Implementation notes: amd64, skylake, crypto_aead/norx6444v3

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: norx6444v3

Test failure

Implementation: crypto_aead/norx6444v3/ref
Compiler: cc

error 111
crypto_aead_encrypt does not handle k=c overlap

Number of similar (compiler,implementation) pairs: 133, namely:

Compiler	Implementations
cc	ref
clang -O3 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ref ymm
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ref ymm
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	ref ymm
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref ymm
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
gcc	ref
gcc -O2 -fomit-frame-pointer	ref
gcc -O3 -fomit-frame-pointer	ref
gcc -O -fomit-frame-pointer	ref
gcc -Os -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops	ref
gcc -funroll-loops -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -O -fomit-frame-pointer	ref
gcc -funroll-loops -Os -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	ref
gcc -m64 -O2 -fomit-frame-pointer	ref
gcc -m64 -O3 -fomit-frame-pointer	ref
gcc -m64 -O -fomit-frame-pointer	ref
gcc -m64 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	ref ymm
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer	ref ymm
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	ref ymm
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	ref ymm
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	ref ymm
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	ref ymm
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	ref ymm
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	ref ymm
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -march=barcelona -O -fomit-frame-pointer	ref
gcc -march=barcelona -Os -fomit-frame-pointer	ref
gcc -march=k8 -O2 -fomit-frame-pointer	ref
gcc -march=k8 -O3 -fomit-frame-pointer	ref
gcc -march=k8 -O -fomit-frame-pointer	ref
gcc -march=k8 -Os -fomit-frame-pointer	ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	ref ymm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	ref ymm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	ref ymm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	ref ymm
gcc -march=nocona -O2 -fomit-frame-pointer	ref
gcc -march=nocona -O3 -fomit-frame-pointer	ref
gcc -march=nocona -O -fomit-frame-pointer	ref
gcc -march=nocona -Os -fomit-frame-pointer	ref

Test failure

Implementation: crypto_aead/norx6444v3/ref
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

error 111
crypto_aead_encrypt does not handle k=c overlap
error 111
crypto_aead_encrypt does not handle k=c overlap

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -O -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: cc

Number of similar (compiler,implementation) pairs: 87, namely:

Compiler	Implementations
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 -O3 -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 -O3 -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 -O3 -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=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=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:656:3: 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, key);
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:656:3: 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: norx.c:255:7: note: expanded from macro 'INITIALISE'
norx.c: B = 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:656:3: 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:656:3: 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:656:3: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'avx2'
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
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 -mavx -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:656:3: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'avx2'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^
norx.c: norx.c:258:7: note: expanded from macro 'INITIALISE'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:63:19: note: expanded from macro 'XOR'
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:656:3: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'avx2'
norx.c: norx.c:259:3: note: expanded from macro 'INITIALISE'
norx.c: PERMUTE(A, B, C, D); \
norx.c: ^
norx.c: norx.c:186:5: note: expanded from macro 'PERMUTE'
norx.c: F(A, B, C, D); \
norx.c: ^
norx.c: norx.c:177:3: note: expanded from macro 'F'
norx.c: G(A, B, C, D); \
norx.c: ^
norx.c: norx.c:98:10: note: expanded from macro 'G'
norx.c: t0 = XOR( A, B); \
norx.c: ^
norx.c: norx.c:63:19: note: expanded from macro 'XOR'
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	ymm
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -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:254:5: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: 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:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:254:5: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: 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:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
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

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: 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:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/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: note: 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:656:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	ymm