Implementation notes: amd64, h8bobcat, crypto_aead/xoodyakv1

Computer: h8bobcat
Microarchitecture: amd64; Bobcat (500f10)
Architecture: amd64
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20240107
Operation: crypto_aead
Primitive: xoodyakv1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
14340712665 0 028836 824 856T:xkcp/plain-uaclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
14397310967 0 023950 816 856T:xkcp/plain-uaclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
14460012376 0 028164 824 856T:xkcp/plain-uaclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
14461411432 0 025116 824 856T:xkcp/plain-uaclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
14492711840 0 026484 824 856T:xkcp/plain-uaclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
16840712411 0 025680 768 896T:xkcp/plain-uagcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
16966513132 0 027757 792 928T:xkcp/plain-uagcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
17302812982 0 027989 792 928T:xkcp/plain-uagcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
17828214480 0 030973 792 928T:xkcp/plain-uagcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
1944516022 0 020652 824 856T:refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
1948126390 0 022164 824 856T:refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
1956486830 0 022980 824 856T:refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
4397939916 0 026413 792 928T:refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
8280104830 0 017838 816 856T:refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
11032645690 0 020661 792 928T:refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
11456915305 0 018972 824 856T:refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
14616085559 0 020157 792 928T:refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
41045084609 0 017896 768 896T:refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
849972642240 176 14061777 1232 1008T:refcppclang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
908669354104 176 12675870 1752 1104T:refcppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
957460932541 176 14049748 1248 1000T:refcppclang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
959250240094 176 14058505 1232 1008T:refcppclang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
1003016238966 200 14056458 1256 1008T:refcppclang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121820231212
1062502844101 176 12664845 1776 1104T:refcppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
1237639136025 176 12655987 1784 1104T:refcppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212
1949815730974 176 12649570 1248 1072T:refcppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121820231212

Compiler output

Implementation: T:xkcp/AVR8
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:2:16: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; The eXtended Keccak Code Package (XKCP)
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:5:14: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; The Xoodoo permutation, designed by Joan Daemen, Seth Hoffert, Gilles Van Assche and Ronny Van Keer.
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:7:21: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; Implementation by Ronny Van Keer, hereby denoted as "the implementer".
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:9:12: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; For more information, feedback or questions, please refer to the Keccak Team website:
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:10:3: error: symbol 'https' is already defined
Xoodoo-avr8-u1.s: ; https://keccak.team/
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:12:10: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; To the extent possible under law, the implementer has waived all copyright
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:13:15: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ; and related or neighboring rights to the source code in this file.
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:16:3: error: unexpected token at start of statement
Xoodoo-avr8-u1.s: ; ---
Xoodoo-avr8-u1.s: ^
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:18:13: error: unexpected token in argument list
Xoodoo-avr8-u1.s: ...

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVR8
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVR8
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVR8
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVR8
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVR8

Compiler output

Implementation: T:xkcp/AVR8
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s: Assembler messages:
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:2: Error: no such instruction: `the eXtended Keccak Code Package (XKCP)'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:5: Error: no such instruction: `the Xoodoo permutation,designed by Joan Daemen,Seth Hoffert,Gilles Van Assche and Ronny Van Keer.'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:7: Error: no such instruction: `implementation by Ronny Van Keer,hereby denoted as "the implementer".'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:9: Error: no such instruction: `for more information,feedback or questions,please refer to the Keccak Team website:'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:12: Error: no such instruction: `to the extent possible under law,the implementer has waived all copyright'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:13: Error: junk `or neighboring rights to the source code in this file.' after expression
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:13: Error: number of operands mismatch for `and'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:16: Error: junk at end of line, first unrecognized character is `-'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:18: Error: no such instruction: `this file implements Xoodoo in a SnP-compatible way.'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:19: Error: no such instruction: `please refer to SnP-documentation.h for more details.'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:21: Error: no such instruction: `this implementation comes with Xoodoo-SnP.h in the same folder.'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:22: Error: no such instruction: `please refer to LowLevel.build for the exact list of other files it must be combined with.'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:25: Error: no such instruction: `tested on ATmega1280 simulator'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:27: Error: no such instruction: `registers used in all routines'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:35: Error: junk at end of line, first unrecognized character is `-'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:37: Error: no such instruction: `void Xoodoo_StaticInitialize( void)'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:41: Error: junk at end of line, first unrecognized character is `-'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:43: Error: no such instruction: `void Xoodoo_Initialize(void *state)'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:45: Error: no such instruction: `argument state is passed in r24:r25'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:49: Error: too many memory references for `mov'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:50: Error: no such instruction: `ldi r23,3*4/2'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:50: Error: no such instruction: `clear state (8 bytes/2 lanes)per iteration'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:52: Error: no such instruction: `st z+,zero'
Xoodoo-avr8-u1.s: Xoodoo-avr8-u1.s:53: Error: no such instruction: `st z+,zero'
Xoodoo-avr8-u1.s: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVR8
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVR8
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVR8
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVR8

Compiler output

Implementation: T:xkcp/AVX512
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:379:9: error: '__builtin_ia32_pternlogd128_mask' needs target feature avx512vl
Xoodoo-SIMD512.c: Round(RC[i]);
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:328:29: note: expanded from macro 'Round'
Xoodoo-SIMD512.c: p = XOR3( a0, a1, a2 ); \
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:311:33: note: expanded from macro 'XOR3'
Xoodoo-SIMD512.c: #define XOR3(a,b,c) _mm_ternarylogic_epi32(a,b,c,0x96)
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx512vlintrin.h:6529:13: note: expanded from macro '_mm_ternarylogic_epi32'
Xoodoo-SIMD512.c: ((__m128i)__builtin_ia32_pternlogd128_mask((__v4si)(__m128i)(A), \
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:379:9: error: '__builtin_ia32_prold128' needs target feature avx512vl
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:330:29: note: expanded from macro 'Round'
Xoodoo-SIMD512.c: e = ROL32( p, 5 ); \
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:305:33: note: expanded from macro 'ROL32'
Xoodoo-SIMD512.c: #define ROL32(a, o) _mm_rol_epi32(a, o)
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx512vlintrin.h:4301:13: note: expanded from macro '_mm_rol_epi32'
Xoodoo-SIMD512.c: ((__m128i)__builtin_ia32_prold128((__v4si)(__m128i)(a), (int)(b)))
Xoodoo-SIMD512.c: ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:379:9: error: '__builtin_ia32_prold128' needs target feature avx512vl
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:331:29: note: expanded from macro 'Round'
Xoodoo-SIMD512.c: p = ROL32( p, 14 ); \
Xoodoo-SIMD512.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVX512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVX512
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVX512
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVX512
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/AVX512

Compiler output

Implementation: T:xkcp/AVX512
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c: In function 'Xoofff_AddIs':
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:429:16: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
Xoodoo-SIMD512.c: 429 | lanes1 = LOAD512u(input[ 0]);
Xoodoo-SIMD512.c: | ^
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:442:16: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
Xoodoo-SIMD512.c: 442 | lanesA = LOAD256u(input[0]);
Xoodoo-SIMD512.c: | ^
Xoodoo-SIMD512.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:57,
Xoodoo-SIMD512.c: from Xoodoo-SIMD512.c:24:
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c: In function 'Xoodoo_Permute_Nrounds':
Xoodoo-SIMD512.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx512vlintrin.h:11579:1: error: inlining failed in call to 'always_inline' '_mm_rol_epi32': target specific option mismatch
Xoodoo-SIMD512.c: 11579 | _mm_rol_epi32 (__m128i __A, const int __B)
Xoodoo-SIMD512.c: | ^~~~~~~~~~~~~
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:305:33: note: called from here
Xoodoo-SIMD512.c: 305 | #define ROL32(a, o) _mm_rol_epi32(a, o)
Xoodoo-SIMD512.c: | ^~~~~~~~~~~~~~~~~~~
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:353:30: note: in expansion of macro 'ROL32'
Xoodoo-SIMD512.c: 353 | a1 = ROL32(a1, 1); \
Xoodoo-SIMD512.c: | ^~~~~
Xoodoo-SIMD512.c: Xoodoo-SIMD512.c:379:9: note: in expansion of macro 'Round'
Xoodoo-SIMD512.c: 379 | Round(RC[i]);
Xoodoo-SIMD512.c: | ^~~~~
Xoodoo-SIMD512.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:57,
Xoodoo-SIMD512.c: from Xoodoo-SIMD512.c:24:
Xoodoo-SIMD512.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx512vlintrin.h:10681:1: error: inlining failed in call to 'always_inline' '_mm_ternarylogic_epi32': target specific option mismatch
Xoodoo-SIMD512.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVX512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVX512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVX512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/AVX512

Compiler output

Implementation: T:xkcp/SSE2
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Xoodyak-full-block-SIMD128.c: Xoodyak-full-block-SIMD128.c:337:14: error: '__builtin_ia32_vec_set_v2di' needs target feature sse4.1
Xoodyak-full-block-SIMD128.c: a1 = _mm_insert_epi64(a1, *((uint64_t*)(I+16)), 0);
Xoodyak-full-block-SIMD128.c: ^
Xoodyak-full-block-SIMD128.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/smmintrin.h:993:13: note: expanded from macro '_mm_insert_epi64'
Xoodyak-full-block-SIMD128.c: ((__m128i)__builtin_ia32_vec_set_v2di((__v2di)(__m128i)(X), \
Xoodyak-full-block-SIMD128.c: ^
Xoodyak-full-block-SIMD128.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/SSE2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/SSE2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/SSE2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/SSE2

Compiler output

Implementation: T:xkcp/SSE2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Xoodoo-SIMD128.c: Xoodoo-SIMD128.c:288:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'Xoodoo_Permute_Nrounds' that is compiled without support for 'ssse3'
Xoodoo-SIMD128.c: Round(RC[i]);
Xoodoo-SIMD128.c: ^
Xoodoo-SIMD128.c: Xoodoo-SIMD128.c:263:25: note: expanded from macro 'Round'
Xoodoo-SIMD128.c: Rho_east(); \
Xoodoo-SIMD128.c: ^
Xoodoo-SIMD128.c: Xoodoo-SIMD128.c:251:30: note: expanded from macro 'Rho_east'
Xoodoo-SIMD128.c: a2 = _mm_shuffle_epi8( a2, rhoEast2);
Xoodoo-SIMD128.c: ^
Xoodoo-SIMD128.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:xkcp/SSE2

Compiler output

Implementation: T:xkcp/SSE2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
Xoodyak-full-block-SIMD128.c: In file included from Xoodyak-full-block-SIMD128.c:24:
Xoodyak-full-block-SIMD128.c: Xoodyak-full-block-SIMD128.c: In function 'Xoodyak_DecryptFullBlocks':
Xoodyak-full-block-SIMD128.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:415:1: error: inlining failed in call to 'always_inline' '_mm_insert_epi64': target specific option mismatch
Xoodyak-full-block-SIMD128.c: 415 | _mm_insert_epi64 (__m128i __D, long long __S, const int __N)
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: Xoodyak-full-block-SIMD128.c:337:14: note: called from here
Xoodyak-full-block-SIMD128.c: 337 | a1 = _mm_insert_epi64(a1, *((uint64_t*)(I+16)), 0);
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: In file included from Xoodyak-full-block-SIMD128.c:24:
Xoodyak-full-block-SIMD128.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
Xoodyak-full-block-SIMD128.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: Xoodyak-full-block-SIMD128.c:336:55: note: called from here
Xoodyak-full-block-SIMD128.c: 336 | *((uint64_t*)(O+16)) = *((uint64_t*)(I+16)) ^ _mm_extract_epi64(a1, 0);
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: In file included from Xoodyak-full-block-SIMD128.c:24:
Xoodyak-full-block-SIMD128.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:415:1: error: inlining failed in call to 'always_inline' '_mm_insert_epi64': target specific option mismatch
Xoodyak-full-block-SIMD128.c: 415 | _mm_insert_epi64 (__m128i __D, long long __S, const int __N)
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: Xoodyak-full-block-SIMD128.c:337:14: note: called from here
Xoodyak-full-block-SIMD128.c: 337 | a1 = _mm_insert_epi64(a1, *((uint64_t*)(I+16)), 0);
Xoodyak-full-block-SIMD128.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xoodyak-full-block-SIMD128.c: In file included from Xoodyak-full-block-SIMD128.c:24:
Xoodyak-full-block-SIMD128.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:455:1: error: inlining failed in call to 'always_inline' '_mm_extract_epi64': target specific option mismatch
Xoodyak-full-block-SIMD128.c: 455 | _mm_extract_epi64 (__m128i __X, const int __N)
Xoodyak-full-block-SIMD128.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/SSE2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/SSE2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/SSE2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:xkcp/SSE2