Remove unnecessary aligned memory check when __SSE__ is used

core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c

 /*
  * The copyright in this software is being made available under the 2-clauses 
  * BSD License, included below. This software may be subject to other third 
  * party and contributor rights, including patent rights, and no such rights
  * are granted under this license.
  *
  * Copyright (c) 2002-2014, Universite catholique de Louvain (UCL), Belgium
  * Copyright (c) 2002-2014, Professor Benoit Macq
  * Copyright (c) 2001-2003, David Janssens
  * Copyright (c) 2002-2003, Yannick Verschueren
@@ skipping 132 matching lines @@
 /* Inverse irreversible MCT. */
 /* </summary> */
 void opj_mct_decode_real(
                 OPJ_FLOAT32* restrict c0,
                 OPJ_FLOAT32* restrict c1,
                 OPJ_FLOAT32* restrict c2,
                 OPJ_UINT32 n)
 {
         OPJ_UINT32 i;
 #ifdef __SSE__
-        // Mantis BUGID: 0056291. The address must be 16-byte aligned.
-        // TestFile: fuzz-signal_sigsegv_6e9e7f_5076_5265.pdf
-        if ((OPJ_UINT32)c0 % 16 == 0 && (OPJ_UINT32)c1 % 16 == 0 && (OPJ_UINT32)c2 % 16 == 0){
-                __m128 vrv, vgu, vgv, vbu;
-                vrv = _mm_set1_ps(1.402f);
-                vgu = _mm_set1_ps(0.34413f);
-                vgv = _mm_set1_ps(0.71414f);
-                vbu = _mm_set1_ps(1.772f);
-                for (i = 0; i < (n >> 3); ++i) {
-                        __m128 vy, vu, vv;
-                        __m128 vr, vg, vb;
+    __m128 vrv, vgu, vgv, vbu;
+    vrv = _mm_set1_ps(1.402f);
+    vgu = _mm_set1_ps(0.34413f);
+    vgv = _mm_set1_ps(0.71414f);
+    vbu = _mm_set1_ps(1.772f);
+    for (i = 0; i < (n >> 3); ++i) {
+        __m128 vy, vu, vv;
+        __m128 vr, vg, vb;
 
-                        vy = _mm_load_ps(c0);
-                        vu = _mm_load_ps(c1);
-                        vv = _mm_load_ps(c2);
-                        vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
-                        vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv));
-                        vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
-                        _mm_store_ps(c0, vr);
-                        _mm_store_ps(c1, vg);
-                        _mm_store_ps(c2, vb);
-                        c0 += 4;
-                        c1 += 4;
-                        c2 += 4;
+        vy = _mm_load_ps(c0);
+        vu = _mm_load_ps(c1);
+        vv = _mm_load_ps(c2);
+        vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
+        vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv));
+        vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
+        _mm_store_ps(c0, vr);
+        _mm_store_ps(c1, vg);
+        _mm_store_ps(c2, vb);
+        c0 += 4;
+        c1 += 4;
+        c2 += 4;
 
-                        vy = _mm_load_ps(c0);
-                        vu = _mm_load_ps(c1);
-                        vv = _mm_load_ps(c2);
-                        vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
-                        vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv));
-                        vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
-                        _mm_store_ps(c0, vr);
-                        _mm_store_ps(c1, vg);
-                        _mm_store_ps(c2, vb);
-                        c0 += 4;
-                        c1 += 4;
-                        c2 += 4;
-                }
-                n &= 7;
-        } else {
-                for (i = 0; i < n; ++i) {
-                        OPJ_FLOAT32 y = c0[i];
-                        OPJ_FLOAT32 u = c1[i];
-                        OPJ_FLOAT32 v = c2[i];
-                        OPJ_FLOAT32 r = y + (v * 1.402f);
-                        OPJ_FLOAT32 g = y - (u * 0.34413f) - (v * (0.71414f));
-                        OPJ_FLOAT32 b = y + (u * 1.772f);
-                        c0[i] = r;
-                        c1[i] = g;
-                        c2[i] = b;
-                }
-        }
+        vy = _mm_load_ps(c0);
+        vu = _mm_load_ps(c1);
+        vv = _mm_load_ps(c2);
+        vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
+        vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv));
+        vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
+        _mm_store_ps(c0, vr);
+        _mm_store_ps(c1, vg);
+        _mm_store_ps(c2, vb);
+        c0 += 4;
+        c1 += 4;
+        c2 += 4;
+    }
+    n &= 7;
+
 #endif
         for(i = 0; i < n; ++i) {
                 OPJ_FLOAT32 y = c0[i];
                 OPJ_FLOAT32 u = c1[i];
                 OPJ_FLOAT32 v = c2[i];
                 OPJ_FLOAT32 r = y + (v * 1.402f);
                 OPJ_FLOAT32 g = y - (u * 0.34413f) - (v * (0.71414f));
                 OPJ_FLOAT32 b = y + (u * 1.772f);
                 c0[i] = r;
                 c1[i] = g;
@@ skipping 117 matching lines @@
                 lIndex = i;
 
                 for     (j=0;j<pNbComps;++j) {
                         lCurrentValue = lMatrix[lIndex];
                         lIndex += pNbComps;
                         lNorms[i] += lCurrentValue * lCurrentValue;
                 }
                 lNorms[i] = sqrt(lNorms[i]);
         }
 }