Implementation notes: amd64, hydra2, crypto_aead/hs1sivhiv1

Computer: hydra2
Architecture: amd64
CPU ID: GenuineIntel-000206c2-bfebfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: hs1sivhiv1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
66076	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20141014	20141014
66156	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20141014	20141014
68332	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20141014	20141014
68436	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20141014	20141014
68596	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20141014	20141014
69044	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20141014	20141014
69076	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20141014	20141014
72756	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20141014	20141014
72824	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20141014	20141014
74288	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20141014	20141014
74388	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141014	20141014
74404	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20141014	20141014
74476	`ref`	`gcc -O3 -fomit-frame-pointer`	20141014	20141014
74512	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20141014	20141014
74628	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20141014	20141014
74672	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20141014	20141014
74712	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20141014	20141014
74720	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20141014	20141014
74820	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer`	20141014	20141014
74868	`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`	20141014	20141014
74888	`ref`	`clang -O3 -fomit-frame-pointer`	20141014	20141014
74892	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141014	20141014
74952	`ref`	`clang -O3 -fwrapv -march=native -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141014	20141014
74972	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20141014	20141014
75036	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141014	20141014
75192	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20141014	20141014
75208	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20141014	20141014
75236	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20141014	20141014
75404	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20141014	20141014
75512	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20141014	20141014
79376	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20141014	20141014
79492	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20141014	20141014
80340	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20141014	20141014
80348	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20141014	20141014
80508	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20141014	20141014
80952	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20141014	20141014
80964	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20141014	20141014
81528	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20141014	20141014
81548	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141014	20141014
87804	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20141014	20141014
87940	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20141014	20141014
88352	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20141014	20141014
88400	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20141014	20141014
90636	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20141014	20141014
90660	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20141014	20141014
90764	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20141014	20141014
90776	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20141014	20141014
90788	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20141014	20141014
90800	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20141014	20141014
90960	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20141014	20141014
90988	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20141014	20141014
92388	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20141014	20141014
92440	`ref`	`gcc -O2 -fomit-frame-pointer`	20141014	20141014
101504	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20141014	20141014
101680	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20141014	20141014
102968	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20141014	20141014
103188	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20141014	20141014
103308	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20141014	20141014
104856	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20141014	20141014
104916	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20141014	20141014
104920	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20141014	20141014
104928	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20141014	20141014
105188	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20141014	20141014
105508	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20141014	20141014
105524	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20141014	20141014
105548	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20141014	20141014
105600	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20141014	20141014
105604	`ref`	`gcc -Os -fomit-frame-pointer`	20141014	20141014
105604	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20141014	20141014
107308	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20141014	20141014
107420	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20141014	20141014
107568	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20141014	20141014
107784	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20141014	20141014
107788	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20141014	20141014
107804	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20141014	20141014
107912	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20141014	20141014
219884	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20141014	20141014
219924	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20141014	20141014
220248	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20141014	20141014
220412	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20141014	20141014
221328	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20141014	20141014
221336	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20141014	20141014
221476	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20141014	20141014
221512	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20141014	20141014
221628	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20141014	20141014
230584	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20141014	20141014
230680	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20141014	20141014
234124	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20141014	20141014
234320	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20141014	20141014
234472	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20141014	20141014
234512	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20141014	20141014
234580	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20141014	20141014
234612	`ref`	`gcc -O -fomit-frame-pointer`	20141014	20141014
234624	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20141014	20141014
234676	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20141014	20141014
234792	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20141014	20141014
234832	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20141014	20141014
234872	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20141014	20141014
235012	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20141014	20141014
624984	`ref`	`gcc`	20141014	20141014
625700	`ref`	`cc`	20141014	20141014
627612	`ref`	`gcc -funroll-loops`	20141014	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: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv1/ref
Compiler: clang -O3 -fomit-frame-pointer

try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer	ref
clang -O3 -fwrapv -march=native -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/hs1sivhiv1/dolbeau/amd64-avx2
Compiler: clang -O3 -fwrapv -march=native -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer

encrypt.c: clang: warning: argument unused during compilation: '-fpolly'
encrypt.c: clang: warning: argument unused during compilation: '-fvectorize'
encrypt.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
encrypt.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'
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: ...