Merge pull request #25984 from fengyuentau:imgproc/warpaffine_opt

imgproc: add optimized warpAffine kernels for 8U/16U/32F + C1/C3/C4 inputs #25984

Merge wtih https://github.com/opencv/opencv_extra/pull/1198.
Merge with https://github.com/opencv/opencv_contrib/pull/3787.


### 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
- [x] 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/include/opencv2/core/hal/intrin_neon.hpp

@@ -2228,9 +2228,7 @@ inline v_int16x8 v_round(const v_float16x8 &a)
 
 inline v_int16x8 v_floor(const v_float16x8 &a)
 {
-    int16x8_t a1 = vcvtq_s16_f16(a.val);
-    uint16x8_t mask = vcgtq_f16(vcvtq_f16_s16(a1), a.val);
-    return v_int16x8(vaddq_s16(a1, vreinterpretq_s16_u16(mask)));
+    return v_int16x8(vcvtmq_s16_f16(a.val));
 }
 
 inline v_int16x8 v_ceil(const v_float16x8 &a)
@@ -2271,9 +2269,13 @@ inline v_int32x4 v_round(const v_float32x4& a)
 #endif
 inline v_int32x4 v_floor(const v_float32x4& a)
 {
+#if __ARM_ARCH > 7
+    return v_int32x4(vcvtmq_s32_f32(a.val));
+#else
     int32x4_t a1 = vcvtq_s32_f32(a.val);
     uint32x4_t mask = vcgtq_f32(vcvtq_f32_s32(a1), a.val);
     return v_int32x4(vaddq_s32(a1, vreinterpretq_s32_u32(mask)));
+#endif
 }
 
 inline v_int32x4 v_ceil(const v_float32x4& a)