Implementation notes: amd64, h8bobcat, crypto_aead/norx6444v3

Computer: h8bobcat
Architecture: amd64
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: norx6444v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
61223? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017081320170718
61384? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017081320170718
61531? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017081320170718
61612? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017081320170718
61665? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017081320170718
61812? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017081320170718
61855? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017081320170718
62182? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017081320170718
62202? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017081320170718
62235? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017081320170718
62287? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017081320170718
62287? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017081320170718
62448? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017081320170718
62467? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017081320170718
63374? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017081320170718
63441? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017081320170718
63536? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017081320170718
63550? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017081320170718
63688? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017081320170718
63731? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017081320170718
63740? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017081320170718
63806? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017081320170718
63821? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017081320170718
63835? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017081320170718
63873? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017081320170718
63878? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017081320170718
63897? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017081320170718
63935? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017081320170718
63935? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017081320170718
63988? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017081320170718
63992? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017081320170718
64073? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017081320170718
64120? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017081320170718
64135? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017081320170718
64158? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017081320170718
64182? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017081320170718
64187? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017081320170718
64286? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017081320170718
64363? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017081320170718
64453? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017081320170718
64500? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017081320170718
64743? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017081320170718
64752? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017081320170718
64809? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017081320170718
64833? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017081320170718
64999? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017081320170718
65037? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017081320170718
65042? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017081320170718
65094? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017081320170718
65189? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017081320170718
65189? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017081320170718
65379? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017081320170718
65697? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017081320170718
65730? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017081320170718
65754? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017081320170718
65773? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017081320170718
65859? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017081320170718
65892? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017081320170718
65939? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017081320170718
65963? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017081320170718
66120? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017081320170718
66219? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017081320170718
66272? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017081320170718
66477? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017081320170718
66481? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017081320170718
66496? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017081320170718
66500? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017081320170718
66510? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017081320170718
66538? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017081320170718
66557? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017081320170718
66585? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017081320170718
66610? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017081320170718
66648? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017081320170718
66656? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017081320170718
66770? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017081320170718
66913? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017081320170718
68742? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017081320170718
68780? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017081320170718
68833? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017081320170718
68837? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017081320170718
68861? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017081320170718
68875? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017081320170718
68946? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017081320170718
68960? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017081320170718
68960? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017081320170718
69051? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017081320170718
69084? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017081320170718
69164? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017081320170718
69212? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017081320170718
69236? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017081320170718
69350? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017081320170718
69374? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017081320170718
69426? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017081320170718
80113? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081320170718
80294? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081320170718
80313? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2017081320170718
80389? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081320170718
82825? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017081320170718
83144? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2017081320170718
378722? ? ?? ? ?refgcc2017081320170718
383986? ? ?? ? ?refgcc_-funroll-loops2017081320170718
388160? ? ?? ? ?refcc2017081320170718

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: cc
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:653:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^
norx.c: norx.c:258:5: error: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:657:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^
norx.c: norx.c:63:19: error: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:258:7: note: in expansion of macro 'XOR'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ...

Number of similar (compiler,implementation) pairs: 92, namely:
CompilerImplementations
cc ymm
gcc ymm
gcc -O2 -fomit-frame-pointer ymm
gcc -O3 -fomit-frame-pointer ymm
gcc -O -fomit-frame-pointer ymm
gcc -Os -fomit-frame-pointer ymm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer ymm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer ymm
gcc -fno-schedule-insns -O -fomit-frame-pointer ymm
gcc -fno-schedule-insns -Os -fomit-frame-pointer ymm
gcc -funroll-loops ymm
gcc -funroll-loops -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -O -fomit-frame-pointer ymm
gcc -funroll-loops -Os -fomit-frame-pointer ymm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer ymm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -O -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -Os -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer ymm
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer ymm
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer ymm
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer ymm
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer ymm
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer ymm
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer ymm
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer ymm
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer ymm
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer ymm
gcc -m64 -O2 -fomit-frame-pointer ymm
gcc -m64 -O3 -fomit-frame-pointer ymm
gcc -m64 -O -fomit-frame-pointer ymm
gcc -m64 -Os -fomit-frame-pointer ymm
gcc -m64 -march=core2 -O2 -fomit-frame-pointer ymm
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ymm
gcc -m64 -march=core2 -O -fomit-frame-pointer ymm
gcc -m64 -march=core2 -Os -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer ymm
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer ymm
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer ymm
gcc -m64 -march=corei7 -O -fomit-frame-pointer ymm
gcc -m64 -march=corei7 -Os -fomit-frame-pointer ymm
gcc -m64 -march=k8 -O2 -fomit-frame-pointer ymm
gcc -m64 -march=k8 -O3 -fomit-frame-pointer ymm
gcc -m64 -march=k8 -O -fomit-frame-pointer ymm
gcc -m64 -march=k8 -Os -fomit-frame-pointer ymm
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer ymm
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer ymm
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer ymm
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer ymm
gcc -m64 -march=nocona -O2 -fomit-frame-pointer ymm
gcc -m64 -march=nocona -O3 -fomit-frame-pointer ymm
gcc -m64 -march=nocona -O -fomit-frame-pointer ymm
gcc -m64 -march=nocona -Os -fomit-frame-pointer ymm
gcc -march=barcelona -O2 -fomit-frame-pointer ymm
gcc -march=barcelona -O3 -fomit-frame-pointer ymm
gcc -march=barcelona -O -fomit-frame-pointer ymm
gcc -march=barcelona -Os -fomit-frame-pointer ymm
gcc -march=k8 -O2 -fomit-frame-pointer ymm
gcc -march=k8 -O3 -fomit-frame-pointer ymm
gcc -march=k8 -O -fomit-frame-pointer ymm
gcc -march=k8 -Os -fomit-frame-pointer ymm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv ymm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv ymm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv ymm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv ymm
gcc -march=nocona -O2 -fomit-frame-pointer ymm
gcc -march=nocona -O3 -fomit-frame-pointer ymm
gcc -march=nocona -O -fomit-frame-pointer ymm
gcc -march=nocona -Os -fomit-frame-pointer ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
norx.c: norx.c:653:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: norx.c:254:7: note: expanded from macro 'INITIALISE'
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:256:7: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:257:7: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_xor_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:258:7: note: expanded from macro 'INITIALISE'
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments ymm
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ymm
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ymm
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
norx.c: norx.c:653:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: norx.c:254:7: note: expanded from macro 'INITIALISE'
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:256:7: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:257:7: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_xor_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:258:7: note: expanded from macro 'INITIALISE'
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments ymm
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:653:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^
norx.c: norx.c:258:5: error: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:657:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^
norx.c: norx.c:63:19: error: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:258:7: note: in expansion of macro 'XOR'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ...
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:653:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^
norx.c: norx.c:258:5: error: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:657:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^
norx.c: norx.c:63:19: error: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:258:7: note: in expansion of macro 'XOR'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer ymm
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer ymm
gcc -m64 -march=barcelona -O -fomit-frame-pointer ymm
gcc -m64 -march=barcelona -Os -fomit-frame-pointer ymm