diff --git a/.wolfssl_known_macro_extras b/.wolfssl_known_macro_extras
index 49353bc671..436de477fc 100644
--- a/.wolfssl_known_macro_extras
+++ b/.wolfssl_known_macro_extras
@@ -506,6 +506,7 @@ SNIFFER_SINGLE_SESSION_CACHE
 SOFTDEVICE_PRESENT
 SO_NOSIGPIPE
 SO_REUSEPORT
+SP_ALIGN_16
 SP_INT_NO_ASM
 SP_MATH_NEED_ADD_OFF
 SP_USE_DIVTI3
diff --git a/wolfcrypt/src/sp_arm32.c b/wolfcrypt/src/sp_arm32.c
index 168168f094..43f3f3ce14 100644
--- a/wolfcrypt/src/sp_arm32.c
+++ b/wolfcrypt/src/sp_arm32.c
@@ -99504,6 +99504,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 17];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_arm64.c b/wolfcrypt/src/sp_arm64.c
index 71a31716dc..51679142bf 100644
--- a/wolfcrypt/src/sp_arm64.c
+++ b/wolfcrypt/src/sp_arm64.c
@@ -67605,6 +67605,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 9];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_armthumb.c b/wolfcrypt/src/sp_armthumb.c
index 98516b9018..7871754ae0 100644
--- a/wolfcrypt/src/sp_armthumb.c
+++ b/wolfcrypt/src/sp_armthumb.c
@@ -118312,6 +118312,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 17];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_c32.c b/wolfcrypt/src/sp_c32.c
index f52cf44859..d2107da8fd 100644
--- a/wolfcrypt/src/sp_c32.c
+++ b/wolfcrypt/src/sp_c32.c
@@ -32707,6 +32707,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 21];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_c64.c b/wolfcrypt/src/sp_c64.c
index 21473732ad..a6dc93d996 100644
--- a/wolfcrypt/src/sp_c64.c
+++ b/wolfcrypt/src/sp_c64.c
@@ -32635,6 +32635,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 9];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_cortexm.c b/wolfcrypt/src/sp_cortexm.c
index 801978d128..e84fde0864 100644
--- a/wolfcrypt/src/sp_cortexm.c
+++ b/wolfcrypt/src/sp_cortexm.c
@@ -51918,6 +51918,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 17];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_x86_64.c b/wolfcrypt/src/sp_x86_64.c
index b792175971..1b39f1b959 100644
--- a/wolfcrypt/src/sp_x86_64.c
+++ b/wolfcrypt/src/sp_x86_64.c
@@ -50649,6 +50649,9 @@ typedef struct sp_point_521 {
     sp_digit z[2 * 9];
     /* Indicates point is at infinity. */
     int infinity;
+#ifdef SP_ALIGN_16
+    byte pad[16-sizeof(int)];
+#endif
 } sp_point_521;
 
 /* The modulus (prime) of the curve P521. */
diff --git a/wolfcrypt/src/sp_x86_64_asm.S b/wolfcrypt/src/sp_x86_64_asm.S
index 9281f10170..ee87242c13 100644
--- a/wolfcrypt/src/sp_x86_64_asm.S
+++ b/wolfcrypt/src/sp_x86_64_asm.S
@@ -66736,7 +66736,11 @@ _sp_521_get_point_33_9:
         movq	$0x01, %r12
         movq	$0x01, %rax
         movd	%edx, %xmm13
+#ifndef SP_ALIGN_16
         addq	$0x1b8, %rsi
+#else
+        addq	$0x1c0, %rsi
+#endif /* !SP_ALIGN_16 */
         movd	%eax, %xmm15
         movq	$32, %rax
         pshufd	$0x00, %xmm15, %xmm15
@@ -66767,7 +66771,11 @@ L_521_get_point_33_9_start_1:
         movq	64(%rsi), %r8
         movdqu	144(%rsi), %xmm10
         movdqu	160(%rsi), %xmm11
+#ifndef SP_ALIGN_16
         addq	$0x1b8, %rsi
+#else
+        addq	$0x1c0, %rsi
+#endif /* !SP_ALIGN_16 */
         pand	%xmm12, %xmm6
         pand	%xmm12, %xmm7
         pand	%xmm12, %xmm8
@@ -66794,7 +66802,11 @@ L_521_get_point_33_9_start_1:
         movq	$0x01, %r12
         movq	$0x01, %rax
         movd	%edx, %xmm13
+#ifndef SP_ALIGN_16
         subq	$0x3700, %rsi
+#else
+        subq	$0x1b800, %rsi
+#endif /* !SP_ALIGN_16 */
         movd	%eax, %xmm15
         movq	$32, %rax
         pshufd	$0x00, %xmm15, %xmm15
@@ -66826,7 +66838,11 @@ L_521_get_point_33_9_start_2:
         movdqu	320(%rsi), %xmm10
         movdqu	336(%rsi), %xmm11
         movq	352(%rsi), %r9
+#ifndef SP_ALIGN_16
         addq	$0x1b8, %rsi
+#else
+        addq	$0x1c0, %rsi
+#endif /* !SP_ALIGN_16 */
         pand	%xmm12, %xmm6
         pand	%xmm12, %xmm7
         pand	%xmm12, %xmm8
@@ -66883,7 +66899,11 @@ _sp_521_get_point_33_avx2_9:
         movq	$0x01, %r14
         movq	$0x01, %rax
         movd	%edx, %xmm13
+#ifndef SP_ALIGN_16
         addq	$0x1b8, %rsi
+#else
+        addq	$0x1c0, %rsi
+#endif /* !SP_ALIGN_16 */
         movd	%eax, %xmm15
         movq	$32, %rax
         vpxor	%ymm14, %ymm14, %ymm14
@@ -66916,7 +66936,11 @@ L_521_get_point_33_avx2_9_start:
         movq	64(%rsi), %r11
         movq	208(%rsi), %r12
         movq	352(%rsi), %r13
+#ifndef SP_ALIGN_16
         addq	$0x1b8, %rsi
+#else
+        addq	$0x1c0, %rsi
+#endif /* !SP_ALIGN_16 */
         vpand	%ymm12, %ymm6, %ymm6
         vpand	%ymm12, %ymm7, %ymm7
         vpand	%ymm12, %ymm8, %ymm8
diff --git a/wolfcrypt/src/sp_x86_64_asm.asm b/wolfcrypt/src/sp_x86_64_asm.asm
index fcce0f5ea4..638f874949 100644
--- a/wolfcrypt/src/sp_x86_64_asm.asm
+++ b/wolfcrypt/src/sp_x86_64_asm.asm
@@ -65067,7 +65067,11 @@ sp_521_get_point_33_9 PROC
         mov	r14, 1
         mov	rax, 1
         movd	xmm13, r8d
+IFNDEF SP_ALIGN_16
         add	rdx, 440
+ELSE
+        add	rdx, 448
+ENDIF
         movd	xmm15, eax
         mov	rax, 32
         pshufd	xmm15, xmm15, 0
@@ -65098,7 +65102,11 @@ L_521_get_point_33_9_start_1:
         mov	r10, QWORD PTR [rdx+64]
         movdqu	xmm10, OWORD PTR [rdx+144]
         movdqu	xmm11, OWORD PTR [rdx+160]
+IFNDEF SP_ALIGN_16
         add	rdx, 440
+ELSE
+        add	rdx, 448
+ENDIF
         pand	xmm6, xmm12
         pand	xmm7, xmm12
         pand	xmm8, xmm12
@@ -65125,7 +65133,11 @@ L_521_get_point_33_9_start_1:
         mov	r14, 1
         mov	rax, 1
         movd	xmm13, r8d
+IFNDEF SP_ALIGN_16
         sub	rdx, 14080
+ELSE
+        sub	rdx, 112640
+ENDIF
         movd	xmm15, eax
         mov	rax, 32
         pshufd	xmm15, xmm15, 0
@@ -65157,7 +65169,11 @@ L_521_get_point_33_9_start_2:
         movdqu	xmm10, OWORD PTR [rdx+320]
         movdqu	xmm11, OWORD PTR [rdx+336]
         mov	r11, QWORD PTR [rdx+352]
+IFNDEF SP_ALIGN_16
         add	rdx, 440
+ELSE
+        add	rdx, 448
+ENDIF
         pand	xmm6, xmm12
         pand	xmm7, xmm12
         pand	xmm8, xmm12
@@ -65229,7 +65245,11 @@ sp_521_get_point_33_avx2_9 PROC
         mov	rdi, 1
         mov	rax, 1
         movd	xmm13, r8d
+IFNDEF SP_ALIGN_16
         add	rdx, 440
+ELSE
+        add	rdx, 448
+ENDIF
         movd	xmm15, eax
         mov	rax, 32
         vpxor	ymm14, ymm14, ymm14
@@ -65262,7 +65282,11 @@ L_521_get_point_33_avx2_9_start:
         mov	r13, QWORD PTR [rdx+64]
         mov	r14, QWORD PTR [rdx+208]
         mov	r15, QWORD PTR [rdx+352]
+IFNDEF SP_ALIGN_16
         add	rdx, 440
+ELSE
+        add	rdx, 448
+ENDIF
         vpand	ymm6, ymm6, ymm12
         vpand	ymm7, ymm7, ymm12
         vpand	ymm8, ymm8, ymm12