Implementation notes: x86, kizomba, crypto_aead/norx6444v3

Computer: kizomba
Architecture: x86
CPU ID: GenuineIntel-000906e9-bfebfbff
SUPERCOP version: 20181216
Operation: crypto_aead
Primitive: norx6444v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
13998	`ymm`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20180824	20180818
14131	`ymm`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180824	20180818
14553	`ymm`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180824	20180818
14562	`ymm`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20180824	20180818
14936	`ymm`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20180824	20180818
14955	`ymm`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20180824	20180818
15147	`ymm`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20180824	20180818
15260	`ymm`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20180824	20180818
93552	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20180824	20180818
94579	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180824	20180818
96030	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20180824	20180818
96674	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20180824	20180818
96849	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20180824	20180818
97182	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20180824	20180818
97772	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20180824	20180818
98089	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20180824	20180818
100042	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180824	20180818
100388	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20180824	20180818
100706	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20180824	20180818
100810	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20180824	20180818
100861	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180824	20180818
101198	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20180824	20180818
101585	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20180824	20180818
101772	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20180824	20180818
101929	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180824	20180818
101989	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20180824	20180818
102033	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20180824	20180818
102147	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20180824	20180818
102292	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20180824	20180818
102522	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20180824	20180818
102597	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20180824	20180818
102708	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20180824	20180818
102881	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20180824	20180818
103032	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20180824	20180818
106029	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180824	20180818
107518	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20180824	20180818
109004	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20180824	20180818
110230	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20180824	20180818
110436	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20180824	20180818
110539	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20180824	20180818
110662	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20180824	20180818
110720	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20180824	20180818
110758	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20180824	20180818
110825	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20180824	20180818
110859	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20180824	20180818
110895	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20180824	20180818
110939	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20180824	20180818
111081	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20180824	20180818
111141	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20180824	20180818
111175	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20180824	20180818
111186	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20180824	20180818
111288	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20180824	20180818
111565	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20180824	20180818
111645	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20180824	20180818
111710	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20180824	20180818
111768	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20180824	20180818
111887	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20180824	20180818
112129	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20180824	20180818
112302	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20180824	20180818
112391	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180824	20180818
112659	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20180824	20180818
113083	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20180824	20180818
113387	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20180824	20180818
113742	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20180824	20180818
113913	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20180824	20180818
114024	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20180824	20180818
114327	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20180824	20180818
114415	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20180824	20180818
114551	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180824	20180818
115385	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20180824	20180818
116510	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180824	20180818
116523	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20180824	20180818
117291	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180824	20180818
117329	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20180824	20180818
117410	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20180824	20180818
117528	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20180824	20180818
117574	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180824	20180818
117924	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20180824	20180818
117945	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180824	20180818
137901	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20180824	20180818
138839	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20180824	20180818
138956	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20180824	20180818
148605	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20180824	20180818
148621	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20180824	20180818
149150	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20180824	20180818
149836	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20180824	20180818
150246	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20180824	20180818
150491	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20180824	20180818
150651	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20180824	20180818
150899	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20180824	20180818
151075	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20180824	20180818
151089	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20180824	20180818
151158	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20180824	20180818
151274	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20180824	20180818
151356	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20180824	20180818
151565	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20180824	20180818
151692	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20180824	20180818
151742	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20180824	20180818
151958	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20180824	20180818
151961	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20180824	20180818
152044	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20180824	20180818
152208	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20180824	20180818
152514	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20180824	20180818
152702	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20180824	20180818
152704	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20180824	20180818
152721	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20180824	20180818
152786	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20180824	20180818
152937	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20180824	20180818
153105	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20180824	20180818
153171	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20180824	20180818
153264	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20180824	20180818
153799	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20180824	20180818
153877	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20180824	20180818
155308	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20180824	20180818
155316	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20180824	20180818
155354	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20180824	20180818
155355	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20180824	20180818
155407	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20180824	20180818
155514	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20180824	20180818
155617	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20180824	20180818
155715	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20180824	20180818
155759	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20180824	20180818
156431	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20180824	20180818
156552	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20180824	20180818
156552	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20180824	20180818
156734	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20180824	20180818
156800	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20180824	20180818
157212	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20180824	20180818
157351	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20180824	20180818
157538	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20180824	20180818
157633	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20180824	20180818
157728	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20180824	20180818
157772	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20180824	20180818
157944	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20180824	20180818
158000	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20180824	20180818
158052	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20180824	20180818
158455	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20180824	20180818
158486	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20180824	20180818
158552	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20180824	20180818
158792	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20180824	20180818
159111	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20180824	20180818
159147	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20180824	20180818
160058	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20180824	20180818
160162	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20180824	20180818
160340	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20180824	20180818
160504	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20180824	20180818
160672	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20180824	20180818
160966	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20180824	20180818
161712	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20180824	20180818
161873	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20180824	20180818
162321	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20180824	20180818
163602	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20180824	20180818
163782	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20180824	20180818
164296	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20180824	20180818
164443	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180824	20180818
165339	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20180824	20180818
166340	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180824	20180818
166787	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180824	20180818
166905	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20180824	20180818
170418	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20180824	20180818
170849	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180824	20180818
171825	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20180824	20180818
172562	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180824	20180818
173532	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180824	20180818
173726	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180824	20180818
177075	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180824	20180818
185766	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20180824	20180818
186609	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20180824	20180818
186875	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20180824	20180818
221808	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180824	20180818
292652	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20180824	20180818
293903	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20180824	20180818
294385	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20180824	20180818
325277	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20180824	20180818
326534	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20180824	20180818
332000	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180824	20180818
336190	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180824	20180818
337492	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180824	20180818
338216	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180824	20180818
352229	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180824	20180818
363113	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20180824	20180818
365833	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20180824	20180818
379327	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20180824	20180818
385506	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20180824	20180818

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/7/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/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: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/7/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: 68, 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 -O3 -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 -O3 -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 -O3 -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=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/7/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/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: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/7/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1295:1: 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: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/7/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/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: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/7/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1295:1: 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: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/7/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/7/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: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/7/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/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: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/7/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: ...

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

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