Implementation notes: amd64, genji262, crypto_sign/sphincsf128sha256

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20180818
Operation: crypto_sign
Primitive: sphincsf128sha256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
99046508	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20180820	20180818
99620664	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20180820	20180818
99768394	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20180820	20180818
100002848	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180820	20180818
100388376	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20180820	20180818
100416646	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20180820	20180818
100739276	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20180820	20180818
100810182	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20180820	20180818
100881638	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20180820	20180818
100886852	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20180820	20180818
100955470	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180820	20180818
101137960	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180820	20180818
101219250	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20180820	20180818
101323024	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20180820	20180818
101481314	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20180820	20180818
101596044	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20180820	20180818
101665696	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20180820	20180818
101747536	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20180820	20180818
101926308	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20180820	20180818
101962542	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20180820	20180818
102039608	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20180820	20180818
102193674	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20180820	20180818
102198536	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20180820	20180818
102391762	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20180820	20180818
102533618	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20180820	20180818
102548908	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20180820	20180818
102623884	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20180820	20180818
102624016	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20180820	20180818
102703370	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20180820	20180818
102752782	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20180820	20180818
102956920	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180820	20180818
103011392	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180820	20180818
103423870	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180820	20180818
103476912	`ref`	`gcc -O3 -fomit-frame-pointer`	20180820	20180818
103497130	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180820	20180818
103518316	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20180820	20180818
103679862	`ref`	`gcc -O2 -fomit-frame-pointer`	20180820	20180818
103750196	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180820	20180818
103772020	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180820	20180818
103942190	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20180820	20180818
104064708	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20180820	20180818
104076412	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20180820	20180818
104096190	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180820	20180818
104152752	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20180820	20180818
104159748	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20180820	20180818
104270342	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20180820	20180818
104304090	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20180820	20180818
104483918	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20180820	20180818
104489220	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20180820	20180818
104507282	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20180820	20180818
104679828	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180820	20180818
104933070	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20180820	20180818
104967192	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20180820	20180818
104991634	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20180820	20180818
105074024	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180820	20180818
105249980	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20180820	20180818
105717480	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180820	20180818
105768388	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180820	20180818
105790278	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20180820	20180818
105902148	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20180820	20180818
105931870	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180820	20180818
105983812	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20180820	20180818
106035314	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20180820	20180818
106113260	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20180820	20180818
106419170	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20180820	20180818
106491792	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20180820	20180818
106529786	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180820	20180818
106727874	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20180820	20180818
106834486	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180820	20180818
107012290	`ref`	`gcc -O -fomit-frame-pointer`	20180820	20180818
107122488	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20180820	20180818
107358812	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20180820	20180818
107421534	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20180820	20180818
107540422	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20180820	20180818
107795974	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20180820	20180818
107836652	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20180820	20180818
108232850	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20180820	20180818
108325382	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20180820	20180818
108583860	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180820	20180818
108585862	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20180820	20180818
109934374	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20180820	20180818
113733994	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20180820	20180818
114021578	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20180820	20180818
114844642	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20180820	20180818
114975696	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180820	20180818
115084178	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20180820	20180818
115186412	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180820	20180818
115254238	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20180820	20180818
115432570	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20180820	20180818
115455824	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20180820	20180818
115481652	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20180820	20180818
115617568	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20180820	20180818
116067182	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20180820	20180818
116083814	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180820	20180818
116292748	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20180820	20180818
116405388	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20180820	20180818
116621736	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20180820	20180818
116668266	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20180820	20180818
116773734	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180820	20180818
116961108	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180820	20180818
117513308	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20180820	20180818
117768354	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20180820	20180818
118660344	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20180820	20180818
119153078	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20180820	20180818
119893532	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20180820	20180818
119954824	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20180820	20180818
120557008	`ref`	`gcc -Os -fomit-frame-pointer`	20180820	20180818
121633534	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20180820	20180818
164358722	`ref`	`cc`	20180820	20180818
173336064	`ref`	`gcc -funroll-loops`	20180820	20180818
176194700	`avx2`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180820	20180818
176323356	`ref`	`gcc`	20180820	20180818
177613546	`avx2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180820	20180818
181263830	`avx2`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180820	20180818
189371622	`avx2`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180820	20180818
189770570	`avx2`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180820	20180818
196722922	`avx2`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180820	20180818
196833362	`avx2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180820	20180818
202237882	`avx2`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180820	20180818
203531460	`avx2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180820	20180818
221261150	`avx2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180820	20180818
222304456	`avx2`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180820	20180818
223493226	`avx2`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180820	20180818

Compiler output

Implementation: crypto_sign/sphincsf128sha256/avx2
Compiler: cc

hash_sha256x8.c: In file included from hash_sha256x8.c:9:0:
hash_sha256x8.c: sha256avx.h:67:5: error: unknown type name '__m256i'
hash_sha256x8.c: u256 s[8];
hash_sha256x8.c: ^
hash_sha256x8.c: In file included from hash_sha256x8.c:9:0:
hash_sha256x8.c: sha256avx.h:26:14: error: unknown type name '__m256i'
hash_sha256x8.c: #define u256 __m256i
hash_sha256x8.c: ^
hash_sha256x8.c: sha256avx.h:74:16: note: in expansion of macro 'u256'
hash_sha256x8.c: void transpose(u256 s[8]);
hash_sha256x8.c: ^

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
cc	avx2

Compiler output

Implementation: crypto_sign/sphincsf128sha256/avx2
Compiler: gcc

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

Compiler	Implementations
gcc	avx2
gcc -funroll-loops	avx2

Compiler output

Implementation: crypto_sign/sphincsf128sha256/avx2
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 84, namely:

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

Compiler output

Implementation: crypto_sign/sphincsf128sha256/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

sha256avx.c: sha256avx.c: In function 'transpose':
sha256avx.c: sha256avx.c:10:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
sha256avx.c: tmp0[0] = _mm256_unpacklo_epi32(s[0], s[1]);
sha256avx.c: ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:33:12: note: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:32:12: note: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: ...
sha256avx.c: sha256avx.c: In function 'transpose':
sha256avx.c: sha256avx.c:10:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
sha256avx.c: tmp0[0] = _mm256_unpacklo_epi32(s[0], s[1]);
sha256avx.c: ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:33:12: note: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:32:12: note: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: crypto_sign/sphincsf128sha256/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: sha256avx.c: In function 'transpose':
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:33:12: note: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: sha256avx.c:32:12: note: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '_mm256_permute2x128_si256': target specific option mismatch
sha256avx.c: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
sha256avx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
sha256avx.c: ...

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

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx2