test NEON-optimized cv::threshold() on mobile device

edit

I have been writing some optimizations for the OpenCV's threshold function, for ARM devices (mobile phones). It should be working on both Android and iPhone.

However, I do not have a device to test it on, so I am looking for volunteers to give me a little help. If that motivates you more, I am planning to push it to the main OpenCV repo - and hope you guys will accept it

I am interested in code correctness, and if it happens to work as intended, some statistics for original/optimized performance. Do not forget to look at all scenarios.

If this patch format is a nonsense for you, the post here may help you more

Edit

I forgot to mention that you have to activate it by adding #define CV_USE_NEON somewhere at the top of the thresh.cpp function or as compile flag -DCV_USE_NEON

Patch 1/3. Update checkHardwareSupport()

From 5129091430a7423e5c07a4f3c845033adb8ccefe Mon Sep 17 00:00:00 2001
From: sammy <[email protected]>
Date: Tue, 31 Jul 2012 09:59:36 +0300
Subject: [PATCH 1/2] Update checkHardwareSupport and HWFeatures to support
 ARM NEON

---
 modules/core/include/opencv2/core/core_c.h |  3 +++
 modules/core/src/system.cpp                | 17 ++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/modules/core/include/opencv2/core/core_c.h b/modules/core/include/opencv2/core/core_c.h
index df763ab..bdfb879 100644
--- a/modules/core/include/opencv2/core/core_c.h
+++ b/modules/core/include/opencv2/core/core_c.h
@@ -1706,6 +1706,9 @@ CVAPI(double) cvGetTickFrequency( void );
 #define CV_CPU_SSE4_2  7
 #define CV_CPU_POPCNT  8
 #define CV_CPU_AVX    10
+
+#define CV_CPU_ARM_NEON 100
+
 #define CV_HARDWARE_MAX_FEATURE 255

 CVAPI(int) cvCheckHardwareSupport(int feature);
diff --git a/modules/core/src/system.cpp b/modules/core/src/system.cpp
index b8a4661..eeb2a58 100644
--- a/modules/core/src/system.cpp
+++ b/modules/core/src/system.cpp
@@ -176,7 +176,22 @@ struct HWFeatures
             f.have[CV_CPU_POPCNT] = (cpuid_data[2] & (1<<23)) != 0;
             f.have[CV_CPU_AVX]    = (cpuid_data[2] & (1<<28)) != 0;
         }
-
+       
+       // Android check
+       #if defined ANDROID
+       if (android_getCpuFamily() == ANDROID_CPU_FAMILY_ARM &&
+            (android_getCpuFeatures() & ANDROID_CPU_ARM_FEATURE_NEON) != 0)
+        {
+            f.have[CV_CPU_ARM_NEON] = 1;
+        }
+       #endif
+       // iOS check. Automatically activated by GCC/LLVM compiler option
+       #if define TARGET_OS_IPHONE 
+       #if define __ARM_NEON__
+       f.have[CV_CPU_ARM_NEON] = 1;
+       #endif
+       #endif
+       
         return f;
     }

-- 
1.7.11

Patch 2/3. threshold() optimizations

From 9f9e6e0a382b0ec2b5ddb3eedd27bcdf95af9763 Mon Sep 17 00:00:00 2001
From: sammy <[email protected]>
Date: Tue, 31 Jul 2012 10:02:35 +0300
Subject: [PATCH 2/2] NEON-accelerated threshold()

---
 modules/imgproc/src/thresh.cpp | 140 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 140 insertions(+)

diff --git a/modules/imgproc/src/thresh.cpp b/modules/imgproc/src/thresh.cpp
index 1fb4847..fb01852 100644
--- a/modules/imgproc/src/thresh.cpp
+++ b/modules/imgproc/src/thresh.cpp
@@ -42,6 +42,10 @@

 #include "precomp.hpp"

+#if defined CV_USE_NEON
+#include <arm_neon.h>
+#endif
+
 namespace cv
 {

@@ -226,6 +230,142 @@ thresh_8u( const Mat& _src, Mat& _dst, uchar thresh, uchar maxval, int type )
     }
 #endif

+#if CV_USE_NEON
+    if( checkHardwareSupport(CV_CPU_ARM_NEON) )
+    {
+       uint8x16_t thresh_u = vdupq_n_u8(thresh);
+        uint8x16_t maxval_ = vdupq_n_u8(maxval);
+       
+        j_scalar = roi.width & -8;
+
+        for( i = 0; i < roi.height; i++ )
+        {
+            const uchar ...