Implementation notes: amd64, h3neo, crypto_aead/norx6444v3

Computer: h3neo
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: norx6444v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
49409? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016122320161220
49413? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016122320161220
49428? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016122320161220
49438? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016122320161220
49922? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016122320161220
49929? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016122320161220
49941? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016122320161220
49951? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016122320161220
49963? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016122320161220
50014? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016122320161220
50592? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016122320161220
50626? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016122320161220
50662? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016122320161220
51165? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016122320161220
51177? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016122320161220
51360? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016122320161220
51381? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016122320161220
51522? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016122320161220
51525? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016122320161220
51542? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016122320161220
51559? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016122320161220
51582? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016122320161220
51780? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016122320161220
51789? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016122320161220
51805? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016122320161220
51836? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016122320161220
51847? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016122320161220
51913? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016122320161220
51930? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016122320161220
51933? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016122320161220
52027? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016122320161220
52031? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016122320161220
52035? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016122320161220
52052? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016122320161220
52218? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016122320161220
52233? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016122320161220
52282? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016122320161220
52298? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016122320161220
52304? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016122320161220
52330? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016122320161220
52413? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016122320161220
52421? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016122320161220
52515? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016122320161220
52754? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016122320161220
52778? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016122320161220
52812? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016122320161220
52880? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016122320161220
52894? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016122320161220
52945? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016122320161220
52982? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016122320161220
53016? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016122320161220
53118? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016122320161220
53361? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016122320161220
53458? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016122320161220
53638? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016122320161220
53642? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016122320161220
53726? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016122320161220
53768? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016122320161220
53837? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016122320161220
53882? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016122320161220
54113? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016122320161220
54155? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016122320161220
54165? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016122320161220
54169? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016122320161220
54429? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016122320161220
54597? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016122320161220
54708? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016122320161220
54712? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016122320161220
54723? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016122320161220
54735? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016122320161220
54749? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016122320161220
54839? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016122320161220
54882? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016122320161220
54910? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016122320161220
55218? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016122320161220
58371? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016122320161220
58429? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016122320161220
58485? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016122320161220
58485? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016122320161220
58516? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016122320161220
58523? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016122320161220
58526? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016122320161220
58543? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016122320161220
58560? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016122320161220
58574? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016122320161220
58764? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016122320161220
58854? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016122320161220
58866? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016122320161220
58890? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016122320161220
58907? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016122320161220
58975? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016122320161220
59073? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016122320161220
81107? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016122320161220
81134? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016122320161220
81141? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016122320161220
81148? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016122320161220
96419? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016122320161220
96521? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016122320161220
293806? ? ?? ? ?refgcc_-funroll-loops2016122320161220
293888? ? ?? ? ?refgcc2016122320161220
293996? ? ?? ? ?refcc2016122320161220

Test failure

Implementation: crypto_aead/norx6444v3/ref
Compiler: gcc -m64 -march=core2 -O3 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ref

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