diff --git a/wolfcrypt/src/sp_arm64.c b/wolfcrypt/src/sp_arm64.c
index 46b080ca0..ebebe2a55 100644
--- a/wolfcrypt/src/sp_arm64.c
+++ b/wolfcrypt/src/sp_arm64.c
@@ -2503,7 +2503,6 @@ SP_NOINLINE static void sp_2048_mont_reduce_16(sp_digit* a, const sp_digit* m,
         "ldp	x23, x24, [%[m], 64]\n\t"
         "ldp	x25, x26, [%[m], 80]\n\t"
         "ldp	x27, x28, [%[m], 96]\n\t"
-        "ldp	x29, x30, [%[m], 112]\n\t"
         "# i = 16\n\t"
         "mov	x4, 16\n\t"
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -2628,19 +2627,21 @@ SP_NOINLINE static void sp_2048_mont_reduce_16(sp_digit* a, const sp_digit* m,
         "# a[i+14] += m[14] * mu\n\t"
         "ldr	x11, [%[a], 112]\n\t"
         "adc	x5, x8, xzr\n\t"
+        "ldr	x8, [%[m], 112]\n\t"
         "adds	x10, x10, x6\n\t"
-        "mul	x7, x29, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x5, x5, xzr\n\t"
-        "umulh	x8, x29, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x10, [%[a], 104]\n\t"
         "adds	x11, x11, x7\n\t"
         "# a[i+15] += m[15] * mu\n\t"
         "ldr	x10, [%[a], 120]\n\t"
         "adc	x6, x8, xzr\n\t"
+        "ldr	x8, [%[m], 120]\n\t"
         "adds	x11, x11, x5\n\t"
-        "mul	x7, x30, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x6, x6, xzr\n\t"
-        "umulh	x8, x30, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "adds	x6, x6, x7\n\t"
         "adcs	x8, x8, %[ca]\n\t"
         "str	x11, [%[a], 112]\n\t"
@@ -2657,7 +2658,7 @@ SP_NOINLINE static void sp_2048_mont_reduce_16(sp_digit* a, const sp_digit* m,
         "stp	x12, x13, [%[a], 0]\n\t"
         : [ca] "+r" (ca), [a] "+r" (a)
         : [m] "r" (m), [mp] "r" (mp)
-        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28", "x29", "x30"
+        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
     );
 
     sp_2048_cond_sub_16(a - 16, a, m, (sp_digit)0 - ca);
@@ -3616,7 +3617,6 @@ SP_NOINLINE static void sp_2048_mont_reduce_32(sp_digit* a, const sp_digit* m,
         "ldp	x23, x24, [%[m], 64]\n\t"
         "ldp	x25, x26, [%[m], 80]\n\t"
         "ldp	x27, x28, [%[m], 96]\n\t"
-        "ldp	x29, x30, [%[m], 112]\n\t"
         "# i = 32\n\t"
         "mov	x4, 32\n\t"
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -3741,19 +3741,21 @@ SP_NOINLINE static void sp_2048_mont_reduce_32(sp_digit* a, const sp_digit* m,
         "# a[i+14] += m[14] * mu\n\t"
         "ldr	x11, [%[a], 112]\n\t"
         "adc	x5, x8, xzr\n\t"
+        "ldr	x8, [%[m], 112]\n\t"
         "adds	x10, x10, x6\n\t"
-        "mul	x7, x29, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x5, x5, xzr\n\t"
-        "umulh	x8, x29, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x10, [%[a], 104]\n\t"
         "adds	x11, x11, x7\n\t"
         "# a[i+15] += m[15] * mu\n\t"
         "ldr	x10, [%[a], 120]\n\t"
         "adc	x6, x8, xzr\n\t"
+        "ldr	x8, [%[m], 120]\n\t"
         "adds	x11, x11, x5\n\t"
-        "mul	x7, x30, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x6, x6, xzr\n\t"
-        "umulh	x8, x30, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x11, [%[a], 112]\n\t"
         "adds	x10, x10, x7\n\t"
         "# a[i+16] += m[16] * mu\n\t"
@@ -3930,7 +3932,7 @@ SP_NOINLINE static void sp_2048_mont_reduce_32(sp_digit* a, const sp_digit* m,
         "stp	x12, x13, [%[a], 0]\n\t"
         : [ca] "+r" (ca), [a] "+r" (a)
         : [m] "r" (m), [mp] "r" (mp)
-        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28", "x29", "x30"
+        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
     );
 
     sp_2048_cond_sub_32(a - 32, a, m, (sp_digit)0 - ca);
@@ -9633,7 +9635,6 @@ SP_NOINLINE static void sp_3072_mont_reduce_24(sp_digit* a, const sp_digit* m,
         "ldp	x23, x24, [%[m], 64]\n\t"
         "ldp	x25, x26, [%[m], 80]\n\t"
         "ldp	x27, x28, [%[m], 96]\n\t"
-        "ldp	x29, x30, [%[m], 112]\n\t"
         "# i = 24\n\t"
         "mov	x4, 24\n\t"
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -9758,19 +9759,21 @@ SP_NOINLINE static void sp_3072_mont_reduce_24(sp_digit* a, const sp_digit* m,
         "# a[i+14] += m[14] * mu\n\t"
         "ldr	x11, [%[a], 112]\n\t"
         "adc	x5, x8, xzr\n\t"
+        "ldr	x8, [%[m], 112]\n\t"
         "adds	x10, x10, x6\n\t"
-        "mul	x7, x29, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x5, x5, xzr\n\t"
-        "umulh	x8, x29, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x10, [%[a], 104]\n\t"
         "adds	x11, x11, x7\n\t"
         "# a[i+15] += m[15] * mu\n\t"
         "ldr	x10, [%[a], 120]\n\t"
         "adc	x6, x8, xzr\n\t"
+        "ldr	x8, [%[m], 120]\n\t"
         "adds	x11, x11, x5\n\t"
-        "mul	x7, x30, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x6, x6, xzr\n\t"
-        "umulh	x8, x30, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x11, [%[a], 112]\n\t"
         "adds	x10, x10, x7\n\t"
         "# a[i+16] += m[16] * mu\n\t"
@@ -9867,7 +9870,7 @@ SP_NOINLINE static void sp_3072_mont_reduce_24(sp_digit* a, const sp_digit* m,
         "stp	x12, x13, [%[a], 0]\n\t"
         : [ca] "+r" (ca), [a] "+r" (a)
         : [m] "r" (m), [mp] "r" (mp)
-        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28", "x29", "x30"
+        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
     );
 
     sp_3072_cond_sub_24(a - 24, a, m, (sp_digit)0 - ca);
@@ -11006,7 +11009,6 @@ SP_NOINLINE static void sp_3072_mont_reduce_48(sp_digit* a, const sp_digit* m,
         "ldp	x23, x24, [%[m], 64]\n\t"
         "ldp	x25, x26, [%[m], 80]\n\t"
         "ldp	x27, x28, [%[m], 96]\n\t"
-        "ldp	x29, x30, [%[m], 112]\n\t"
         "# i = 48\n\t"
         "mov	x4, 48\n\t"
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -11131,19 +11133,21 @@ SP_NOINLINE static void sp_3072_mont_reduce_48(sp_digit* a, const sp_digit* m,
         "# a[i+14] += m[14] * mu\n\t"
         "ldr	x11, [%[a], 112]\n\t"
         "adc	x5, x8, xzr\n\t"
+        "ldr	x8, [%[m], 112]\n\t"
         "adds	x10, x10, x6\n\t"
-        "mul	x7, x29, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x5, x5, xzr\n\t"
-        "umulh	x8, x29, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x10, [%[a], 104]\n\t"
         "adds	x11, x11, x7\n\t"
         "# a[i+15] += m[15] * mu\n\t"
         "ldr	x10, [%[a], 120]\n\t"
         "adc	x6, x8, xzr\n\t"
+        "ldr	x8, [%[m], 120]\n\t"
         "adds	x11, x11, x5\n\t"
-        "mul	x7, x30, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x6, x6, xzr\n\t"
-        "umulh	x8, x30, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x11, [%[a], 112]\n\t"
         "adds	x10, x10, x7\n\t"
         "# a[i+16] += m[16] * mu\n\t"
@@ -11480,7 +11484,7 @@ SP_NOINLINE static void sp_3072_mont_reduce_48(sp_digit* a, const sp_digit* m,
         "stp	x12, x13, [%[a], 0]\n\t"
         : [ca] "+r" (ca), [a] "+r" (a)
         : [m] "r" (m), [mp] "r" (mp)
-        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28", "x29", "x30"
+        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
     );
 
     sp_3072_cond_sub_48(a - 48, a, m, (sp_digit)0 - ca);
@@ -15623,7 +15627,6 @@ SP_NOINLINE static void sp_4096_mont_reduce_64(sp_digit* a, const sp_digit* m,
         "ldp	x23, x24, [%[m], 64]\n\t"
         "ldp	x25, x26, [%[m], 80]\n\t"
         "ldp	x27, x28, [%[m], 96]\n\t"
-        "ldp	x29, x30, [%[m], 112]\n\t"
         "# i = 64\n\t"
         "mov	x4, 64\n\t"
         "ldp	x12, x13, [%[a], 0]\n\t"
@@ -15748,19 +15751,21 @@ SP_NOINLINE static void sp_4096_mont_reduce_64(sp_digit* a, const sp_digit* m,
         "# a[i+14] += m[14] * mu\n\t"
         "ldr	x11, [%[a], 112]\n\t"
         "adc	x5, x8, xzr\n\t"
+        "ldr	x8, [%[m], 112]\n\t"
         "adds	x10, x10, x6\n\t"
-        "mul	x7, x29, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x5, x5, xzr\n\t"
-        "umulh	x8, x29, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x10, [%[a], 104]\n\t"
         "adds	x11, x11, x7\n\t"
         "# a[i+15] += m[15] * mu\n\t"
         "ldr	x10, [%[a], 120]\n\t"
         "adc	x6, x8, xzr\n\t"
+        "ldr	x8, [%[m], 120]\n\t"
         "adds	x11, x11, x5\n\t"
-        "mul	x7, x30, x9\n\t"
+        "mul	x7, x8, x9\n\t"
         "adc	x6, x6, xzr\n\t"
-        "umulh	x8, x30, x9\n\t"
+        "umulh	x8, x8, x9\n\t"
         "str	x11, [%[a], 112]\n\t"
         "adds	x10, x10, x7\n\t"
         "# a[i+16] += m[16] * mu\n\t"
@@ -16257,7 +16262,7 @@ SP_NOINLINE static void sp_4096_mont_reduce_64(sp_digit* a, const sp_digit* m,
         "stp	x12, x13, [%[a], 0]\n\t"
         : [ca] "+r" (ca), [a] "+r" (a)
         : [m] "r" (m), [mp] "r" (mp)
-        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28", "x29", "x30"
+        : "memory", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", "x16", "x17", "x19", "x20", "x21", "x22", "x23", "x24", "x25", "x26", "x27", "x28"
     );
 
     sp_4096_cond_sub_64(a - 64, a, m, (sp_digit)0 - ca);