dnn_backend_native_layer_conv2d.c:Add mutithread function

Use pthread to multithread dnn_execute_layer_conv2d.
Can be tested with command "./ffmpeg_g -i input.png -vf \
format=yuvj420p,dnn_processing=dnn_backend=native:model= \
espcn.model:input=x:output=y:options=conv2d_threads=23 \
 -y sr_native.jpg -benchmark"

before patch: utime=11.238s stime=0.005s rtime=11.248s
after patch:  utime=20.817s stime=0.047s rtime=1.051s
on my 3900X 12c24t @4.2GHz

About the increase of utime, it's because that CPU HyperThreading
technology makes logical cores twice of physical cores while cpu's
counting performance improves less than double. And utime sums
all cpu's logical cores' runtime. As a result, using threads num
near cpu's logical core's number will double utime, while reduce
rtime less than half for HyperThreading CPUs.

Signed-off-by: Xu Jun <xujunzz@sjtu.edu.cn>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>

1 files changed, 12 insertions, 2 deletions

diff --git a/tests/dnn/dnn-layer-conv2d-test.c b/tests/dnn/dnn-layer-conv2d-test.c
index 836839cc64..378a05eafc 100644
--- a/tests/dnn/dnn-layer-conv2d-test.c
+++ b/tests/dnn/dnn-layer-conv2d-test.c
@@ -25,6 +25,8 @@
 
 #define EPSON 0.00001
 
+extern const AVClass dnn_native_class;
+
 static int test_with_same_dilate(void)
 {
     // the input data and expected data are generated with below python code.
@@ -96,6 +98,10 @@ static int test_with_same_dilate(void)
     };
     float bias[2] = { -1.6574852, -0.72915393 };
 
+    NativeContext ctx;
+    ctx.class = &dnn_native_class;
+    ctx.options.conv2d_threads = 1;
+
     params.activation = TANH;
     params.has_bias = 1;
     params.biases = bias;
@@ -114,7 +120,7 @@ static int test_with_same_dilate(void)
     operands[1].data = NULL;
 
     input_indexes[0] = 0;
-    dnn_execute_layer_conv2d(operands, input_indexes, 1, &params, NULL);
+    dnn_execute_layer_conv2d(operands, input_indexes, 1, &params, &ctx);
 
     output = operands[1].data;
     for (int i = 0; i < sizeof(expected_output) / sizeof(float); i++) {
@@ -196,6 +202,10 @@ static int test_with_valid(void)
     };
     float bias[2] = { -0.4773722, -0.19620377 };
 
+    NativeContext ctx;
+    ctx.class = &dnn_native_class;
+    ctx.options.conv2d_threads = 1;
+
     params.activation = TANH;
     params.has_bias = 1;
     params.biases = bias;
@@ -214,7 +224,7 @@ static int test_with_valid(void)
     operands[1].data = NULL;
 
     input_indexes[0] = 0;
-    dnn_execute_layer_conv2d(operands, input_indexes, 1, &params, NULL);
+    dnn_execute_layer_conv2d(operands, input_indexes, 1, &params, &ctx);
 
     output = operands[1].data;
     for (int i = 0; i < sizeof(expected_output) / sizeof(float); i++) {