diff --git a/wolfcrypt/src/sp_arm32.c b/wolfcrypt/src/sp_arm32.c
index 54423c2d5..1467181fa 100644
--- a/wolfcrypt/src/sp_arm32.c
+++ b/wolfcrypt/src/sp_arm32.c
@@ -71032,8 +71032,8 @@ static SP_NOINLINE void sp_256_mont_sqr_8(sp_digit* r_p, const sp_digit* a_p, co
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_8(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_8(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_8(r, a, m, mp);
     for (; n > 1; n--) {
@@ -89861,8 +89861,8 @@ SP_NOINLINE static void sp_384_mont_sqr_12(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_12(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_12(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_12(r, a, m, mp);
     for (; n > 1; n--) {
@@ -116850,8 +116850,8 @@ SP_NOINLINE static void sp_521_mont_sqr_17(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_17(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_17(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_17(r, a, m, mp);
     for (; n > 1; n--) {
diff --git a/wolfcrypt/src/sp_arm64.c b/wolfcrypt/src/sp_arm64.c
index 0533f9396..dcbbaa137 100644
--- a/wolfcrypt/src/sp_arm64.c
+++ b/wolfcrypt/src/sp_arm64.c
@@ -21872,7 +21872,8 @@ static void sp_256_mul_4(sp_digit* r, const sp_digit* a, const sp_digit* b)
  * a  A single precision integer.
  * b  A single precision integer.
  */
-static void sp_256_mul_4(sp_digit* r, const sp_digit* a, const sp_digit* b)
+SP_NOINLINE static void sp_256_mul_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* b)
 {
     __asm__ __volatile__ (
         "ldp	x13, x14, [%[a], 0]\n\t"
@@ -21978,7 +21979,7 @@ static void sp_256_mul_4(sp_digit* r, const sp_digit* a, const sp_digit* b)
  * r  A single precision integer.
  * a  A single precision integer.
  */
-static void sp_256_sqr_4(sp_digit* r, const sp_digit* a)
+SP_NOINLINE static void sp_256_sqr_4(sp_digit* r, const sp_digit* a)
 {
     __asm__ __volatile__ (
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -22421,8 +22422,8 @@ static void sp_256_cond_copy_4(sp_digit* r, const sp_digit* a, sp_digit m)
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_mul_4(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_mul_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m, sp_digit mp)
 {
     (void)m;
     (void)mp;
@@ -22596,8 +22597,8 @@ static void sp_256_mont_mul_4(sp_digit* r, const sp_digit* a, const sp_digit* b,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_4(sp_digit* r, const sp_digit* a, const sp_digit* m,
-        sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* m, sp_digit mp)
 {
     (void)m;
     (void)mp;
@@ -22741,8 +22742,8 @@ static void sp_256_mont_sqr_4(sp_digit* r, const sp_digit* a, const sp_digit* m,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_4(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_4(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_4(r, a, m, mp);
     for (; n > 1; n--) {
@@ -23081,7 +23082,8 @@ static void sp_256_map_4(sp_point_256* r, const sp_point_256* p,
  * a   Number to double in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_dbl_4(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_dbl_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x3, x4, [%[a]]\n\t"
@@ -23121,7 +23123,8 @@ static void sp_256_mont_dbl_4(sp_digit* r, const sp_digit* a, const sp_digit* m)
  * a   Number to triple in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_tpl_4(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_tpl_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x9, x10, [%[a]]\n\t"
@@ -23176,8 +23179,8 @@ static void sp_256_mont_tpl_4(sp_digit* r, const sp_digit* a, const sp_digit* m)
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_sub_4(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_sub_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -23218,7 +23221,8 @@ static void sp_256_mont_sub_4(sp_digit* r, const sp_digit* a, const sp_digit* b,
  * a  Number to divide.
  * m  Modulus (prime).
  */
-static void sp_256_mont_div2_4(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_div2_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp   x3, x4, [%[a], 0]\n\t"
@@ -23250,8 +23254,8 @@ static void sp_256_mont_div2_4(sp_digit* r, const sp_digit* a, const sp_digit* m
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_rsb_sub_dbl_4(sp_digit* r, const sp_digit* a,
-        sp_digit* b, const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_rsb_sub_dbl_4(sp_digit* r,
+    const sp_digit* a, sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x8, x9, [%[b]]\n\t"
@@ -23327,8 +23331,8 @@ static void sp_256_mont_rsb_sub_dbl_4(sp_digit* r, const sp_digit* a,
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_add_sub_4(sp_digit* ra, sp_digit* rs, const sp_digit* a,
-        const sp_digit* b, const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_add_sub_4(sp_digit* ra,
+    sp_digit* rs, const sp_digit* a, const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -23807,7 +23811,8 @@ static void sp_256_proj_point_add_4(sp_point_256* r,
         : [r] "r" (r), [p] "r" (p), [q] "r" (q), [x] "r" (x),
           [y] "r" (y), [z] "r" (z)
         : "memory", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17",
-          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
+          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28",
+          "cc"
     );
 }
     }
@@ -24039,7 +24044,8 @@ static int sp_256_proj_point_add_4_nb(sp_ecc_ctx_t* sp_ctx, sp_point_256* r,
         : [r] "r" (r), [p] "r" (p), [q] "r" (q), [x] "r" (ctx->x),
           [y] "r" (ctx->y), [z] "r" (ctx->z)
         : "memory", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17",
-          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
+          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28",
+          "cc"
     );
 }
         ctx->state = 25;
@@ -24282,8 +24288,8 @@ static void sp_256_ecc_recode_6_4(const sp_digit* k, ecc_recode_256* v)
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_256_get_point_33_4(sp_point_256* r, const sp_point_256* table,
-    int idx)
+SP_NOINLINE static void sp_256_get_point_33_4(sp_point_256* r,
+    const sp_point_256* table, int idx)
 {
     __asm__ __volatile__ (
         "mov	w30, #1\n\t"
@@ -24340,7 +24346,7 @@ static void sp_256_get_point_33_4(sp_point_256* r, const sp_point_256* table,
         "stp	x13, x14, [%[r], #144]\n\t"
        : [table] "+r" (table)
        : [r] "r" (r), [idx] "r" (idx)
-       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30"
+       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30", "cc"
     );
 }
 #endif /* !WC_NO_CACHE_RESISTANT */
@@ -24609,7 +24615,8 @@ static void sp_256_proj_point_add_qz1_4(sp_point_256* r,
         : [r] "r" (r), [p] "r" (p), [q] "r" (q), [x] "r" (x),
           [y] "r" (y), [z] "r" (z)
         : "memory", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17",
-          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
+          "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28",
+          "cc"
     );
 }
     }
@@ -24740,7 +24747,7 @@ static int sp_256_gen_stripe_table_4(const sp_point_256* a,
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_256_get_entry_64_4(sp_point_256* r,
+SP_NOINLINE static void sp_256_get_entry_64_4(sp_point_256* r,
     const sp_table_entry_256* table, int idx)
 {
     __asm__ __volatile__ (
@@ -24784,7 +24791,7 @@ static void sp_256_get_entry_64_4(sp_point_256* r,
         "stp	x9, x10, [%[r], #80]\n\t"
        : [table] "+r" (table)
        : [r] "r" (r), [idx] "r" (idx)
-       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30"
+       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30", "cc"
     );
 }
 #endif /* !WC_NO_CACHE_RESISTANT */
@@ -25169,7 +25176,7 @@ static int sp_256_gen_stripe_table_4(const sp_point_256* a,
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_256_get_entry_256_4(sp_point_256* r,
+SP_NOINLINE static void sp_256_get_entry_256_4(sp_point_256* r,
     const sp_table_entry_256* table, int idx)
 {
     __asm__ __volatile__ (
@@ -25213,7 +25220,7 @@ static void sp_256_get_entry_256_4(sp_point_256* r,
         "stp	x9, x10, [%[r], #80]\n\t"
        : [table] "+r" (table)
        : [r] "r" (r), [idx] "r" (idx)
-       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30"
+       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30", "cc"
     );
 }
 #endif /* !WC_NO_CACHE_RESISTANT */
@@ -27368,7 +27375,7 @@ static void sp_256_ecc_recode_7_4(const sp_digit* k, ecc_recode_256* v)
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_256_get_entry_65_4(sp_point_256* r,
+SP_NOINLINE static void sp_256_get_entry_65_4(sp_point_256* r,
     const sp_table_entry_256* table, int idx)
 {
     __asm__ __volatile__ (
@@ -27412,7 +27419,7 @@ static void sp_256_get_entry_65_4(sp_point_256* r,
         "stp	x9, x10, [%[r], #80]\n\t"
        : [table] "+r" (table)
        : [r] "r" (r), [idx] "r" (idx)
-       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30"
+       : "memory", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "w30", "cc"
     );
 }
 #endif /* !WC_NO_CACHE_RESISTANT */
@@ -40321,7 +40328,8 @@ static WC_INLINE int sp_256_mod_4(sp_digit* r, const sp_digit* a, const sp_digit
  * a  First operand of the multiplication.
  * b  Second operand of the multiplication.
  */
-static void sp_256_mont_mul_order_4(sp_digit* r, const sp_digit* a, const sp_digit* b)
+SP_NOINLINE static void sp_256_mont_mul_order_4(sp_digit* r,
+    const sp_digit* a, const sp_digit* b)
 {
     __asm__ __volatile__ (
         "ldp	x13, x14, [%[a], 0]\n\t"
@@ -40546,7 +40554,8 @@ static const uint64_t p256_order_minus_2[4] = {
  * r  Result of the squaring.
  * a  Number to square.
  */
-static void sp_256_mont_sqr_order_4(sp_digit* r, const sp_digit* a)
+SP_NOINLINE static void sp_256_mont_sqr_order_4(sp_digit* r,
+    const sp_digit* a)
 {
     __asm__ __volatile__ (
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -40732,7 +40741,8 @@ static void sp_256_mont_sqr_order_4(sp_digit* r, const sp_digit* a)
  * r  Result of the squaring.
  * a  Number to square.
  */
-static void sp_256_mont_sqr_n_order_4(sp_digit* r, const sp_digit* a, int n)
+SP_NOINLINE static void sp_256_mont_sqr_n_order_4(sp_digit* r,
+    const sp_digit* a, int n)
 {
 
     __asm__ __volatile__ (
@@ -42080,8 +42090,8 @@ int sp_ecc_verify_256_nb(sp_ecc_ctx_t* sp_ctx, const byte* hash,
  * b   Second number to add in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_256_mont_add_4(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_256_mont_add_4(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -43961,8 +43971,8 @@ SP_NOINLINE static void sp_384_mont_sqr_6(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_6(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_6(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_6(r, a, m, mp);
     for (; n > 1; n--) {
@@ -44250,8 +44260,8 @@ static void sp_384_map_6(sp_point_384* r, const sp_point_384* p,
  * b   Second number to add in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_384_mont_add_6(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_384_mont_add_6(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     sp_digit o;
 
@@ -44265,7 +44275,8 @@ static void sp_384_mont_add_6(sp_digit* r, const sp_digit* a, const sp_digit* b,
  * a   Number to double in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_384_mont_dbl_6(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_384_mont_dbl_6(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     sp_digit o;
 
@@ -44279,7 +44290,8 @@ static void sp_384_mont_dbl_6(sp_digit* r, const sp_digit* a, const sp_digit* m)
  * a   Number to triple in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_384_mont_tpl_6(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_384_mont_tpl_6(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     sp_digit o;
 
@@ -44377,8 +44389,8 @@ static sp_digit sp_384_cond_add_6(sp_digit* r, const sp_digit* a, const sp_digit
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_384_mont_sub_6(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_384_mont_sub_6(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     sp_digit o;
 
@@ -44413,7 +44425,8 @@ static void sp_384_rshift1_6(sp_digit* r, const sp_digit* a)
  * a  Number to divide.
  * m  Modulus (prime).
  */
-static void sp_384_mont_div2_6(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_384_mont_div2_6(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     sp_digit o;
 
@@ -45260,8 +45273,8 @@ static void sp_384_ecc_recode_6_6(const sp_digit* k, ecc_recode_384* v)
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_384_get_point_33_6(sp_point_384* r, const sp_point_384* table,
-    int idx)
+SP_NOINLINE static void sp_384_get_point_33_6(sp_point_384* r,
+    const sp_point_384* table, int idx)
 {
     int i;
     sp_digit mask;
@@ -72148,8 +72161,8 @@ SP_NOINLINE static void sp_521_mont_sqr_9(sp_digit* r, const sp_digit* a, const
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_9(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_9(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_9(r, a, m, mp);
     for (; n > 1; n--) {
@@ -72448,8 +72461,8 @@ static void sp_521_map_9(sp_point_521* r, const sp_point_521* p,
  * b   Second number to add in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_521_mont_add_9(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_521_mont_add_9(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -72501,7 +72514,8 @@ static void sp_521_mont_add_9(sp_digit* r, const sp_digit* a, const sp_digit* b,
  * a   Number to double in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_521_mont_dbl_9(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_521_mont_dbl_9(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -72548,7 +72562,8 @@ static void sp_521_mont_dbl_9(sp_digit* r, const sp_digit* a, const sp_digit* m)
  * a   Number to triple in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_521_mont_tpl_9(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_521_mont_tpl_9(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -72605,8 +72620,8 @@ static void sp_521_mont_tpl_9(sp_digit* r, const sp_digit* a, const sp_digit* m)
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_521_mont_sub_9(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_521_mont_sub_9(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp	x4, x5, [%[a], 0]\n\t"
@@ -72787,7 +72802,8 @@ static void sp_521_rshift1_9(sp_digit* r, const sp_digit* a)
  * a  Number to divide.
  * m  Modulus (prime).
  */
-static void sp_521_mont_div2_9(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_521_mont_div2_9(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     sp_digit o;
 
@@ -73636,8 +73652,8 @@ static void sp_521_ecc_recode_6_9(const sp_digit* k, ecc_recode_521* v)
  * table  Table - start of the entries to access
  * idx    Index of entry to retrieve.
  */
-static void sp_521_get_point_33_9(sp_point_521* r, const sp_point_521* table,
-    int idx)
+SP_NOINLINE static void sp_521_get_point_33_9(sp_point_521* r,
+    const sp_point_521* table, int idx)
 {
     int i;
     sp_digit mask;
@@ -116258,8 +116274,8 @@ static void sp_1024_map_16(sp_point_1024* r, const sp_point_1024* p,
  * b   Second number to add in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_1024_mont_add_16(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_1024_mont_add_16(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp       x4, x5, [%[a], 0]\n\t"
@@ -116359,7 +116375,8 @@ static void sp_1024_mont_add_16(sp_digit* r, const sp_digit* a, const sp_digit*
  * a   Number to double in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_1024_mont_dbl_16(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_1024_mont_dbl_16(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp       x4, x5, [%[a], 0]\n\t"
@@ -116451,7 +116468,8 @@ static void sp_1024_mont_dbl_16(sp_digit* r, const sp_digit* a, const sp_digit*
  * a   Number to triple in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_1024_mont_tpl_16(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_1024_mont_tpl_16(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp       x4, x5, [%[a], 0]\n\t"
@@ -116613,8 +116631,8 @@ static void sp_1024_mont_tpl_16(sp_digit* r, const sp_digit* a, const sp_digit*
  * b   Number to subtract with in Montgomery form.
  * m   Modulus (prime).
  */
-static void sp_1024_mont_sub_16(sp_digit* r, const sp_digit* a, const sp_digit* b,
-        const sp_digit* m)
+SP_NOINLINE static void sp_1024_mont_sub_16(sp_digit* r, const sp_digit* a,
+    const sp_digit* b, const sp_digit* m)
 {
     __asm__ __volatile__ (
         "ldp       x4, x5, [%[a], 0]\n\t"
@@ -116882,7 +116900,8 @@ static void sp_1024_rshift1_16(sp_digit* r, const sp_digit* a)
  * a  Number to divide.
  * m  Modulus (prime).
  */
-static void sp_1024_mont_div2_16(sp_digit* r, const sp_digit* a, const sp_digit* m)
+SP_NOINLINE static void sp_1024_mont_div2_16(sp_digit* r, const sp_digit* a,
+    const sp_digit* m)
 {
     sp_digit o;
 
diff --git a/wolfcrypt/src/sp_armthumb.c b/wolfcrypt/src/sp_armthumb.c
index f7aeb1055..9b5345e5f 100644
--- a/wolfcrypt/src/sp_armthumb.c
+++ b/wolfcrypt/src/sp_armthumb.c
@@ -98862,8 +98862,8 @@ SP_NOINLINE static void sp_256_mont_sqr_8(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_8(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_8(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_8(r, a, m, mp);
     for (; n > 1; n--) {
@@ -110310,8 +110310,8 @@ SP_NOINLINE static void sp_384_mont_sqr_12(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_12(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_12(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_12(r, a, m, mp);
     for (; n > 1; n--) {
@@ -122594,8 +122594,8 @@ SP_NOINLINE static void sp_521_mont_sqr_17(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_17(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_17(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_17(r, a, m, mp);
     for (; n > 1; n--) {
diff --git a/wolfcrypt/src/sp_c32.c b/wolfcrypt/src/sp_c32.c
index 8baa651ea..66d057a21 100644
--- a/wolfcrypt/src/sp_c32.c
+++ b/wolfcrypt/src/sp_c32.c
@@ -20988,8 +20988,8 @@ SP_NOINLINE static void sp_256_mont_sqr_9(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_9(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_9(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_9(r, a, m, mp);
     for (; n > 1; n--) {
@@ -28396,8 +28396,8 @@ SP_NOINLINE static void sp_384_mont_sqr_15(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_15(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_15(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_15(r, a, m, mp);
     for (; n > 1; n--) {
@@ -36069,8 +36069,8 @@ SP_NOINLINE static void sp_521_mont_sqr_21(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_21(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_21(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_21(r, a, m, mp);
     for (; n > 1; n--) {
diff --git a/wolfcrypt/src/sp_c64.c b/wolfcrypt/src/sp_c64.c
index f6aef0ebb..607b7274d 100644
--- a/wolfcrypt/src/sp_c64.c
+++ b/wolfcrypt/src/sp_c64.c
@@ -21968,8 +21968,8 @@ SP_NOINLINE static void sp_256_mont_sqr_5(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_5(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_5(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_5(r, a, m, mp);
     for (; n > 1; n--) {
@@ -28872,8 +28872,8 @@ SP_NOINLINE static void sp_384_mont_sqr_7(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_7(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_7(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_7(r, a, m, mp);
     for (; n > 1; n--) {
@@ -36410,8 +36410,8 @@ SP_NOINLINE static void sp_521_mont_sqr_9(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_9(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_9(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_9(r, a, m, mp);
     for (; n > 1; n--) {
diff --git a/wolfcrypt/src/sp_cortexm.c b/wolfcrypt/src/sp_cortexm.c
index af612beba..3b7b03c91 100644
--- a/wolfcrypt/src/sp_cortexm.c
+++ b/wolfcrypt/src/sp_cortexm.c
@@ -33861,8 +33861,8 @@ static void sp_256_mont_sqr_8(sp_digit* r, const sp_digit* a, const sp_digit* m,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_8(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_8(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_8(r, a, m, mp);
     for (; n > 1; n--) {
@@ -44264,8 +44264,8 @@ SP_NOINLINE static void sp_384_mont_sqr_12(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_12(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_12(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_12(r, a, m, mp);
     for (; n > 1; n--) {
@@ -56088,8 +56088,8 @@ SP_NOINLINE static void sp_521_mont_sqr_17(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_17(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_17(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_17(r, a, m, mp);
     for (; n > 1; n--) {
diff --git a/wolfcrypt/src/sp_x86_64.c b/wolfcrypt/src/sp_x86_64.c
index e0e1495b9..102884672 100644
--- a/wolfcrypt/src/sp_x86_64.c
+++ b/wolfcrypt/src/sp_x86_64.c
@@ -8409,8 +8409,8 @@ extern void sp_256_mont_sqr_4(sp_digit* r, const sp_digit* a, const sp_digit* m,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_4(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_4(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_4(r, a, m, mp);
     for (; n > 1; n--) {
@@ -9609,8 +9609,8 @@ extern void sp_256_mont_sqr_avx2_4(sp_digit* r, const sp_digit* a, const sp_digi
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_256_mont_sqr_n_avx2_4(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_256_mont_sqr_n_avx2_4(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_256_mont_sqr_avx2_4(r, a, m, mp);
     for (; n > 1; n--) {
@@ -27535,8 +27535,8 @@ SP_NOINLINE static void sp_384_mont_sqr_6(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_6(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_6(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_6(r, a, m, mp);
     for (; n > 1; n--) {
@@ -28769,8 +28769,8 @@ SP_NOINLINE static void sp_384_mont_sqr_avx2_6(sp_digit* r, const sp_digit* a,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_384_mont_sqr_n_avx2_6(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_384_mont_sqr_n_avx2_6(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_384_mont_sqr_avx2_6(r, a, m, mp);
     for (; n > 1; n--) {
@@ -52416,8 +52416,8 @@ extern void sp_521_mont_sqr_9(sp_digit* r, const sp_digit* a, const sp_digit* m,
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_9(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_9(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_9(r, a, m, mp);
     for (; n > 1; n--) {
@@ -53642,8 +53642,8 @@ extern void sp_521_mont_sqr_avx2_9(sp_digit* r, const sp_digit* a, const sp_digi
  * m   Modulus (prime).
  * mp  Montgomery multiplier.
  */
-static void sp_521_mont_sqr_n_avx2_9(sp_digit* r, const sp_digit* a, int n,
-        const sp_digit* m, sp_digit mp)
+SP_NOINLINE static void sp_521_mont_sqr_n_avx2_9(sp_digit* r,
+    const sp_digit* a, int n, const sp_digit* m, sp_digit mp)
 {
     sp_521_mont_sqr_avx2_9(r, a, m, mp);
     for (; n > 1; n--) {