Implementation notes: x86, h4e450, crypto_aead/norx6444v3

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: norx6444v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
268769	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171001	20170725
268807	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171001	20170725
269815	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20171001	20170725
269862	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171001	20170725
269880	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171001	20170725
270845	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171001	20170725
270859	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171001	20170725
272735	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20171001	20170725
272859	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171001	20170725
272883	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20171001	20170725
272930	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20171001	20170725
273933	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20171001	20170725
273957	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20171001	20170725
275225	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20171001	20170725
275405	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171001	20170725
275609	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20171001	20170725
275728	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20171001	20170725
276155	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20171001	20170725
281238	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20171001	20170725
281433	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20171001	20170725
281879	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171001	20170725
282074	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20171001	20170725
282079	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20171001	20170725
283827	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171001	20170725
283889	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20171001	20170725
284259	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171001	20170725
284767	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171001	20170725
284820	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171001	20170725
285618	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20171001	20170725
285627	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20171001	20170725
285703	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20171001	20170725
285722	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171001	20170725
286064	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20171001	20170725
286116	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171001	20170725
286169	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171001	20170725
286358	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20171001	20170725
288320	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20171001	20170725
290021	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20171001	20170725
290069	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20171001	20170725
290101	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20171001	20170725
290192	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20171001	20170725
414337	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20171001	20170725
414367	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20171001	20170725
420503	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20171001	20170725
421135	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20171001	20170725
423211	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171001	20170725
424541	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20171001	20170725
425795	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20171001	20170725
426242	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20171001	20170725
427681	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20171001	20170725
427718	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20171001	20170725
427747	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20171001	20170725
428374	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20171001	20170725
429457	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20171001	20170725
429651	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171001	20170725
429955	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20171001	20170725
430587	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20171001	20170725
430645	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20171001	20170725
431286	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20171001	20170725
431799	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20171001	20170725
431965	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20171001	20170725
431979	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20171001	20170725
432412	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20171001	20170725
432421	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20171001	20170725
432844	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20171001	20170725
432868	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20171001	20170725
432892	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20171001	20170725
433361	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20171001	20170725
433376	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20171001	20170725
434601	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20171001	20170725
434606	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20171001	20170725
434649	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20171001	20170725
434792	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20171001	20170725
434796	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20171001	20170725
434796	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20171001	20170725
435200	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20171001	20170725
435242	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20171001	20170725
435413	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20171001	20170725
435751	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20171001	20170725
435756	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20171001	20170725
436140	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20171001	20170725
436173	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171001	20170725
436416	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171001	20170725
436643	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20171001	20170725
436995	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20171001	20170725
437290	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20171001	20170725
437437	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20171001	20170725
437485	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20171001	20170725
437679	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171001	20170725
437822	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20171001	20170725
438986	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171001	20170725
439099	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20171001	20170725
439698	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20171001	20170725
439888	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171001	20170725
439926	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20171001	20170725
440411	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20171001	20170725
440634	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20171001	20170725
440810	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20171001	20170725
440833	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20171001	20170725
440876	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171001	20170725
440962	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20171001	20170725
440967	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20171001	20170725
440975	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171001	20170725
441204	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20171001	20170725
441209	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171001	20170725
441280	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171001	20170725
441936	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20171001	20170725
443061	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171001	20170725
443109	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20171001	20170725
443930	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171001	20170725
444134	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20171001	20170725
444443	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171001	20170725
444605	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20171001	20170725
444742	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171001	20170725
444813	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171001	20170725
444861	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171001	20170725
444889	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171001	20170725
444961	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171001	20170725
445056	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20171001	20170725
445079	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20171001	20170725
445118	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20171001	20170725
445460	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20171001	20170725
445726	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171001	20170725
445802	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171001	20170725
445859	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20171001	20170725
446068	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171001	20170725
446391	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171001	20170725
446490	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171001	20170725
446504	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171001	20170725
446827	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20171001	20170725
447027	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171001	20170725
447236	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171001	20170725
448005	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20171001	20170725
448205	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20171001	20170725
448305	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20171001	20170725
448396	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171001	20170725
448457	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20171001	20170725
448528	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20171001	20170725
448656	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20171001	20170725
449112	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20171001	20170725
449141	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20171001	20170725
449972	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20171001	20170725
451254	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171001	20170725
451469	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20171001	20170725
451735	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171001	20170725
451801	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20171001	20170725
451986	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20171001	20170725
452000	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171001	20170725
452000	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20171001	20170725
452076	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171001	20170725
452243	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171001	20170725
452532	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171001	20170725
452713	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20171001	20170725
452903	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171001	20170725
454162	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171001	20170725
454309	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171001	20170725
454779	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171001	20170725
454789	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171001	20170725
454836	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171001	20170725
456314	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20171001	20170725
456732	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20171001	20170725

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: 12, 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=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