[NEON] Add AES instructions.

arm/neon.h

@@ -46,6 +46,7 @@
 #include "neon/addv.h"
 #include "neon/addw.h"
 #include "neon/addw_high.h"
+#include "neon/aes.h"
 #include "neon/and.h"
 #include "neon/bcax.h"
 #include "neon/bic.h"

arm/neon/aes.h

+/* SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy,
+ * modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Copyright:
+ *   2023      Yi-Yen Chung <eric681@andestech.com> (Copyright owned by Andes Technology)
+ */
+
+#if !defined(SIMDE_ARM_NEON_AES_H)
+#define SIMDE_ARM_NEON_AES_H
+
+#include "types.h"
+#include "../../simde-aes.h"
+
+HEDLEY_DIAGNOSTIC_PUSH
+SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
+SIMDE_BEGIN_DECLS_
+
+static uint8_t xtime(uint8_t x)
+{
+  return HEDLEY_STATIC_CAST(uint8_t, (x<<1) ^ (((x>>7) & 1) * 0x1b));
+}
+
+SIMDE_FUNCTION_ATTRIBUTES
+simde_uint8x16_t
+simde_vaeseq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
+  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(__ARM_FEATURE_AES)
+    return vaeseq_u8(data, key);
+  #else
+    /* ref: https://github.com/kokke/tiny-AES-c/blob/master/aes.c */
+    simde_uint8x16_private
+      r_,
+      a_ = simde_uint8x16_to_private(data),
+      b_ = simde_uint8x16_to_private(key);
+
+    SIMDE_VECTORIZE
+    for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
+      r_.values[i] = a_.values[i] ^ b_.values[i];
+    }
+    // AESShiftRows
+    uint8_t tmp;
+    tmp = r_.values[1];
+    r_.values[1] = r_.values[5];
+    r_.values[5] = r_.values[9];
+    r_.values[9] = r_.values[13];
+    r_.values[13] = tmp;
+
+    tmp = r_.values[2];
+    r_.values[2] = r_.values[10];
+    r_.values[10] = tmp;
+
+    tmp = r_.values[6];
+    r_.values[6] = r_.values[14];
+    r_.values[14] = tmp;
+
+    tmp = r_.values[3];
+    r_.values[3] = r_.values[15];
+    r_.values[15] = r_.values[11];
+    r_.values[11] = r_.values[7];
+    r_.values[7] = tmp;
+
+    SIMDE_VECTORIZE
+    for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
+      r_.values[i] = simde_x_aes_s_box[r_.values[i]];
+    }
+    return simde_uint8x16_from_private(r_);
+  #endif
+}
+#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
+  #undef vaeseq_u8
+  #define vaeseq_u8(data, key) simde_vaeseq_u8((data), (key))
+#endif
+
+SIMDE_FUNCTION_ATTRIBUTES
+simde_uint8x16_t
+simde_vaesdq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
+  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(__ARM_FEATURE_AES)
+    return vaesdq_u8(data, key);
+  #else
+    /* ref: https://github.com/kokke/tiny-AES-c/blob/master/aes.c */
+    simde_uint8x16_private
+      r_,
+      a_ = simde_uint8x16_to_private(data),
+      b_ = simde_uint8x16_to_private(key);
+
+    SIMDE_VECTORIZE
+    for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
+      r_.values[i] = a_.values[i] ^ b_.values[i];
+    }
+    // AESInvShiftRows
+    uint8_t tmp;
+    tmp = r_.values[13];
+    r_.values[13] = r_.values[9];
+    r_.values[9] = r_.values[5];
+    r_.values[5] = r_.values[1];
+    r_.values[1] = tmp;
+
+    tmp = r_.values[2];
+    r_.values[2] = r_.values[10];
+    r_.values[10] = tmp;
+
+    tmp = r_.values[6];
+    r_.values[6] = r_.values[14];
+    r_.values[14] = tmp;
+
+    tmp = r_.values[3];
+    r_.values[3] = r_.values[7];
+    r_.values[7] = r_.values[11];
+    r_.values[11] = r_.values[15];
+    r_.values[15] = tmp;
+    for(int i = 0; i < 16; ++i) {
+      r_.values[i] = simde_x_aes_inv_s_box[r_.values[i]];
+    }
+    return simde_uint8x16_from_private(r_);
+  #endif
+}
+#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
+  #undef vaesdq_u8
+  #define vaesdq_u8(data, key) simde_vaesdq_u8((data), (key))
+#endif
+
+SIMDE_FUNCTION_ATTRIBUTES
+simde_uint8x16_t
+simde_vaesmcq_u8(simde_uint8x16_t data) {
+  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(__ARM_FEATURE_AES)
+    return vaesmcq_u8(data);
+  #else
+    /* ref: https://github.com/kokke/tiny-AES-c/blob/master/aes.c */
+    simde_uint8x16_private
+      a_ = simde_uint8x16_to_private(data);
+    uint8_t i;
+    uint8_t Tmp, Tm, t;
+    for (i = 0; i < 4; ++i)
+    {
+      t   = a_.values[i*4+0];
+      Tmp = a_.values[i*4+0] ^ a_.values[i*4+1] ^ a_.values[i*4+2] ^ a_.values[i*4+3] ;
+      Tm  = a_.values[i*4+0] ^ a_.values[i*4+1] ; Tm = xtime(Tm);  a_.values[i*4+0] ^= Tm ^ Tmp ;
+      Tm  = a_.values[i*4+1] ^ a_.values[i*4+2] ; Tm = xtime(Tm);  a_.values[i*4+1] ^= Tm ^ Tmp ;
+      Tm  = a_.values[i*4+2] ^ a_.values[i*4+3] ; Tm = xtime(Tm);  a_.values[i*4+2] ^= Tm ^ Tmp ;
+      Tm  = a_.values[i*4+3] ^ t ;        Tm = xtime(Tm);  a_.values[i*4+3] ^= Tm ^ Tmp ;
+    }
+    return simde_uint8x16_from_private(a_);
+  #endif
+}
+#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
+  #undef vaesmcq_u8
+  #define vaesmcq_u8(data) simde_vaesmcq_u8((data))
+#endif
+
+static uint8_t Multiply(uint8_t x, uint8_t y)
+{
+  return (((y & 1) * x) ^
+       ((y>>1 & 1) * xtime(x)) ^
+       ((y>>2 & 1) * xtime(xtime(x))) ^
+       ((y>>3 & 1) * xtime(xtime(xtime(x)))) ^
+       ((y>>4 & 1) * xtime(xtime(xtime(xtime(x)))))); /* this last call to xtime() can be omitted */
+}
+
+SIMDE_FUNCTION_ATTRIBUTES
+simde_uint8x16_t
+simde_vaesimcq_u8(simde_uint8x16_t data) {
+  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(__ARM_FEATURE_AES)
+    return vaesimcq_u8(data);
+  #else
+    /* ref: https://github.com/kokke/tiny-AES-c/blob/master/aes.c */
+    simde_uint8x16_private
+      a_ = simde_uint8x16_to_private(data);
+    #if defined(SIMDE_X86_AES_NATIVE)
+      a_.m128i = _mm_aesimc_si128(a_.m128i);
+    #else
+      int i;
+      uint8_t a, b, c, d;
+      for (i = 0; i < 4; ++i)
+      {
+        a = a_.values[i*4+0];
+        b = a_.values[i*4+1];
+        c = a_.values[i*4+2];
+        d = a_.values[i*4+3];
+
+        a_.values[i*4+0] = Multiply(a, 0x0e) ^ Multiply(b, 0x0b) ^ Multiply(c, 0x0d) ^ Multiply(d, 0x09);
+        a_.values[i*4+1] = Multiply(a, 0x09) ^ Multiply(b, 0x0e) ^ Multiply(c, 0x0b) ^ Multiply(d, 0x0d);
+        a_.values[i*4+2] = Multiply(a, 0x0d) ^ Multiply(b, 0x09) ^ Multiply(c, 0x0e) ^ Multiply(d, 0x0b);
+        a_.values[i*4+3] = Multiply(a, 0x0b) ^ Multiply(b, 0x0d) ^ Multiply(c, 0x09) ^ Multiply(d, 0x0e);
+      }
+    #endif
+    return simde_uint8x16_from_private(a_);
+  #endif
+}
+#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
+  #undef vaesimcq_u8
+  #define vaesimcq_u8(data) simde_vaesimcq_u8((data))
+#endif
+
+SIMDE_END_DECLS_
+HEDLEY_DIAGNOSTIC_POP
+
+#endif /* !defined(SIMDE_ARM_NEON_AES_H) */

simde-aes.h

+/* SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy,
+ * modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Copyright:
+ *   2023      Yi-Yen Chung <eric681@andestech.com> (Copyright owned by Andes Technology)
+ */
+
+#if !defined(SIMDE_AES_H)
+#define SIMDE_AES_H
+
+#include "simde-features.h"
+
+HEDLEY_DIAGNOSTIC_PUSH
+SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
+
+#if !(defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO))
+
+/*
+ * Number of columns (32-bit words) comprising the State. For this
+ * standard, Nb = 4.
+ */
+#define simde_x_aes_Nb 4
+
+/*
+ * S-box transformation table
+ */
+static uint8_t simde_x_aes_s_box[256] = {
+  // 0     1     2     3     4     5     6     7     8     9     a     b     c     d     e     f
+  0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, // 0
+  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, // 1
+  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, // 2
+  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, // 3
+  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, // 4
+  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, // 5
+  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, // 6
+  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, // 7
+  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, // 8
+  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, // 9
+  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, // a
+  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, // b
+  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, // c
+  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, // d
+  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, // e
+  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16};// f
+
+/*
+ * Inverse S-box transformation table
+ */
+static uint8_t simde_x_aes_inv_s_box[256] = {
+  // 0     1     2     3     4     5     6     7     8     9     a     b     c     d     e     f
+  0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, // 0
+  0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, // 1
+  0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, // 2
+  0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, // 3
+  0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, // 4
+  0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, // 5
+  0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, // 6
+  0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, // 7
+  0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, // 8
+  0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, // 9
+  0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, // a
+  0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, // b
+  0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, // c
+  0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, // d
+  0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, // e
+  0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d};// f
+
+#endif
+
+HEDLEY_DIAGNOSTIC_POP
+
+#endif /* !defined(SIMDE_AES_H) */

x86/aes.h

@@ -237,56 +237,7 @@ void simde_x_aes_coef_mult_lookup(int lookup_table_offset, uint8_t *b, uint8_t *
   #undef gmultl
 }
 
-/*
- * Number of columns (32-bit words) comprising the State. For this
- * standard, Nb = 4.
- */
-#define simde_x_aes_Nb 4
-
-/*
- * S-box transformation table
- */
-static uint8_t simde_x_aes_s_box[256] = {
-  // 0     1     2     3     4     5     6     7     8     9     a     b     c     d     e     f
-  0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, // 0
-  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, // 1
-  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, // 2
-  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, // 3
-  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, // 4
-  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, // 5
-  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, // 6
-  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, // 7
-  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, // 8
-  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, // 9
-  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, // a
-  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, // b
-  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, // c
-  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, // d
-  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, // e
-  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16};// f
-
-/*
- * Inverse S-box transformation table
- */
-static uint8_t simde_x_aes_inv_s_box[256] = {
-  // 0     1     2     3     4     5     6     7     8     9     a     b     c     d     e     f
-  0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, // 0
-  0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, // 1
-  0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, // 2
-  0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, // 3
-  0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, // 4
-  0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, // 5
-  0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, // 6
-  0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, // 7
-  0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, // 8
-  0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, // 9
-  0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, // a
-  0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, // b
-  0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, // c
-  0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, // d
-  0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, // e
-  0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d};// f
-
+#include "../simde-aes.h"
 
 /*
  * Transformation in the Cipher and Inverse Cipher in which a Round
@@ -520,7 +471,7 @@ simde__m128i simde_mm_aesenc_si128(simde__m128i a, simde__m128i round_key) {
     simde__m128i_private result_;
     simde__m128i_private a_ = simde__m128i_to_private(a);
     simde__m128i_private round_key_ = simde__m128i_to_private(round_key);
-    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
+    #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
       result_.neon_u8 = veorq_u8(
         vaesmcq_u8(vaeseq_u8(a_.neon_u8, vdupq_n_u8(0))),
         round_key_.neon_u8);
@@ -542,7 +493,7 @@ simde__m128i simde_mm_aesdec_si128(simde__m128i a, simde__m128i round_key) {
     simde__m128i_private result_;
     simde__m128i_private a_ = simde__m128i_to_private(a);
     simde__m128i_private round_key_ = simde__m128i_to_private(round_key);
-    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
+    #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
       result_.neon_u8 = veorq_u8(
         vaesimcq_u8(vaesdq_u8(a_.neon_u8, vdupq_n_u8(0))),
         round_key_.neon_u8);
@@ -564,7 +515,7 @@ simde__m128i simde_mm_aesenclast_si128(simde__m128i a, simde__m128i round_key) {
     simde__m128i_private result_;
     simde__m128i_private a_ = simde__m128i_to_private(a);
     simde__m128i_private round_key_ = simde__m128i_to_private(round_key);
-    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
+    #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
       result_.neon_u8 = vaeseq_u8(a_.neon_u8, vdupq_n_u8(0));
       result_.neon_i32 = veorq_s32(result_.neon_i32, round_key_.neon_i32); // _mm_xor_si128
     #else
@@ -585,7 +536,7 @@ simde__m128i simde_mm_aesdeclast_si128(simde__m128i a, simde__m128i round_key) {
     simde__m128i_private result_;
     simde__m128i_private a_ = simde__m128i_to_private(a);
     simde__m128i_private round_key_ = simde__m128i_to_private(round_key);
-    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
+    #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
       result_.neon_u8 = veorq_u8(
         vaesdq_u8(a_.neon_u8, vdupq_n_u8(0)),
         round_key_.neon_u8);
@@ -607,7 +558,7 @@ simde__m128i simde_mm_aesimc_si128(simde__m128i a) {
     simde__m128i_private result_ = simde__m128i_to_private(simde_mm_setzero_si128());
     simde__m128i_private a_ = simde__m128i_to_private(a);
 
-    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
+    #if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && defined(SIMDE_ARCH_ARM_CRYPTO)
       result_.neon_u8 = vaesimcq_u8(a_.neon_u8);
     #else
       int Nb = simde_x_aes_Nb;