using-the-android-ndk-vulkan-kompute-1e9da37b7617)
 * [Game Development Kompute ML in Godot Engine](https://towardsdatascience.com/supercharging-game-development-with-gpu-accelerated-ml-using-vulkan-kompute-the-godot-game-engine-4e75a84ea9f0)
 

docs/conf.py

@@ -22,7 +22,7 @@ copyright = '2020, The Institute for Ethical AI & Machine Learning'
 author = 'Alejandro Saucedo'
 
 # The full version, including alpha/beta/rc tags
-release = '0.3.2'
+release = '0.4.0'
 
 
 # -- General configuration ---------------------------------------------------

docs/overview/advanced-examples.rst

@@ -23,6 +23,7 @@ End-to-end examples
 
 
 * `Machine Learning Logistic Regression Implementation <https://towardsdatascience.com/machine-learning-and-data-processing-in-the-gpu-with-vulkan-kompute-c9350e5e5d3a>`_
+* `Parallelizing GPU-intensive Workloads via Multi-Queue Operations [https://towardsdatascience.com/parallelizing-heavy-gpu-workloads-via-multi-queue-operations-50a38b15a1dc>`_
 * `Android NDK Mobile Kompute ML Application <https://towardsdatascience.com/gpu-accelerated-machine-learning-in-your-mobile-applications-using-the-android-ndk-vulkan-kompute-1e9da37b7617>`_
 * `Game Development Kompute ML in Godot Engine <https://towardsdatascience.com/supercharging-game-development-with-gpu-accelerated-ml-using-vulkan-kompute-the-godot-game-engine-4e75a84ea9f0>`_
 
@@ -69,11 +70,7 @@ Pass compute shader data in glsl/hlsl text or compiled SPIR-V format (or as path
             std::vector<char>(shader.begin(), shader.end()));
 
         // Sync the GPU memory back to the local tensor
-        // You can run the job asynchronously with the Async function
-        mgr.evalOpAsyncDefault<kp::OpTensorSyncLocal>({ tensorA, tensorB });
-
-        // Await for the asynchonous default sequence to finish
-        mgr.evalOpAwaitDefault();
+        mgr.evalOpDefault<kp::OpTensorSyncLocal>({ tensorA, tensorB });
 
         // Prints the output which is A: { 0, 1, 2 } B: { 3, 4, 5 }
         std::cout << fmt::format("A: {}, B: {}", 

docs/overview/async-parallel.rst

@@ -11,6 +11,8 @@ In this section we will cover the following points:
 * Asynchronous operation submission
 * Parallel processing of operations
 
+You can also find the published `blog post on the topic using Kompute <https://towardsdatascience.com/parallelizing-heavy-gpu-workloads-via-multi-queue-operations-50a38b15a1dc>`_, which covers the points discussed in this section further.
+
 Below is the architecture we'll be covering further in the parallel operations section through command submission across multiple family queues.
 
 .. image:: ../images/queue-allocation.jpg