Implementation notes: amd64, h4e350, crypto_aead/hs1sivhiv1

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: hs1sivhiv1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
101946	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20141016	20141014
102021	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141016	20141014
102099	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20141016	20141014
102138	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20141016	20141014
102375	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20141016	20141014
102645	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20141016	20141014
102726	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20141016	20141014
103752	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20141016	20141014
103779	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20141016	20141014
109515	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20141016	20141014
109719	`ref`	`gcc -O3 -fomit-frame-pointer`	20141016	20141014
109779	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20141016	20141014
111222	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141016	20141014
111234	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20141016	20141014
111255	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20141016	20141014
112221	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20141016	20141014
112317	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20141016	20141014
114222	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141016	20141014
114267	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
114288	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20141016	20141014
114315	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141016	20141014
114399	`ref`	`clang -O3 -fomit-frame-pointer`	20141016	20141014
114444	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20141016	20141014
115617	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141016	20141014
116079	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20141016	20141014
116307	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20141016	20141014
116322	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20141016	20141014
116739	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20141016	20141014
117117	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20141016	20141014
117210	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20141016	20141014
117849	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20141016	20141014
118056	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20141016	20141014
118263	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20141016	20141014
121014	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20141016	20141014
124644	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20141016	20141014
124710	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20141016	20141014
125799	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141016	20141014
125817	`ref`	`gcc -O2 -fomit-frame-pointer`	20141016	20141014
125922	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20141016	20141014
125928	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20141016	20141014
125952	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20141016	20141014
125979	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20141016	20141014
126141	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20141016	20141014
126171	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20141016	20141014
126642	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20141016	20141014
126765	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20141016	20141014
127326	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20141016	20141014
130308	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20141016	20141014
142521	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20141016	20141014
142527	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20141016	20141014
142554	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20141016	20141014
142668	`ref`	`gcc -Os -fomit-frame-pointer`	20141016	20141014
142692	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20141016	20141014
142767	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20141016	20141014
143010	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20141016	20141014
143133	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20141016	20141014
144753	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20141016	20141014
144903	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20141016	20141014
144939	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20141016	20141014
144963	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20141016	20141014
144993	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20141016	20141014
144993	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20141016	20141014
145092	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20141016	20141014
145134	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20141016	20141014
145191	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20141016	20141014
145206	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20141016	20141014
145290	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20141016	20141014
145335	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20141016	20141014
145374	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20141016	20141014
146577	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20141016	20141014
147441	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20141016	20141014
277077	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20141016	20141014
277101	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20141016	20141014
282450	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20141016	20141014
282894	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20141016	20141014
286635	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20141016	20141014
287001	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20141016	20141014
297681	`ref`	`gcc -O -fomit-frame-pointer`	20141016	20141014
297807	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20141016	20141014
298092	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20141016	20141014
298113	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20141016	20141014
298182	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20141016	20141014
300597	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20141016	20141014
300705	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20141016	20141014
302037	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20141016	20141014
302394	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20141016	20141014
302853	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20141016	20141014
312165	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20141016	20141014
312348	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20141016	20141014
316206	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20141016	20141014
316308	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20141016	20141014
317538	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20141016	20141014
359976	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20141016	20141014
360102	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20141016	20141014
1053231	`ref`	`gcc`	20141016	20141014
1053453	`ref`	`cc`	20141016	20141014
1053930	`ref`	`gcc -funroll-loops`	20141016	20141014

Compiler output

Implementation: crypto_aead/hs1sivhiv1/dolbeau/amd64-avx2
Compiler: cc

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

Compiler	Implementations
cc	dolbeau/amd64-avx2
gcc	dolbeau/amd64-avx2
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops	dolbeau/amd64-avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv1/dolbeau/amd64-avx2
Compiler: clang -O3 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: In file included from encrypt.c:195:
encrypt.c: ./c368.h:110:3: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^
encrypt.c: ./c368.h:111:3: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i rot8 = _mm256_set_epi8(14,13,12,15,10,9,8,11,6,5,4,7,2,1,0,3,14,13,12,15,10,9,8,11,6,5,4,7,2,1,0,3);
encrypt.c: ^
encrypt.c: ./c368.h:115:1: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i x_0 = _mm256_set1_epi32(x[0]);
encrypt.c: ^
encrypt.c: ./c368.h:116:1: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i x_1 = _mm256_set1_epi32(x[1]);
encrypt.c: ^
encrypt.c: ./c368.h:117:1: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i x_2 = _mm256_set1_epi32(x[2]);
encrypt.c: ^
encrypt.c: ./c368.h:118:1: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i x_3 = _mm256_set1_epi32(x[3]);
encrypt.c: ^
encrypt.c: ./c368.h:119:1: error: use of undeclared identifier '__m256i'
encrypt.c: __m256i x_4 = _mm256_set1_epi32(x[4]);
encrypt.c: ^
encrypt.c: ...