Merge pull request #15371 from Wenzhao-Xiang:gsoc_2019

[GSoC 2019] Improve the performance of JavaScript version of OpenCV (OpenCV.js)

* [GSoC 2019]

Improve the performance of JavaScript version of OpenCV (OpenCV.js):
1. Create the base of OpenCV.js performance test:
     This perf test is based on benchmark.js(https://benchmarkjs.com). And first add `cvtColor`, `Resize`, `Threshold` into it.
2. Optimize the OpenCV.js performance by WASM threads:
     This optimization is based on Web Worker API and SharedArrayBuffer, so it can be only used in browser.
3. Optimize the OpenCV.js performance by WASM SIMD:
     Add WASM SIMD backend for OpenCV Universal Intrinsics. It's experimental as WASM SIMD is still in development.

* [GSoC2019] 

1. use short license header
2. fix documentation node issue
3. remove the unused `hasSIMD128()` api

* [GSoC2019]

1. fix emscripten define
2. use fallback function for f16

* [GSoC2019]

Fix rebase issue

modules/core/include/opencv2/core/cv_cpu_dispatch.h

@@ -157,6 +157,11 @@
 #  define CV_MSA 1
 #endif
 
+#ifdef __EMSCRIPTEN__
+#  define CV_WASM_SIMD 1
+#  include <wasm_simd128.h>
+#endif
+
 #endif // CV_ENABLE_INTRINSICS && !CV_DISABLE_OPTIMIZATION && !__CUDACC__
 
 #if defined CV_CPU_COMPILE_AVX && !defined CV_CPU_BASELINE_COMPILE_AVX
@@ -328,3 +333,7 @@ struct VZeroUpperGuard {
 #ifndef CV_MSA
 #  define CV_MSA 0
 #endif
+
+#ifndef CV_WASM_SIMD
+#  define CV_WASM_SIMD 0
+#endif

modules/core/include/opencv2/core/hal/intrin.hpp

@@ -168,7 +168,7 @@ using namespace CV_CPU_OPTIMIZATION_HAL_NAMESPACE;
 #   undef CV_MSA
 #endif
 
-#if CV_SSE2 || CV_NEON || CV_VSX || CV_MSA
+#if CV_SSE2 || CV_NEON || CV_VSX || CV_MSA || CV_WASM_SIMD
 #define CV__SIMD_FORWARD 128
 #include "opencv2/core/hal/intrin_forward.hpp"
 #endif
@@ -190,6 +190,9 @@ using namespace CV_CPU_OPTIMIZATION_HAL_NAMESPACE;
 
 #include "opencv2/core/hal/intrin_msa.hpp"
 
+#elif CV_WASM_SIMD
+#include "opencv2/core/hal/intrin_wasm.hpp"
+
 #else
 
 #define CV_SIMD128_CPP 1

modules/core/src/mathfuncs_core.simd.hpp

@@ -31,6 +31,11 @@ using namespace cv;
 
 namespace {
 
+static const float atan2_p1 = 0.9997878412794807f*(float)(180/CV_PI);
+static const float atan2_p3 = -0.3258083974640975f*(float)(180/CV_PI);
+static const float atan2_p5 = 0.1555786518463281f*(float)(180/CV_PI);
+static const float atan2_p7 = -0.04432655554792128f*(float)(180/CV_PI);
+
 #ifdef __EMSCRIPTEN__
 static inline float atan_f32(float y, float x)
 {
@@ -42,11 +47,6 @@ static inline float atan_f32(float y, float x)
     return a; // range [0; 360)
 }
 #else
-static const float atan2_p1 = 0.9997878412794807f*(float)(180/CV_PI);
-static const float atan2_p3 = -0.3258083974640975f*(float)(180/CV_PI);
-static const float atan2_p5 = 0.1555786518463281f*(float)(180/CV_PI);
-static const float atan2_p7 = -0.04432655554792128f*(float)(180/CV_PI);
-
 static inline float atan_f32(float y, float x)
 {
     float ax = std::abs(x), ay = std::abs(y);

modules/core/src/parallel.cpp

@@ -54,7 +54,7 @@
 #endif
 
 #if defined __linux__ || defined __APPLE__ || defined __GLIBC__ \
-    || defined __HAIKU__
+    || defined __HAIKU__ || defined __EMSCRIPTEN__
     #include <unistd.h>
     #include <stdio.h>
     #include <sys/types.h>
@@ -793,7 +793,7 @@ int cv::getNumberOfCPUs(void)
 #elif defined __ANDROID__
     static int ncpus = getNumberOfCPUsImpl();
     return ncpus;
-#elif defined __linux__ || defined __GLIBC__ || defined __HAIKU__
+#elif defined __linux__ || defined __GLIBC__ || defined __HAIKU__ || defined __EMSCRIPTEN__
     return (int)sysconf( _SC_NPROCESSORS_ONLN );
 #elif defined __APPLE__
     int numCPU=0;