Implementation notes: amd64, h5nano, crypto_aead/hs1sivhiv1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: hs1sivhiv1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
125395	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20141017	20141014
125395	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20141017	20141014
128535	`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`	20141017	20141014
128545	`ref`	`clang -O3 -fomit-frame-pointer`	20141017	20141014
128605	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20141017	20141014
128615	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141017	20141014
128615	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141017	20141014
130320	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20141017	20141014
130320	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20141017	20141014
130860	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20141017	20141014
130860	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20141017	20141014
130860	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20141017	20141014
131595	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141017	20141014
131610	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20141017	20141014
135660	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20141017	20141014
135660	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20141017	20141014
139725	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20141017	20141014
139760	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20141017	20141014
139765	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20141017	20141014
139775	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20141017	20141014
139850	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20141017	20141014
140170	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20141017	20141014
140310	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20141017	20141014
140475	`ref`	`gcc -O3 -fomit-frame-pointer`	20141017	20141014
140505	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20141017	20141014
140510	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20141017	20141014
141475	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141017	20141014
141640	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20141017	20141014
142875	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20141017	20141014
142930	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20141017	20141014
142980	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20141017	20141014
142980	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20141017	20141014
143670	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20141017	20141014
143670	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20141017	20141014
143730	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20141017	20141014
144805	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20141017	20141014
144860	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141017	20141014
155575	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20141017	20141014
155615	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20141017	20141014
160630	`ref`	`gcc -O2 -fomit-frame-pointer`	20141017	20141014
160695	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20141017	20141014
161140	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20141017	20141014
161180	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20141017	20141014
161490	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20141017	20141014
161550	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20141017	20141014
162000	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20141017	20141014
162035	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20141017	20141014
163025	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20141017	20141014
165560	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20141017	20141014
165600	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141017	20141014
174110	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20141017	20141014
174125	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20141017	20141014
174230	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20141017	20141014
174230	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20141017	20141014
174300	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20141017	20141014
174320	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20141017	20141014
174350	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20141017	20141014
174395	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20141017	20141014
174475	`ref`	`gcc -Os -fomit-frame-pointer`	20141017	20141014
174560	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20141017	20141014
174610	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20141017	20141014
174630	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20141017	20141014
174810	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20141017	20141014
174860	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20141017	20141014
174895	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20141017	20141014
174905	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20141017	20141014
174905	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20141017	20141014
174955	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20141017	20141014
175040	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20141017	20141014
176165	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20141017	20141014
176300	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20141017	20141014
176405	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20141017	20141014
179375	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20141017	20141014
179980	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20141017	20141014
322035	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20141017	20141014
322095	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20141017	20141014
322975	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20141017	20141014
324210	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20141017	20141014
324225	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20141017	20141014
324320	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20141017	20141014
324370	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20141017	20141014
327300	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20141017	20141014
328640	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20141017	20141014
341855	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20141017	20141014
343185	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20141017	20141014
347885	`ref`	`gcc -O -fomit-frame-pointer`	20141017	20141014
347970	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20141017	20141014
349270	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20141017	20141014
349330	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20141017	20141014
349370	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20141017	20141014
350195	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20141017	20141014
350235	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20141017	20141014
351545	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20141017	20141014
360580	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20141017	20141014
361975	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20141017	20141014
363660	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20141017	20141014
363665	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20141017	20141014
786350	`ref`	`gcc`	20141017	20141014
787755	`ref`	`gcc -funroll-loops`	20141017	20141014
787890	`ref`	`cc`	20141017	20141014

Compiler output

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

Number of similar (compiler,implementation) pairs: 91, 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 -O3 -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 -O3 -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 -O3 -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: ...