diff --git a/src/md_MAIN_013/md_MAIN_013.c b/src/md_MAIN_013/md_MAIN_013.c
index 6ebcd7f32..453a2fa03 100644
--- a/src/md_MAIN_013/md_MAIN_013.c
+++ b/src/md_MAIN_013/md_MAIN_013.c
@@ -305,7 +305,71 @@ void func_800CB510(void *arg0) {
 }
 
 
-INCLUDE_ASM("asm/md_MAIN_013/nonmatchings/md_MAIN_013", func_800CB56C);
+#include "common.h"
+
+void func_800CB56C(s32 arg0) {
+
+    typedef struct { s32 w[8]; } Blk20;
+
+    extern Blk20 D_800AE620;
+    extern void RotMatrixZ(s32 a0, void *a1);
+    extern void ApplyMatrixSV();
+    extern void MulMatrix0(s32 a0, void *a1, s32 a2);
+    extern void func_8012F14C(s32 a0, s32 a1, s32 a2);
+    extern s32 func_80128ED8(s32 param_1, s32 *param_2);
+    extern void func_80146C3C();
+
+    u16   vec[8];
+    Blk20 blk;
+
+    s32 ent;
+    s32 obj;
+    s32 ang;
+    register s32 ang2 __asm__("$4");
+
+    obj = *(s32 *)(arg0 + 0x20);
+    __asm__ __volatile__("" : : : "memory");
+    ent = *(s32 *)(arg0 + 0x34);
+    __asm__ __volatile__("" : : : "memory");
+    { register Blk20 *s __asm__("$5") = &D_800AE620; s32 t0, t1, t2;
+      __asm__ __volatile__("" : "=r"(s) : "0"(s));
+      t0 = s->w[0]; t1 = s->w[1]; t2 = s->w[2];
+      blk.w[0] = t0; blk.w[1] = t1; blk.w[2] = t2;
+      t0 = s->w[3]; t1 = s->w[4]; t2 = s->w[5];
+      blk.w[3] = t0; blk.w[4] = t1; blk.w[5] = t2;
+      t0 = s->w[6]; t1 = s->w[7];
+      blk.w[6] = t0; blk.w[7] = t1; }
+    ang = *(s16 *)(arg0 + 0x10);
+    { void *q = &blk; RotMatrixZ(ang, q); __asm__ __volatile__("" : "=r"(q)); }
+    vec[0] = *(s32 *)(arg0 + 0x30) << 2;
+    vec[1] = 0;
+    vec[2] = 0x30;
+    { void *q = &blk; ApplyMatrixSV(q, vec, vec); __asm__ __volatile__("" : "=r"(q)); }
+    ent += 0x38;
+    func_8012F14C(ent, (s32)vec, (s32)vec);
+    *(s16 *)(arg0 + 6)   = vec[0];
+    *(s16 *)(arg0 + 0xA) = vec[1];
+    ang2 = ang + 0x200;
+    __asm__ __volatile__("" : : : "memory");
+    *(s16 *)(arg0 + 0xE) = vec[2];
+    __asm__ __volatile__("" : : : "memory");
+    { register Blk20 *s __asm__("$7") = &D_800AE620;
+      s32 t0, t1; register s32 t2 __asm__("$6");
+      __asm__ __volatile__("" : "=r"(s) : "0"(s));
+      t0 = s->w[0]; t1 = s->w[1]; t2 = s->w[2];
+      blk.w[0] = t0; blk.w[1] = t1; blk.w[2] = t2;
+      t0 = s->w[3]; t1 = s->w[4]; t2 = s->w[5];
+      blk.w[3] = t0; blk.w[4] = t1; blk.w[5] = t2;
+      t0 = s->w[6]; t1 = s->w[7];
+      blk.w[6] = t0; blk.w[7] = t1; }
+    { void *q; __asm__ __volatile__("" : : : "memory"); q = &blk;
+      RotMatrixZ(ang2, q); __asm__ __volatile__("" : "=r"(q)); }
+    MulMatrix0(ent, &blk, arg0 + 0x38);
+    if (func_80128ED8(obj, (s32 *)(arg0 + 0x24)) != 0) {
+        ((void (*)(s32))func_80146C3C)(arg0);
+    }
+}
+
 
 void func_800CB6E4(void *arg0) {
     extern s32 func_80146A6C(s32, void *, s32, s32, s32, s32, s32);
diff --git a/src/ov_SC04_003/ov_SC04_003_jr_8017BEBC.c b/src/ov_SC04_003/ov_SC04_003_jr_8017BEBC.c
index 21aa93d54..029912acf 100644
--- a/src/ov_SC04_003/ov_SC04_003_jr_8017BEBC.c
+++ b/src/ov_SC04_003/ov_SC04_003_jr_8017BEBC.c
@@ -6016,7 +6016,91 @@ void func_80180E8C(u8 *a0)
 }
 
 
-INCLUDE_ASM("asm/ov_SC04_003/nonmatchings/ov_SC04_003_jr_8017BEBC", func_80180FB8);
+
+
+typedef struct { short a, b, c; } SV3_801802D0;
+typedef struct { s16 a, b, c, d; } SV4x_80183E2C;       /* 8-byte, align-2 quad of s16 */
+
+
+extern s32 D_80126B58;
+extern u16 D_80126B5E;
+extern u16 D_80126B62;
+extern u16 D_80126B66;
+
+void func_80180FB8(s32 arg0, s32 arg1) {
+    u16 w5e;
+    u16 p6;
+    u16 w66;
+    u16 pE;
+    s16 x;
+    s16 y;
+    s16 z;
+    s16 lim;
+    s32 wide;
+    s16 t1n;
+    s16 a3n;
+    register s32 d __asm__("6");
+    register s32 t1 __asm__("9");
+    register s32 a3 __asm__("7");
+
+    if (*(u16 *)&D_80126B58 == 0x1A) {
+        return;
+    }
+    w5e = D_80126B5E;
+    p6 = *(u16 *)(arg0 + 6);
+    d = w5e - p6;
+    t1 = d;
+    if ((s16)d < 0) {
+        t1 = -d;
+    }
+    w66 = D_80126B66;
+    pE = *(u16 *)(arg0 + 0xE);
+    d = w66 - pE;
+    a3 = d;
+    if ((s16)d < 0) {
+        a3 = -d;
+    }
+    x = *(s16 *)(arg0 + 0xA);
+    y = *(s16 *)(arg1 + 8);
+    lim = *(s16 *)&D_80126B62;
+    if (lim < x + y) {
+        return;
+    }
+    z = *(s16 *)(arg1 + 0xA);
+    if (x + z < lim) {
+        return;
+    }
+    wide = t1 << 16;
+    t1 = wide >> 16;
+    if (t1 >= 0x49) {
+        return;
+    }
+    wide = a3 << 16;
+    a3 = wide >> 16;
+    if (a3 >= 0x49) {
+        return;
+    }
+    if (lim < x + ((y + z) >> 1)) {
+        D_80126B62 = x + y - 1;
+        return;
+    }
+    t1n = t1;
+    a3n = a3;
+    if (t1n < a3n) {
+        if ((s16)w66 > (s16)pE) {
+            D_80126B66 = pE + 0x49;
+        } else {
+            D_80126B66 = pE - 0x49;
+        }
+    } else {
+        if ((s16)w5e > (s16)p6) {
+            D_80126B5E = p6 + 0x49;
+        } else {
+            D_80126B5E = p6 - 0x49;
+        }
+    }
+}
+
 
 extern s32 func_8012B6D4(s16 *a0, s16 *a1);
 
diff --git a/src/ov_SC04_005/ov_SC04_005_jr_8017BEBC.c b/src/ov_SC04_005/ov_SC04_005_jr_8017BEBC.c
index b487bb05f..ef3844ccf 100644
--- a/src/ov_SC04_005/ov_SC04_005_jr_8017BEBC.c
+++ b/src/ov_SC04_005/ov_SC04_005_jr_8017BEBC.c
@@ -10877,7 +10877,91 @@ void func_8018741C(void *a0)
 }
 
 
-INCLUDE_ASM("asm/ov_SC04_005/nonmatchings/ov_SC04_005_jr_8017BEBC", func_80187548);
+
+
+typedef struct { short a, b, c; } SV3_801802D0;
+typedef struct { s16 a, b, c, d; } SV4x_80183E2C;       /* 8-byte, align-2 quad of s16 */
+
+
+extern s32 D_80126B58;
+extern u16 D_80126B5E;
+extern u16 D_80126B62;
+extern u16 D_80126B66;
+
+void func_80187548(s32 arg0, s32 arg1) {
+    u16 w5e;
+    u16 p6;
+    u16 w66;
+    u16 pE;
+    s16 x;
+    s16 y;
+    s16 z;
+    s16 lim;
+    s32 wide;
+    s16 t1n;
+    s16 a3n;
+    register s32 d __asm__("6");
+    register s32 t1 __asm__("9");
+    register s32 a3 __asm__("7");
+
+    if (*(u16 *)&D_80126B58 == 0x1A) {
+        return;
+    }
+    w5e = D_80126B5E;
+    p6 = *(u16 *)(arg0 + 6);
+    d = w5e - p6;
+    t1 = d;
+    if ((s16)d < 0) {
+        t1 = -d;
+    }
+    w66 = D_80126B66;
+    pE = *(u16 *)(arg0 + 0xE);
+    d = w66 - pE;
+    a3 = d;
+    if ((s16)d < 0) {
+        a3 = -d;
+    }
+    x = *(s16 *)(arg0 + 0xA);
+    y = *(s16 *)(arg1 + 8);
+    lim = *(s16 *)&D_80126B62;
+    if (lim < x + y) {
+        return;
+    }
+    z = *(s16 *)(arg1 + 0xA);
+    if (x + z < lim) {
+        return;
+    }
+    wide = t1 << 16;
+    t1 = wide >> 16;
+    if (t1 >= 0x49) {
+        return;
+    }
+    wide = a3 << 16;
+    a3 = wide >> 16;
+    if (a3 >= 0x49) {
+        return;
+    }
+    if (lim < x + ((y + z) >> 1)) {
+        D_80126B62 = x + y - 1;
+        return;
+    }
+    t1n = t1;
+    a3n = a3;
+    if (t1n < a3n) {
+        if ((s16)w66 > (s16)pE) {
+            D_80126B66 = pE + 0x49;
+        } else {
+            D_80126B66 = pE - 0x49;
+        }
+    } else {
+        if ((s16)w5e > (s16)p6) {
+            D_80126B5E = p6 + 0x49;
+        } else {
+            D_80126B5E = p6 - 0x49;
+        }
+    }
+}
+
 
 extern s32 func_8012B6D4(s16 *a0, s16 *a1);