Skip to content

Commit 8646058

Browse files
twhuang-utahtwhuang-utah
committed
updated pages
1 parent be87b0f commit 8646058

5 files changed

Lines changed: 26 additions & 5 deletions

File tree

‎README.md‎

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -214,9 +214,12 @@ cond.precede(cond, stop);
214214
Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.
215215
216216
```cpp
217-
// saxpy kernel
218-
__global__ void saxpy(size_t N, float alpha, float* dx, float* dy);
219-
217+
__global__ void saxpy(size_t N, float alpha, float* dx, float* dy) {
218+
int i = blockIdx.x*blockDim.x + threadIdx.x;
219+
if (i < n) {
220+
y[i] = a*x[i] + y[i];
221+
}
222+
}
220223
tf::Task cudaflow = taskflow.emplace([&](tf::cudaFlow& cf) {
221224
222225
// data copy tasks

‎docs/index.html‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -283,7 +283,13 @@ <h3>Contents</h3>
283283
</g>
284284
</g>
285285
</svg>
286-
</div></section><section id="QuickStartOffloadTasksToGPU"><h2><a href="#QuickStartOffloadTasksToGPU">Offload Tasks to a GPU</a></h2><p>Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.</p><pre class="m-code"><span class="n">tf</span><span class="o">::</span><span class="n">Task</span> <span class="n">cudaflow</span> <span class="o">=</span> <span class="n">taskflow</span><span class="p">.</span><span class="n">emplace</span><span class="p">([</span><span class="o">&amp;</span><span class="p">](</span><span class="n">tf</span><span class="o">::</span><span class="n">cudaFlow</span><span class="o">&amp;</span> <span class="n">cf</span><span class="p">)</span> <span class="p">{</span>
286+
</div></section><section id="QuickStartOffloadTasksToGPU"><h2><a href="#QuickStartOffloadTasksToGPU">Offload Tasks to a GPU</a></h2><p>Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.</p><pre class="m-code"><span class="n">__global__</span> <span class="kt">void</span> <span class="n">saxpy</span><span class="p">(</span><span class="kt">int</span> <span class="n">n</span><span class="p">,</span> <span class="kt">float</span> <span class="n">a</span><span class="p">,</span> <span class="kt">float</span> <span class="o">*</span><span class="n">x</span><span class="p">,</span> <span class="kt">float</span> <span class="o">*</span><span class="n">y</span><span class="p">)</span> <span class="p">{</span>
287+
<span class="kt">int</span> <span class="n">i</span> <span class="o">=</span> <span class="n">blockIdx</span><span class="p">.</span><span class="n">x</span><span class="o">*</span><span class="n">blockDim</span><span class="p">.</span><span class="n">x</span> <span class="o">+</span> <span class="n">threadIdx</span><span class="p">.</span><span class="n">x</span><span class="p">;</span>
288+
<span class="k">if</span> <span class="p">(</span><span class="n">i</span> <span class="o">&lt;</span> <span class="n">n</span><span class="p">)</span> <span class="p">{</span>
289+
<span class="n">y</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">a</span><span class="o">*</span><span class="n">x</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="n">y</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
290+
<span class="p">}</span>
291+
<span class="p">}</span>
292+
<span class="n">tf</span><span class="o">::</span><span class="n">Task</span> <span class="n">cudaflow</span> <span class="o">=</span> <span class="n">taskflow</span><span class="p">.</span><span class="n">emplace</span><span class="p">([</span><span class="o">&amp;</span><span class="p">](</span><span class="n">tf</span><span class="o">::</span><span class="n">cudaFlow</span><span class="o">&amp;</span> <span class="n">cf</span><span class="p">)</span> <span class="p">{</span>
287293
<span class="n">tf</span><span class="o">::</span><span class="n">cudaTask</span> <span class="n">h2d_x</span> <span class="o">=</span> <span class="n">cf</span><span class="p">.</span><span class="n">copy</span><span class="p">(</span><span class="n">dx</span><span class="p">,</span> <span class="n">hx</span><span class="p">.</span><span class="n">data</span><span class="p">(),</span> <span class="n">N</span><span class="p">).</span><span class="n">name</span><span class="p">(</span><span class="s">&quot;h2d_x&quot;</span><span class="p">);</span>
288294
<span class="n">tf</span><span class="o">::</span><span class="n">cudaTask</span> <span class="n">h2d_y</span> <span class="o">=</span> <span class="n">cf</span><span class="p">.</span><span class="n">copy</span><span class="p">(</span><span class="n">dy</span><span class="p">,</span> <span class="n">hy</span><span class="p">.</span><span class="n">data</span><span class="p">(),</span> <span class="n">N</span><span class="p">).</span><span class="n">name</span><span class="p">(</span><span class="s">&quot;h2d_y&quot;</span><span class="p">);</span>
289295
<span class="n">tf</span><span class="o">::</span><span class="n">cudaTask</span> <span class="n">d2h_x</span> <span class="o">=</span> <span class="n">cf</span><span class="p">.</span><span class="n">copy</span><span class="p">(</span><span class="n">hx</span><span class="p">.</span><span class="n">data</span><span class="p">(),</span> <span class="n">dx</span><span class="p">,</span> <span class="n">N</span><span class="p">).</span><span class="n">name</span><span class="p">(</span><span class="s">&quot;d2h_x&quot;</span><span class="p">);</span>

‎docs/m.math.cache‎

0 Bytes
Binary file not shown.

‎docs/xml/indexpage.xml‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,13 @@
7979
</para></sect1>
8080
<sect1 id="index_1QuickStartOffloadTasksToGPU">
8181
<title>Offload Tasks to a GPU</title>
82-
<para>Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.</para><para><programlisting filename=".cpp"><codeline><highlight class="normal"><ref refid="classtf_1_1Task" kindref="compound">tf::Task</ref><sp/>cudaflow<sp/>=<sp/>taskflow.<ref refid="classtf_1_1FlowBuilder_1a60d7a666cab71ecfa3010b2efb0d6b57" kindref="member">emplace</ref>([&amp;](<ref refid="classtf_1_1cudaFlow" kindref="compound">tf::cudaFlow</ref>&amp;<sp/>cf)<sp/>{</highlight></codeline>
82+
<para>Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.</para><para><programlisting filename=".cpp"><codeline><highlight class="normal">__global__<sp/></highlight><highlight class="keywordtype">void</highlight><highlight class="normal"><sp/>saxpy(</highlight><highlight class="keywordtype">int</highlight><highlight class="normal"><sp/>n,<sp/></highlight><highlight class="keywordtype">float</highlight><highlight class="normal"><sp/>a,<sp/></highlight><highlight class="keywordtype">float</highlight><highlight class="normal"><sp/>*x,<sp/></highlight><highlight class="keywordtype">float</highlight><highlight class="normal"><sp/>*y)<sp/>{</highlight></codeline>
83+
<codeline><highlight class="normal"><sp/><sp/></highlight><highlight class="keywordtype">int</highlight><highlight class="normal"><sp/>i<sp/>=<sp/>blockIdx.x*blockDim.x<sp/>+<sp/>threadIdx.x;</highlight></codeline>
84+
<codeline><highlight class="normal"><sp/><sp/></highlight><highlight class="keywordflow">if</highlight><highlight class="normal"><sp/>(i<sp/>&lt;<sp/>n)<sp/>{</highlight></codeline>
85+
<codeline><highlight class="normal"><sp/><sp/><sp/><sp/>y[i]<sp/>=<sp/>a*x[i]<sp/>+<sp/>y[i];</highlight></codeline>
86+
<codeline><highlight class="normal"><sp/><sp/>}</highlight></codeline>
87+
<codeline><highlight class="normal">}</highlight></codeline>
88+
<codeline><highlight class="normal"><ref refid="classtf_1_1Task" kindref="compound">tf::Task</ref><sp/>cudaflow<sp/>=<sp/>taskflow.<ref refid="classtf_1_1FlowBuilder_1a60d7a666cab71ecfa3010b2efb0d6b57" kindref="member">emplace</ref>([&amp;](<ref refid="classtf_1_1cudaFlow" kindref="compound">tf::cudaFlow</ref>&amp;<sp/>cf)<sp/>{</highlight></codeline>
8389
<codeline><highlight class="normal"><sp/><sp/><ref refid="classtf_1_1cudaTask" kindref="compound">tf::cudaTask</ref><sp/>h2d_x<sp/>=<sp/>cf.<ref refid="classtf_1_1cudaFlow_1af03e04771b655f9e629eb4c22e19b19f" kindref="member">copy</ref>(dx,<sp/>hx.data(),<sp/>N).name(</highlight><highlight class="stringliteral">&quot;h2d_x&quot;</highlight><highlight class="normal">);</highlight></codeline>
8490
<codeline><highlight class="normal"><sp/><sp/><ref refid="classtf_1_1cudaTask" kindref="compound">tf::cudaTask</ref><sp/>h2d_y<sp/>=<sp/>cf.<ref refid="classtf_1_1cudaFlow_1af03e04771b655f9e629eb4c22e19b19f" kindref="member">copy</ref>(dy,<sp/>hy.data(),<sp/>N).name(</highlight><highlight class="stringliteral">&quot;h2d_y&quot;</highlight><highlight class="normal">);</highlight></codeline>
8591
<codeline><highlight class="normal"><sp/><sp/><ref refid="classtf_1_1cudaTask" kindref="compound">tf::cudaTask</ref><sp/>d2h_x<sp/>=<sp/>cf.<ref refid="classtf_1_1cudaFlow_1af03e04771b655f9e629eb4c22e19b19f" kindref="member">copy</ref>(hx.data(),<sp/>dx,<sp/>N).name(</highlight><highlight class="stringliteral">&quot;d2h_x&quot;</highlight><highlight class="normal">);</highlight></codeline>

‎doxygen/QuickStart.dox‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -124,6 +124,12 @@ cond.precede(cond, stop); // moves on to 'cond' on returning 0, or 'stop' on 1
124124
%Taskflow supports GPU tasking for you to accelerate a wide range of scientific computing applications by harnessing the power of CPU-GPU collaborative computing using CUDA.
125125

126126
@code{.cpp}
127+
__global__ void saxpy(int n, float a, float *x, float *y) {
128+
int i = blockIdx.x*blockDim.x + threadIdx.x;
129+
if (i < n) {
130+
y[i] = a*x[i] + y[i];
131+
}
132+
}
127133
tf::Task cudaflow = taskflow.emplace([&](tf::cudaFlow& cf) {
128134
tf::cudaTask h2d_x = cf.copy(dx, hx.data(), N).name("h2d_x");
129135
tf::cudaTask h2d_y = cf.copy(dy, hy.data(), N).name("h2d_y");

0 commit comments

Comments
 (0)