[Fix] Add clang wrong type bug detect macro when build in aarch64

[Fix] Modified ci.yml to skip RNDX series tests, which causes timeouts in loongarch64. [Fix] i686-linux-gnu-gcc-11: error: dereferencing type-punned pointer will break strict-aliasing rules [-Werror=strict-aliasing] [Fix] Detect __ARM_FEATURE_AES and __ARM_FEATURE_SHA2
simd-everywhere · Oct 27, 2023 · b0e4d8f · b0e4d8f
1 parent c9636fb
commit b0e4d8f
Show file tree

Hide file tree

Showing 14 changed files with 200 additions and 318 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -689,6 +689,13 @@ jobs:
         rm test/x86/svml.c
         echo "Due to the qemu versions 7.2 through 8.0 causing timeouts in four sets of test cases,"
         echo "the SVML tests have been temporarily disabled."
+    - name: Disable RND*X tests
+      run: |
+        sed -i "/rndx/d" meson.build
+        sed -i "/rnd..x/d" meson.build
+        rm test/arm/neon/rndx.c test/arm/neon/rnd32x.c test/arm/neon/rnd64x.c
+        echo "Due to the qemu versions 7.2 through 8.0 causing timeouts in four sets of test cases,"
+        echo "the RNDX, RND32X, and RND64X tests have been temporarily disabled."
     - name: Configure
       run: meson setup build --cross-file=docker/cross-files/loongarch64-gcc-13-ccache.cross
     - name: Build

diff --git a/simde/arm/neon/aes.h b/simde/arm/neon/aes.h
@@ -28,48 +28,13 @@
 #define SIMDE_ARM_NEON_AES_H
 
 #include "types.h"
+#include "../../simde-aes.h"
 
 HEDLEY_DIAGNOSTIC_PUSH
 SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
 SIMDE_BEGIN_DECLS_
 
 /* ref: https://github.com/kokke/tiny-AES-c/blob/master/aes.c */
-static const uint8_t sbox[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,
-  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
-  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
-  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
-  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
-  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
-  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
-  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
-  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
-  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
-  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
-  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
-  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
-  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
-  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
-  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16 };
-
-static const uint8_t rsbox[256] = {
-  0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
-  0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
-  0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
-  0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
-  0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
-  0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
-  0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
-  0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
-  0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
-  0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
-  0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
-  0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
-  0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
-  0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
-  0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
-  0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d };
 
 static uint8_t xtime(uint8_t x)
 {
@@ -79,7 +44,7 @@ static uint8_t xtime(uint8_t x)
 SIMDE_FUNCTION_ATTRIBUTES
 simde_uint8x16_t
 simde_vaeseq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
-  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE)
+  #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 */
@@ -116,7 +81,7 @@ simde_vaeseq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
 
     SIMDE_VECTORIZE
     for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
-      r_.values[i] = sbox[r_.values[i]];
+      r_.values[i] = simde_x_aes_s_box[r_.values[i]];
     }
     return simde_uint8x16_from_private(r_);
   #endif
@@ -129,7 +94,7 @@ simde_vaeseq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
 SIMDE_FUNCTION_ATTRIBUTES
 simde_uint8x16_t
 simde_vaesdq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
-  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE)
+  #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 */
@@ -164,7 +129,7 @@ simde_vaesdq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
     r_.values[11] = r_.values[15];
     r_.values[15] = tmp;
     for(int i = 0; i < 16; ++i) {
-      r_.values[i] = rsbox[r_.values[i]];
+      r_.values[i] = simde_x_aes_inv_s_box[r_.values[i]];
     }
     return simde_uint8x16_from_private(r_);
   #endif
@@ -177,7 +142,7 @@ simde_vaesdq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
 SIMDE_FUNCTION_ATTRIBUTES
 simde_uint8x16_t
 simde_vaesmcq_u8(simde_uint8x16_t data) {
-  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE)
+  #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 */
@@ -214,7 +179,7 @@ static uint8_t Multiply(uint8_t x, uint8_t y)
 SIMDE_FUNCTION_ATTRIBUTES
 simde_uint8x16_t
 simde_vaesimcq_u8(simde_uint8x16_t data) {
-  #if defined(SIMDE_ARM_NEON_A32V8_NATIVE)
+  #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 */

diff --git a/simde/arm/neon/copy_lane.h b/simde/arm/neon/copy_lane.h
@@ -866,13 +866,8 @@ simde_vcopy_lane_p8(simde_poly8x8_t a, const int lane1, simde_poly8x8_t b, const
   r_.values[lane1] = b_.values[lane2];
   return simde_poly8x8_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_lane_p8(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_lane_p8((a), (lane1), (b), (lane2)))
-  #else
-    #define simde_vcopy_lane_p8(a, lane1, b, lane2) vcopy_lane_p8((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_lane_p8(a, lane1, b, lane2) vcopy_lane_p8((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_lane_p8
@@ -891,13 +886,8 @@ simde_vcopy_lane_p16(simde_poly16x4_t a, const int lane1, simde_poly16x4_t b, co
   r_.values[lane1] = b_.values[lane2];
   return simde_poly16x4_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_lane_p16(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_lane_p16(a, lane1, b, lane2))
-  #else
-    #define simde_vcopy_lane_p16(a, lane1, b, lane2) vcopy_lane_p16((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_lane_p16(a, lane1, b, lane2) vcopy_lane_p16((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_lane_p16
@@ -916,13 +906,8 @@ simde_vcopy_lane_p64(simde_poly64x1_t a, const int lane1, simde_poly64x1_t b, co
   r_.values[lane1] = b_.values[lane2];
   return simde_poly64x1_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_lane_p64(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_lane_p64(a, lane1, b, lane2))
-  #else
-    #define simde_vcopy_lane_p64(a, lane1, b, lane2) vcopy_lane_p64((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_lane_p64(a, lane1, b, lane2) vcopy_lane_p64((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_lane_p64
@@ -942,13 +927,8 @@ simde_vcopy_laneq_p8(simde_poly8x8_t a, const int lane1, simde_poly8x16_t b, con
   r_.values[lane1] = b_.values[lane2];
   return simde_poly8x8_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_laneq_p8(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_laneq_p8(a, lane1, b, lane2))
-  #else
-    #define simde_vcopy_laneq_p8(a, lane1, b, lane2) vcopy_laneq_p8((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_laneq_p8(a, lane1, b, lane2) vcopy_laneq_p8((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_laneq_p8
@@ -968,13 +948,8 @@ simde_vcopy_laneq_p16(simde_poly16x4_t a, const int lane1, simde_poly16x8_t b, c
   r_.values[lane1] = b_.values[lane2];
   return simde_poly16x4_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_laneq_p16(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_laneq_p16(a, lane1, b, lane2))
-  #else
-    #define simde_vcopy_laneq_p16(a, lane1, b, lane2) vcopy_laneq_p16((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_laneq_p16(a, lane1, b, lane2) vcopy_laneq_p16((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_laneq_p16
@@ -994,13 +969,8 @@ simde_vcopy_laneq_p64(simde_poly64x1_t a, const int lane1, simde_poly64x2_t b, c
   r_.values[lane1] = b_.values[lane2];
   return simde_poly64x1_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopy_laneq_p64(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopy_laneq_p64(a, lane1, b, lane2))
-  #else
-    #define simde_vcopy_laneq_p64(a, lane1, b, lane2) vcopy_laneq_p64((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopy_laneq_p64(a, lane1, b, lane2) vcopy_laneq_p64((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopy_laneq_p64
@@ -1020,13 +990,8 @@ simde_vcopyq_lane_p8(simde_poly8x16_t a, const int lane1, simde_poly8x8_t b, con
   r_.values[lane1] = b_.values[lane2];
   return simde_poly8x16_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_lane_p8(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_lane_p8(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_lane_p8(a, lane1, b, lane2) vcopyq_lane_p8((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_lane_p8(a, lane1, b, lane2) vcopyq_lane_p8((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_lane_p8
@@ -1046,13 +1011,8 @@ simde_vcopyq_lane_p16(simde_poly16x8_t a, const int lane1, simde_poly16x4_t b, c
   r_.values[lane1] = b_.values[lane2];
   return simde_poly16x8_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_lane_p16(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_lane_p16(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_lane_p16(a, lane1, b, lane2) vcopyq_lane_p16((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_lane_p16(a, lane1, b, lane2) vcopyq_lane_p16((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_lane_p16
@@ -1072,13 +1032,8 @@ simde_vcopyq_lane_p64(simde_poly64x2_t a, const int lane1, simde_poly64x1_t b, c
   r_.values[lane1] = b_.values[lane2];
   return simde_poly64x2_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_lane_p64(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_lane_p64(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_lane_p64(a, lane1, b, lane2) vcopyq_lane_p64((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_lane_p64(a, lane1, b, lane2) vcopyq_lane_p64((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_lane_p64
@@ -1097,13 +1052,8 @@ simde_vcopyq_laneq_p8(simde_poly8x16_t a, const int lane1, simde_poly8x16_t b, c
   r_.values[lane1] = b_.values[lane2];
   return simde_poly8x16_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_laneq_p8(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_laneq_p8(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_laneq_p8(a, lane1, b, lane2) vcopyq_laneq_p8((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_laneq_p8(a, lane1, b, lane2) vcopyq_laneq_p8((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_laneq_p8
@@ -1122,13 +1072,8 @@ simde_vcopyq_laneq_p16(simde_poly16x8_t a, const int lane1, simde_poly16x8_t b,
   r_.values[lane1] = b_.values[lane2];
   return simde_poly16x8_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_laneq_p16(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_laneq_p16(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_laneq_p16(a, lane1, b, lane2) vcopyq_laneq_p16((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_laneq_p16(a, lane1, b, lane2) vcopyq_laneq_p16((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_laneq_p16
@@ -1147,13 +1092,8 @@ simde_vcopyq_laneq_p64(simde_poly64x2_t a, const int lane1, simde_poly64x2_t b,
   r_.values[lane1] = b_.values[lane2];
   return simde_poly64x2_from_private(r_);
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vcopyq_laneq_p64(a, lane1, b, lane2) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vcopyq_laneq_p64(a, lane1, b, lane2))
-  #else
-    #define simde_vcopyq_laneq_p64(a, lane1, b, lane2) vcopyq_laneq_p64((a), (lane1), (b), (lane2))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vcopyq_laneq_p64(a, lane1, b, lane2) vcopyq_laneq_p64((a), (lane1), (b), (lane2))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vcopyq_laneq_p64

diff --git a/simde/arm/neon/dup_lane.h b/simde/arm/neon/dup_lane.h
@@ -1626,13 +1626,8 @@ simde_vdupb_lane_p8(simde_poly8x8_t vec, const int lane)
     SIMDE_REQUIRE_CONSTANT_RANGE(lane, 0, 7) {
   return simde_poly8x8_to_private(vec).values[lane];
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vdupb_lane_p8(vec, lane) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vdupb_lane_p8(vec, lane))
-  #else
-    #define simde_vdupb_lane_p8(vec, lane) vdupb_lane_p8((vec), (lane))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vdupb_lane_p8(vec, lane) vdupb_lane_p8((vec), (lane))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vdupb_lane_p8
@@ -1645,13 +1640,8 @@ simde_vdupb_laneq_p8(simde_poly8x16_t vec, const int lane)
     SIMDE_REQUIRE_CONSTANT_RANGE(lane, 0, 15) {
   return simde_poly8x16_to_private(vec).values[lane];
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vdupb_laneq_p8(vec, lane) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vdupb_laneq_p8(vec, lane))
-  #else
-    #define simde_vdupb_laneq_p8(vec, lane) vdupb_laneq_p8((vec), (lane))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vdupb_laneq_p8(vec, lane) vdupb_laneq_p8((vec), (lane))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vdupb_laneq_p8
@@ -1664,13 +1654,8 @@ simde_vduph_lane_p16(simde_poly16x4_t vec, const int lane)
     SIMDE_REQUIRE_CONSTANT_RANGE(lane, 0, 3) {
   return simde_poly16x4_to_private(vec).values[lane];
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vduph_lane_p16(vec, lane) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vduph_lane_p16(vec, lane))
-  #else
-    #define simde_vduph_lane_p16(vec, lane) vduph_lane_p16((vec), (lane))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vduph_lane_p16(vec, lane) vduph_lane_p16((vec), (lane))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vduph_lane_p16
@@ -1683,13 +1668,8 @@ simde_vduph_laneq_p16(simde_poly16x8_t vec, const int lane)
     SIMDE_REQUIRE_CONSTANT_RANGE(lane, 0, 7) {
   return simde_poly16x8_to_private(vec).values[lane];
 }
-#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
-  #if defined(__clang__) && !SIMDE_DETECT_CLANG_VERSION_CHECK(11,0,0)
-    #define simde_vduph_laneq_p16(vec, lane) \
-    SIMDE_DISABLE_DIAGNOSTIC_EXPR_(SIMDE_DIAGNOSTIC_DISABLE_VECTOR_CONVERSION_, vduph_laneq_p16(vec, lane))
-  #else
-    #define simde_vduph_laneq_p16(vec, lane) vduph_laneq_p16((vec), (lane))
-  #endif
+#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && !defined(SIMDE_BUG_CLANG_BAD_VGET_SET_LANE_TYPES)
+  #define simde_vduph_laneq_p16(vec, lane) vduph_laneq_p16((vec), (lane))
 #endif
 #if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
   #undef vduph_laneq_p16