Implementation notes: x86, hydra1, crypto_aead/norx6444v3

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: norx6444v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
197934	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161227	20161220
197962	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161227	20161220
198014	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161227	20161220
198067	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161227	20161220
198968	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161227	20161220
198976	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161227	20161220
200379	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161227	20161220
200430	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161227	20161220
200926	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161227	20161220
200941	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161227	20161220
200952	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161227	20161220
201042	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161227	20161220
201066	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161227	20161220
201365	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161227	20161220
201392	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161227	20161220
201394	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161227	20161220
201456	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161227	20161220
201467	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161227	20161220
201475	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161227	20161220
201477	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161227	20161220
201528	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161227	20161220
201573	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161227	20161220
201743	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161227	20161220
201800	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161227	20161220
201807	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161227	20161220
201838	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161227	20161220
204600	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161227	20161220
204608	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161227	20161220
204618	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161227	20161220
204640	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161227	20161220
204658	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161227	20161220
206274	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161227	20161220
206299	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161227	20161220
206309	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161227	20161220
206314	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161227	20161220
206319	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161227	20161220
213368	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161227	20161220
213389	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161227	20161220
213434	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161227	20161220
213508	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161227	20161220
213541	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161227	20161220
273606	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161227	20161220
276663	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161227	20161220
278414	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161227	20161220
279883	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161227	20161220
280037	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161227	20161220
281048	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161227	20161220
282019	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161227	20161220
282197	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161227	20161220
283507	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161227	20161220
283618	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161227	20161220
283637	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161227	20161220
283805	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161227	20161220
283952	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161227	20161220
285901	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161227	20161220
286053	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161227	20161220
286434	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161227	20161220
286874	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161227	20161220
286968	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161227	20161220
287391	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161227	20161220
287822	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161227	20161220
288258	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161227	20161220
288317	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161227	20161220
288320	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161227	20161220
288339	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161227	20161220
288370	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161227	20161220
288372	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161227	20161220
288672	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161227	20161220
288831	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161227	20161220
289696	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161227	20161220
289703	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161227	20161220
290024	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161227	20161220
290299	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161227	20161220
290319	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161227	20161220
290376	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161227	20161220
290384	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161227	20161220
290523	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161227	20161220
290752	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161227	20161220
290819	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161227	20161220
290888	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161227	20161220
290932	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161227	20161220
290989	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161227	20161220
291013	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161227	20161220
291064	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161227	20161220
291092	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161227	20161220
291139	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161227	20161220
291359	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161227	20161220
291360	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161227	20161220
291382	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161227	20161220
291384	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161227	20161220
291466	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161227	20161220
292088	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161227	20161220
292184	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161227	20161220
292217	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161227	20161220
292410	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161227	20161220
292657	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161227	20161220
292744	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161227	20161220
292749	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161227	20161220
292900	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161227	20161220
293338	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161227	20161220
293367	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161227	20161220
293472	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161227	20161220
293911	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161227	20161220
293964	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161227	20161220
293972	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161227	20161220
294011	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161227	20161220
294115	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161227	20161220
294201	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161227	20161220
294259	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161227	20161220
294567	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161227	20161220
294723	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161227	20161220
295137	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161227	20161220
296318	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161227	20161220
296322	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161227	20161220
296351	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161227	20161220
296490	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161227	20161220
296608	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161227	20161220
296677	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161227	20161220
296835	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161227	20161220
296866	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161227	20161220
296867	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161227	20161220
297480	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161227	20161220
297483	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161227	20161220
297642	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161227	20161220
297674	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161227	20161220
297685	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161227	20161220
297731	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161227	20161220
298202	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161227	20161220
298665	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161227	20161220
298692	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161227	20161220
298731	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161227	20161220
298803	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161227	20161220
298864	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161227	20161220
298875	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161227	20161220
299013	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161227	20161220
299015	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161227	20161220
299292	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161227	20161220
299709	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161227	20161220
299754	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161227	20161220
300811	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161227	20161220
301217	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161227	20161220
301312	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161227	20161220
301339	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161227	20161220
301351	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161227	20161220
301882	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161227	20161220
301884	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161227	20161220
301960	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161227	20161220
302596	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161227	20161220
302712	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161227	20161220
302992	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161227	20161220
303123	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161227	20161220
303148	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161227	20161220
303180	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161227	20161220
304283	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161227	20161220
304349	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161227	20161220
305469	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161227	20161220
305690	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161227	20161220
307954	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161227	20161220
307962	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161227	20161220
307998	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161227	20161220

Test failure

Implementation: crypto_aead/norx6444v3/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 13, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ref
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ref
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ref ymm
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ref ymm
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ref ymm
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -funroll-loops -m32 -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: norx.c:542:11: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
norx.c: S[ 0] = _mm256_broadcastq_epi64(_mm256_castsi256_si128(A)); \
norx.c: ^
norx.c: norx.c:584:5: note: in expansion of macro 'BRANCH_V4'
norx.c: BRANCH_V4(S, A, B, C, D); \
norx.c: ^
norx.c: norx.c:659:3: note: in expansion of macro 'ENCRYPT_DATA_V4'
norx.c: ENCRYPT_DATA_V4(A, B, C, D, c, m, mlen);
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: ...

Number of similar (compiler,implementation) pairs: 88, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	ymm
gcc -m32 -O2 -fomit-frame-pointer	ymm
gcc -m32 -O3 -fomit-frame-pointer	ymm
gcc -m32 -O -fomit-frame-pointer	ymm
gcc -m32 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=athlon -O -fomit-frame-pointer	ymm
gcc -m32 -march=athlon -Os -fomit-frame-pointer	ymm
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=i386 -O -fomit-frame-pointer	ymm
gcc -m32 -march=i386 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=i486 -O -fomit-frame-pointer	ymm
gcc -m32 -march=i486 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	ymm
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	ymm
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=k6 -O -fomit-frame-pointer	ymm
gcc -m32 -march=k6 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 69, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -O -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	ymm
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=corei7 -O -fomit-frame-pointer	ymm
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=k8 -O -fomit-frame-pointer	ymm
gcc -m32 -march=k8 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	ymm
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	ymm
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=nocona -O -fomit-frame-pointer	ymm
gcc -m32 -march=nocona -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	ymm
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	ymm
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=prescott -O -fomit-frame-pointer	ymm
gcc -m32 -march=prescott -Os -fomit-frame-pointer	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -m32 -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:

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -m32 -march=barcelona -O -fomit-frame-pointer	ymm
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

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: norx.c: In function 'norx_aead_encrypt':
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: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:43:0,
norx.c: from norx.c:19:
norx.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ymm
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ymm
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ymm
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ymm
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ymm