Merge pull request #29335 from amd:fast_norm_simd

core: SIMD optimizations for norm, distance and Hamming APIs. (Improves ORB & BRISK) #29335

Generic universal-intrinsic kernels (benefit all SIMD backends: NEON, AVX2, AVX-512, etc.), plus enabling wider dispatch for the norm module.

- hal::normHamming: cached-pointer dispatch (resolve once, no per-call dispatch chain or trace region) + vector popcount path. cv::norm(NORM_HAMMING) and binary-descriptor matching (BFMatcher ORB/BRISK/FREAK via cv::batchDistance).
- hal::normL2Sqr_ / normL1_: direct inlinable kernels with single-vector tail (cv::batchDistance / BFMatcher float L2/L1, cv::kmeans).
- cv::norm masked NORM_INF: deinterleave SIMD for multichannel + back-step tail.
- cv::norm(src1, src2, type, mask): SIMD masked norm-diff; INF is one templated kernel for all element types, plus uchar L1/L2 and int L1 kernels.
- Enable AVX512_SKX/AVX512_ICL dispatch for the norm module.
- features2d: add BFMatcher knnMatch perf tests (float L2/L1, binary Hamming).
- ORB and BRISK performance improved
### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

modules/core/src/stat.dispatch.cpp

@@ -1,6 +1,8 @@
 // This file is part of OpenCV project.
 // It is subject to the license terms in the LICENSE file found in the top-level directory
 // of this distribution and at http://opencv.org/license.html.
+//
+// Copyright (C) 2026, Advanced Micro Devices, Inc., all rights reserved.
 
 #include "precomp.hpp"
 
@@ -9,20 +11,26 @@
 
 namespace cv { namespace hal {
 
+// Resolve the SIMD implementation ONCE via a cached function pointer. normHamming
+// is called per-descriptor in hot matcher loops on short (32/64-byte) descriptors,
+// where a per-call dispatch chain + CV_INSTRUMENT_REGION dominate the cost.
+static NormHammingFunc getNormHammingFunc() {
+    CV_CPU_DISPATCH(getNormHammingFunc, (), CV_CPU_DISPATCH_MODES_ALL);
+}
+static NormHammingDiffFunc getNormHammingDiffFunc() {
+    CV_CPU_DISPATCH(getNormHammingDiffFunc, (), CV_CPU_DISPATCH_MODES_ALL);
+}
+
 int normHamming(const uchar* a, int n)
 {
-    CV_INSTRUMENT_REGION();
-
-    CV_CPU_DISPATCH(normHamming, (a, n),
-        CV_CPU_DISPATCH_MODES_ALL);
+    static const NormHammingFunc fn = getNormHammingFunc();
+    return fn(a, n);
 }
 
 int normHamming(const uchar* a, const uchar* b, int n)
 {
-    CV_INSTRUMENT_REGION();
-
-    CV_CPU_DISPATCH(normHamming, (a, b, n),
-        CV_CPU_DISPATCH_MODES_ALL);
+    static const NormHammingDiffFunc fn = getNormHammingDiffFunc();
+    return fn(a, b, n);
 }
 
 }} //cv::hal