updated documents to include latest information (#8492)

Signed-off-by: Manoj Takasi <[email protected]>
Co-authored-by: Manoj Takasi <[email protected]>

master/html/_sources/xrt_native_apis.rst.txt

@@ -791,6 +791,42 @@ The following code shows a sample example with a single input/output GMIO/Extern
            auto xrt::aie::buffer out_buffer  = xrt::aie::buffer(device, uuid,"gr.out1");
            out_buffer.sync(out_bo, XCL_BO_SYNC_BO_AIE_TO_GMIO, SIZE * sizeof(float),0); 
 
+This class has overloaded member function ``xrt::aie::buffer::async(...)`` that can be used to initiate an asynchronize operation to synchronize the xrt::bo buffer object
+
+xrt::aie::buffer::async(xrt::bo bo, ...) initiate an asynchronize operation between xrt::aie::buffer (GMIO/External Buffer) & xrt::bo (Global Memory)
+
+xrt::aie::buffer::async(xrt::bo ping,xrt::bo pong, ...) initiate an asynchronize operation between xrt::aie::buffer (GMIO/External Buffer) & ping/pong xrt::bo objects
+
+xrt::aie::buffer::wait() waits for the asynchronize operation to complete
+
+The following code shows a sample example with a single input/output GMIO/External Buffer. Data gets transferred from global buffer "in_bo" to "gr.in1"
+
+.. code:: c++
+        :number-lines: 1
+
+           auto device = xrt::aie::device(0);
+           auto uuid = device.load_xclbin(xclbin-filename);
+
+           // Create Buffer in DDR/Global memory & prepare input
+           auto in_bo  = xrt::aie::bo (device, SIZE * sizeof (float), 0, 0);
+           auto inp_bo_map = in_bo.map<float *>(); 
+           std::copy(my_float_array,my_float_array+SIZE,inp_bo_map);
+
+           // Create Buffer in DDR/Global memory to store output
+           auto out_bo  = xrt::aie::bo (device, SIZE * sizeof (float), 0, 0);
+           auto out_bo_map = out_bo.map<float *>();
+
+           // create GMIO/External Buffer object for input & sync from in_bo
+           auto xrt::aie::buffer in_buffer = xrt::aie::buffer(device, uuid,"gr.in1");
+           in_buffer.async(in_bo, XCL_BO_SYNC_BO_GMIO_TO_AIE, SIZE * sizeof(float),0); 
+
+           //run your graphs which uses output GMIO/External buffer
+
+           // create GMIO/External Buffer object for output & sync from out_bo
+           auto xrt::aie::buffer out_buffer  = xrt::aie::buffer(device, uuid,"gr.out1");
+           out_buffer.async(out_bo, XCL_BO_SYNC_BO_AIE_TO_GMIO, SIZE * sizeof(float),0); 
+           out_buffer.wait();
+
 Ping Pong buffers
 ~~~~~~~~~~~~~~~~~
 The following code shows ping-pong buffer example.This shows an example with a ping/ping buffer being set on one of External buffer

master/html/index.html

@@ -331,4 +331,4 @@ <h1>Xilinx® Runtime (XRT) Architecture<a class="headerlink" href="#xilinx-runti
 
 
 </body>
-</html>
+</html>

master/html/xrt_native_apis.html

@@ -884,6 +884,35 @@ <h2>GMIOs &amp; External Buffers<a class="headerlink" href="#gmios-external-buff
 <span class="linenos">21</span><span class="w">   </span><span class="n">out_buffer</span><span class="p">.</span><span class="n">sync</span><span class="p">(</span><span class="n">out_bo</span><span class="p">,</span><span class="w"> </span><span class="n">XCL_BO_SYNC_BO_AIE_TO_GMIO</span><span class="p">,</span><span class="w"> </span><span class="n">SIZE</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">),</span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
 </pre></div>
 </div>
+<p>This class has overloaded member function <code class="docutils literal notranslate"><span class="pre">xrt::aie::buffer::async(...)</span></code> that can be used to initiate an asynchronize operation to synchronize the xrt::bo buffer object</p>
+<p>xrt::aie::buffer::async(xrt::bo bo, …) initiate an asynchronize operation between xrt::aie::buffer (GMIO/External Buffer) &amp; xrt::bo (Global Memory)</p>
+<p>xrt::aie::buffer::async(xrt::bo ping,xrt::bo pong, …) initiate an asynchronize operation between xrt::aie::buffer (GMIO/External Buffer) &amp; ping/pong xrt::bo objects</p>
+<p>xrt::aie::buffer::wait() waits for the asynchronize operation to complete</p>
+<p>The following code shows a sample example with a single input/output GMIO/External Buffer. Data gets transferred from global buffer “in_bo” to “gr.in1”</p>
+<div class="highlight-c++ notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">device</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">device</span><span class="p">(</span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
+<span class="linenos"> 2</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">uuid</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">device</span><span class="p">.</span><span class="n">load_xclbin</span><span class="p">(</span><span class="n">xclbin</span><span class="o">-</span><span class="n">filename</span><span class="p">);</span><span class="w"></span>
+<span class="linenos"> 3</span>
+<span class="linenos"> 4</span><span class="w">   </span><span class="c1">// Create Buffer in DDR/Global memory &amp; prepare input</span>
+<span class="linenos"> 5</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">in_bo</span><span class="w">  </span><span class="o">=</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">bo</span><span class="w"> </span><span class="p">(</span><span class="n">device</span><span class="p">,</span><span class="w"> </span><span class="n">SIZE</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="p">),</span><span class="w"> </span><span class="mi">0</span><span class="p">,</span><span class="w"> </span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
+<span class="linenos"> 6</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">inp_bo_map</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">in_bo</span><span class="p">.</span><span class="n">map</span><span class="o">&lt;</span><span class="kt">float</span><span class="w"> </span><span class="o">*&gt;</span><span class="p">();</span><span class="w"></span>
+<span class="linenos"> 7</span><span class="w">   </span><span class="n">std</span><span class="o">::</span><span class="n">copy</span><span class="p">(</span><span class="n">my_float_array</span><span class="p">,</span><span class="n">my_float_array</span><span class="o">+</span><span class="n">SIZE</span><span class="p">,</span><span class="n">inp_bo_map</span><span class="p">);</span><span class="w"></span>
+<span class="linenos"> 8</span>
+<span class="linenos"> 9</span><span class="w">   </span><span class="c1">// Create Buffer in DDR/Global memory to store output</span>
+<span class="linenos">10</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">out_bo</span><span class="w">  </span><span class="o">=</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">bo</span><span class="w"> </span><span class="p">(</span><span class="n">device</span><span class="p">,</span><span class="w"> </span><span class="n">SIZE</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="p">),</span><span class="w"> </span><span class="mi">0</span><span class="p">,</span><span class="w"> </span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
+<span class="linenos">11</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">out_bo_map</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">out_bo</span><span class="p">.</span><span class="n">map</span><span class="o">&lt;</span><span class="kt">float</span><span class="w"> </span><span class="o">*&gt;</span><span class="p">();</span><span class="w"></span>
+<span class="linenos">12</span>
+<span class="linenos">13</span><span class="w">   </span><span class="c1">// create GMIO/External Buffer object for input &amp; sync from in_bo</span>
+<span class="linenos">14</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">buffer</span><span class="w"> </span><span class="n">in_buffer</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">buffer</span><span class="p">(</span><span class="n">device</span><span class="p">,</span><span class="w"> </span><span class="n">uuid</span><span class="p">,</span><span class="s">&quot;gr.in1&quot;</span><span class="p">);</span><span class="w"></span>
+<span class="linenos">15</span><span class="w">   </span><span class="n">in_buffer</span><span class="p">.</span><span class="n">async</span><span class="p">(</span><span class="n">in_bo</span><span class="p">,</span><span class="w"> </span><span class="n">XCL_BO_SYNC_BO_GMIO_TO_AIE</span><span class="p">,</span><span class="w"> </span><span class="n">SIZE</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">),</span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
+<span class="linenos">16</span>
+<span class="linenos">17</span><span class="w">   </span><span class="c1">//run your graphs which uses output GMIO/External buffer</span>
+<span class="linenos">18</span>
+<span class="linenos">19</span><span class="w">   </span><span class="c1">// create GMIO/External Buffer object for output &amp; sync from out_bo</span>
+<span class="linenos">20</span><span class="w">   </span><span class="k">auto</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">buffer</span><span class="w"> </span><span class="n">out_buffer</span><span class="w">  </span><span class="o">=</span><span class="w"> </span><span class="n">xrt</span><span class="o">::</span><span class="n">aie</span><span class="o">::</span><span class="n">buffer</span><span class="p">(</span><span class="n">device</span><span class="p">,</span><span class="w"> </span><span class="n">uuid</span><span class="p">,</span><span class="s">&quot;gr.out1&quot;</span><span class="p">);</span><span class="w"></span>
+<span class="linenos">21</span><span class="w">   </span><span class="n">out_buffer</span><span class="p">.</span><span class="n">async</span><span class="p">(</span><span class="n">out_bo</span><span class="p">,</span><span class="w"> </span><span class="n">XCL_BO_SYNC_BO_AIE_TO_GMIO</span><span class="p">,</span><span class="w"> </span><span class="n">SIZE</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">),</span><span class="mi">0</span><span class="p">);</span><span class="w"></span>
+<span class="linenos">22</span><span class="w">   </span><span class="n">out_buffer</span><span class="p">.</span><span class="n">wait</span><span class="p">();</span><span class="w"></span>
+</pre></div>
+</div>
 <section id="ping-pong-buffers">
 <h3>Ping Pong buffers<a class="headerlink" href="#ping-pong-buffers" title="Permalink to this headline">¶</a></h3>
 <p>The following code shows ping-pong buffer example.This shows an example with a ping/ping buffer being set on one of External buffer</p>