diff --git a/cham-simd.cpp b/cham-simd.cpp
index 1bab32b2..341ab3fb 100644
--- a/cham-simd.cpp
+++ b/cham-simd.cpp
@@ -310,7 +310,7 @@ inline __m128i RepackXMM(const __m128i& v)
     return UnpackXMM<IDX>(v);
 }
 
-inline void GCC_NO_UBSAN CHAM64_Enc_Block(__m128i &block0,
+inline void CHAM64_Enc_Block(__m128i &block0,
     const word16 *subkeys, unsigned int /*rounds*/)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -427,7 +427,7 @@ inline void GCC_NO_UBSAN CHAM64_Enc_Block(__m128i &block0,
     block0 = RepackXMM<0>(a,b,c,d,e,f,g,h);
 }
 
-inline void GCC_NO_UBSAN CHAM64_Dec_Block(__m128i &block0,
+inline void CHAM64_Dec_Block(__m128i &block0,
     const word16 *subkeys, unsigned int /*rounds*/)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -552,7 +552,7 @@ inline void GCC_NO_UBSAN CHAM64_Dec_Block(__m128i &block0,
     block0 = RepackXMM<0>(a,b,c,d,e,f,g,h);
 }
 
-inline void GCC_NO_UBSAN CHAM64_Enc_2_Blocks(__m128i &block0,
+inline void CHAM64_Enc_2_Blocks(__m128i &block0,
     __m128i &block1, const word16 *subkeys, unsigned int /*rounds*/)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -670,7 +670,7 @@ inline void GCC_NO_UBSAN CHAM64_Enc_2_Blocks(__m128i &block0,
     block1 = RepackXMM<1>(a,b,c,d,e,f,g,h);
 }
 
-inline void GCC_NO_UBSAN CHAM64_Dec_2_Blocks(__m128i &block0,
+inline void CHAM64_Dec_2_Blocks(__m128i &block0,
     __m128i &block1, const word16 *subkeys, unsigned int /*rounds*/)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -946,7 +946,7 @@ inline __m128i RepackXMM(const __m128i& v)
     return UnpackXMM<IDX>(v);
 }
 
-inline void GCC_NO_UBSAN CHAM128_Enc_Block(__m128i &block0,
+inline void CHAM128_Enc_Block(__m128i &block0,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -1012,7 +1012,7 @@ inline void GCC_NO_UBSAN CHAM128_Enc_Block(__m128i &block0,
     block0 = RepackXMM<0>(a,b,c,d);
 }
 
-inline void GCC_NO_UBSAN CHAM128_Dec_Block(__m128i &block0,
+inline void CHAM128_Dec_Block(__m128i &block0,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -1082,7 +1082,7 @@ inline void GCC_NO_UBSAN CHAM128_Dec_Block(__m128i &block0,
     block0 = RepackXMM<0>(a,b,c,d);
 }
 
-inline void GCC_NO_UBSAN CHAM128_Enc_4_Blocks(__m128i &block0, __m128i &block1,
+inline void CHAM128_Enc_4_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
@@ -1151,7 +1151,7 @@ inline void GCC_NO_UBSAN CHAM128_Enc_4_Blocks(__m128i &block0, __m128i &block1,
     block3 = RepackXMM<3>(a,b,c,d);
 }
 
-inline void GCC_NO_UBSAN CHAM128_Dec_4_Blocks(__m128i &block0, __m128i &block1,
+inline void CHAM128_Dec_4_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. UnpackXMM includes a
diff --git a/lea-simd.cpp b/lea-simd.cpp
index 75e710b7..9394dff3 100644
--- a/lea-simd.cpp
+++ b/lea-simd.cpp
@@ -917,7 +917,7 @@ inline void LEA_Decryption(__m128i temp[4], const word32 *subkeys, unsigned int
     temp[3] = Xor(Sub(RotateLeft<3>(temp[3]), Xor(temp[2], LoadKey<4>(subkeys))), LoadKey<5>(subkeys));
 }
 
-inline void GCC_NO_UBSAN LEA_Enc_Block(__m128i &block0,
+inline void LEA_Enc_Block(__m128i &block0,
     const word32 *subkeys, unsigned int rounds)
 {
     __m128i temp[4];
@@ -931,7 +931,7 @@ inline void GCC_NO_UBSAN LEA_Enc_Block(__m128i &block0,
     block0 = RepackXMM<0>(temp[0], temp[1], temp[2], temp[3]);
 }
 
-inline void GCC_NO_UBSAN LEA_Dec_Block(__m128i &block0,
+inline void LEA_Dec_Block(__m128i &block0,
     const word32 *subkeys, unsigned int rounds)
 {
     __m128i temp[4];
@@ -945,7 +945,7 @@ inline void GCC_NO_UBSAN LEA_Dec_Block(__m128i &block0,
     block0 = RepackXMM<0>(temp[0], temp[1], temp[2], temp[3]);
 }
 
-inline void GCC_NO_UBSAN LEA_Enc_4_Blocks(__m128i &block0, __m128i &block1,
+inline void LEA_Enc_4_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, const word32 *subkeys, unsigned int rounds)
 {
     __m128i temp[4];
@@ -962,7 +962,7 @@ inline void GCC_NO_UBSAN LEA_Enc_4_Blocks(__m128i &block0, __m128i &block1,
     block3 = RepackXMM<3>(temp[0], temp[1], temp[2], temp[3]);
 }
 
-inline void GCC_NO_UBSAN LEA_Dec_4_Blocks(__m128i &block0, __m128i &block1,
+inline void LEA_Dec_4_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, const word32 *subkeys, unsigned int rounds)
 {
     __m128i temp[4];
diff --git a/simon-simd.cpp b/simon-simd.cpp
index b947cdd3..b496dee2 100644
--- a/simon-simd.cpp
+++ b/simon-simd.cpp
@@ -607,7 +607,7 @@ inline __m128i SIMON128_f(const __m128i& v)
         _mm_and_si128(RotateLeft64<1>(v), RotateLeft64<8>(v)));
 }
 
-inline void GCC_NO_UBSAN SIMON128_Enc_Block(__m128i &block0, __m128i &block1,
+inline void SIMON128_Enc_Block(__m128i &block0, __m128i &block1,
     const word64 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -642,7 +642,7 @@ inline void GCC_NO_UBSAN SIMON128_Enc_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi64(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SIMON128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SIMON128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word64 *subkeys, unsigned int rounds)
 {
@@ -691,7 +691,7 @@ inline void GCC_NO_UBSAN SIMON128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     block5 = _mm_unpackhi_epi64(y3, x3);
 }
 
-inline void GCC_NO_UBSAN SIMON128_Dec_Block(__m128i &block0, __m128i &block1,
+inline void SIMON128_Dec_Block(__m128i &block0, __m128i &block1,
     const word64 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -727,7 +727,7 @@ inline void GCC_NO_UBSAN SIMON128_Dec_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi64(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SIMON128_Dec_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SIMON128_Dec_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word64 *subkeys, unsigned int rounds)
 {
@@ -818,7 +818,7 @@ inline __m128i SIMON64_f(const __m128i& v)
         _mm_and_si128(RotateLeft32<1>(v), RotateLeft32<8>(v)));
 }
 
-inline void GCC_NO_UBSAN SIMON64_Enc_Block(__m128i &block0, __m128i &block1,
+inline void SIMON64_Enc_Block(__m128i &block0, __m128i &block1,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -853,7 +853,7 @@ inline void GCC_NO_UBSAN SIMON64_Enc_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi32(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SIMON64_Dec_Block(__m128i &block0, __m128i &block1,
+inline void SIMON64_Dec_Block(__m128i &block0, __m128i &block1,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -889,7 +889,7 @@ inline void GCC_NO_UBSAN SIMON64_Dec_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi32(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SIMON64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SIMON64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word32 *subkeys, unsigned int rounds)
 {
@@ -945,7 +945,7 @@ inline void GCC_NO_UBSAN SIMON64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     block5 = _mm_unpackhi_epi32(y3, x3);
 }
 
-inline void GCC_NO_UBSAN SIMON64_Dec_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SIMON64_Dec_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word32 *subkeys, unsigned int rounds)
 {
diff --git a/speck-simd.cpp b/speck-simd.cpp
index f9be52e4..2c01fd51 100644
--- a/speck-simd.cpp
+++ b/speck-simd.cpp
@@ -537,7 +537,7 @@ inline __m128i RotateRight64<8>(const __m128i& val)
     return _mm_shuffle_epi8(val, mask);
 }
 
-inline void GCC_NO_UBSAN SPECK128_Enc_Block(__m128i &block0, __m128i &block1,
+inline void SPECK128_Enc_Block(__m128i &block0, __m128i &block1,
     const word64 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -564,7 +564,7 @@ inline void GCC_NO_UBSAN SPECK128_Enc_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi64(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SPECK128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SPECK128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word64 *subkeys, unsigned int rounds)
 {
@@ -610,7 +610,7 @@ inline void GCC_NO_UBSAN SPECK128_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     block5 = _mm_unpackhi_epi64(y3, x3);
 }
 
-inline void GCC_NO_UBSAN SPECK128_Dec_Block(__m128i &block0, __m128i &block1,
+inline void SPECK128_Dec_Block(__m128i &block0, __m128i &block1,
     const word64 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -637,7 +637,7 @@ inline void GCC_NO_UBSAN SPECK128_Dec_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi64(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SPECK128_Dec_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SPECK128_Dec_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word64 *subkeys, unsigned int rounds)
 {
@@ -717,7 +717,7 @@ inline __m128i RotateRight32<8>(const __m128i& val)
     return _mm_shuffle_epi8(val, mask);
 }
 
-inline void GCC_NO_UBSAN SPECK64_Enc_Block(__m128i &block0, __m128i &block1,
+inline void SPECK64_Enc_Block(__m128i &block0, __m128i &block1,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -747,7 +747,7 @@ inline void GCC_NO_UBSAN SPECK64_Enc_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi32(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SPECK64_Dec_Block(__m128i &block0, __m128i &block1,
+inline void SPECK64_Dec_Block(__m128i &block0, __m128i &block1,
     const word32 *subkeys, unsigned int rounds)
 {
     // Rearrange the data for vectorization. The incoming data was read into
@@ -777,7 +777,7 @@ inline void GCC_NO_UBSAN SPECK64_Dec_Block(__m128i &block0, __m128i &block1,
     block1 = _mm_unpackhi_epi32(y1, x1);
 }
 
-inline void GCC_NO_UBSAN SPECK64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SPECK64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word32 *subkeys, unsigned int rounds)
 {
@@ -832,7 +832,7 @@ inline void GCC_NO_UBSAN SPECK64_Enc_6_Blocks(__m128i &block0, __m128i &block1,
     block5 = _mm_unpackhi_epi32(y3, x3);
 }
 
-inline void GCC_NO_UBSAN SPECK64_Dec_6_Blocks(__m128i &block0, __m128i &block1,
+inline void SPECK64_Dec_6_Blocks(__m128i &block0, __m128i &block1,
     __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,
     const word32 *subkeys, unsigned int rounds)
 {