Implementation notes: x86, titan0, crypto_aead/norx6444v3

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_aead
Primitive: norx6444v3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
14592	`ymm`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190708	20190110
14600	`ymm`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190708	20190110
15068	`ymm`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190708	20190110
15168	`ymm`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190708	20190110
15404	`ymm`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190708	20190110
15444	`ymm`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190708	20190110
15752	`ymm`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190708	20190110
15752	`ymm`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190708	20190110
99620	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20190708	20190110
104028	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20190708	20190110
104404	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20190708	20190110
104556	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20190708	20190110
104844	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20190708	20190110
105408	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20190708	20190110
105528	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20190708	20190110
107676	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190708	20190110
108928	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20190708	20190110
109096	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20190708	20190110
109628	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20190708	20190110
109720	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20190708	20190110
109788	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20190708	20190110
109792	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20190708	20190110
109868	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20190708	20190110
109916	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20190708	20190110
110080	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20190708	20190110
110124	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20190708	20190110
110144	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20190708	20190110
110220	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20190708	20190110
110284	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20190708	20190110
110316	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20190708	20190110
110624	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20190708	20190110
110700	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20190708	20190110
111068	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20190708	20190110
111668	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190708	20190110
111676	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20190708	20190110
114152	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20190708	20190110
117796	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20190708	20190110
117876	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20190708	20190110
120300	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20190708	20190110
120736	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20190708	20190110
120808	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20190708	20190110
121288	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20190708	20190110
122192	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20190708	20190110
122224	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20190708	20190110
125928	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190708	20190110
127464	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20190708	20190110
129964	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20190708	20190110
130112	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20190708	20190110
130432	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190708	20190110
130872	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20190708	20190110
131128	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20190708	20190110
131488	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20190708	20190110
131956	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20190708	20190110
132344	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20190708	20190110
132484	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20190708	20190110
134320	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20190708	20190110
141036	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190708	20190110
141472	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190708	20190110
141908	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190708	20190110
142428	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20190708	20190110
142956	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190708	20190110
143348	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20190708	20190110
143604	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190708	20190110
144048	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20190708	20190110
144140	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20190708	20190110
144348	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20190708	20190110
144476	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20190708	20190110
144496	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20190708	20190110
144580	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20190708	20190110
144872	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20190708	20190110
144996	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190708	20190110
145504	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20190708	20190110
146096	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20190708	20190110
146348	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20190708	20190110
146484	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20190708	20190110
146556	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20190708	20190110
146568	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20190708	20190110
146776	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20190708	20190110
146840	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20190708	20190110
147144	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20190708	20190110
147912	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20190708	20190110
148308	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20190708	20190110
148548	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20190708	20190110
149212	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20190708	20190110
173664	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20190708	20190110
173948	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20190708	20190110
174216	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20190708	20190110
174216	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20190708	20190110
175380	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190708	20190110
179664	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190708	20190110
179792	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20190708	20190110
180116	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20190708	20190110
180496	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20190708	20190110
180944	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20190708	20190110
182636	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20190708	20190110
183740	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20190708	20190110
187612	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20190708	20190110
187668	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20190708	20190110
187972	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20190708	20190110
188980	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20190708	20190110
189172	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190708	20190110
190152	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20190708	20190110
190636	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20190708	20190110
190700	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20190708	20190110
190732	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20190708	20190110
190804	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20190708	20190110
190896	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190708	20190110
191676	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20190708	20190110
192124	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20190708	20190110
192128	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20190708	20190110
192308	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190708	20190110
192368	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20190708	20190110
192620	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20190708	20190110
192780	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20190708	20190110
192852	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20190708	20190110
192936	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20190708	20190110
193076	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20190708	20190110
193332	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20190708	20190110
193344	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20190708	20190110
193516	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20190708	20190110
193604	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20190708	20190110
193652	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20190708	20190110
193696	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20190708	20190110
193732	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20190708	20190110
194036	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20190708	20190110
194320	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190708	20190110
194492	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190708	20190110
195092	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190708	20190110
195092	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20190708	20190110
195336	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20190708	20190110
195504	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20190708	20190110
196068	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20190708	20190110
196664	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190708	20190110
196680	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190708	20190110
196820	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20190708	20190110
196908	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20190708	20190110
196928	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190708	20190110
197076	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190708	20190110
197176	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20190708	20190110
197368	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20190708	20190110
197700	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190708	20190110
197976	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20190708	20190110
197992	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20190708	20190110
198176	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190708	20190110
198640	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20190708	20190110
198880	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190708	20190110
198936	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20190708	20190110
199016	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20190708	20190110
199020	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20190708	20190110
199272	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20190708	20190110
199336	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190708	20190110
199336	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20190708	20190110
199628	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20190708	20190110
199792	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20190708	20190110
200568	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20190708	20190110
200596	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20190708	20190110
200652	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20190708	20190110
201240	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20190708	20190110
201452	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20190708	20190110
201516	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20190708	20190110
201796	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20190708	20190110
202116	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20190708	20190110
202772	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20190708	20190110
203048	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20190708	20190110
203200	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20190708	20190110
204272	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20190708	20190110
204284	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20190708	20190110
204468	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20190708	20190110
204524	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20190708	20190110
204580	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20190708	20190110
204888	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20190708	20190110
205168	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20190708	20190110
325840	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20190708	20190110
327236	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20190708	20190110
364688	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20190708	20190110
364740	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20190708	20190110
367912	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190708	20190110
369216	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20190708	20190110
371220	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190708	20190110
384948	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20190708	20190110
402128	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20190708	20190110
406480	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20190708	20190110
425376	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20190708	20190110
428436	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20190708	20190110

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