Implementation notes: amd64, bolero, crypto_sign/sphincsf256sha256

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_sign
Primitive: sphincsf256sha256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
673046672	`avx2`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
673201576	`avx2`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
711096424	`avx2`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
717295764	`avx2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180920	20180818
747187120	`avx2`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180920	20180818
748155164	`avx2`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180920	20180818
750694312	`avx2`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180920	20180818
770438484	`avx2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180920	20180818
772166136	`avx2`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180920	20180818
777010244	`avx2`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180920	20180818
777814172	`avx2`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180920	20180818
801626944	`avx2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180920	20180818
811835844	`avx2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180920	20180818
890442520	`avx2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180920	20180818
897672100	`avx2`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180920	20180818
902615796	`avx2`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180920	20180818
1599834164	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1599868564	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1605605616	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180920	20180818
1605765460	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180920	20180818
1605858372	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180920	20180818
1606174560	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1609263044	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1614276884	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20180920	20180818
1614884332	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180920	20180818
1617798544	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180920	20180818
1618229292	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20180920	20180818
1621354188	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20180920	20180818
1621383180	`ref`	`gcc -O3 -fomit-frame-pointer`	20180920	20180818
1621510416	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20180920	20180818
1623651480	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20180920	20180818
1623769756	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20180920	20180818
1624200848	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20180920	20180818
1624637816	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20180920	20180818
1624708924	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180920	20180818
1625646888	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20180920	20180818
1626471156	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180920	20180818
1626494272	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20180920	20180818
1627162444	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180920	20180818
1628428140	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1629153332	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20180920	20180818
1629168988	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20180920	20180818
1629877648	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20180920	20180818
1631053296	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180920	20180818
1631094552	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180920	20180818
1631221544	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20180920	20180818
1631239356	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20180920	20180818
1631251888	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20180920	20180818
1631401296	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20180920	20180818
1631856580	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180920	20180818
1632028060	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20180920	20180818
1632136748	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20180920	20180818
1632167328	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20180920	20180818
1632274200	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180920	20180818
1632515292	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20180920	20180818
1632607812	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20180920	20180818
1633399296	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20180920	20180818
1633594160	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20180920	20180818
1633728312	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20180920	20180818
1634487712	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20180920	20180818
1634846660	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20180920	20180818
1635048056	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20180920	20180818
1635209496	`ref`	`gcc -O2 -fomit-frame-pointer`	20180920	20180818
1635263396	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180920	20180818
1635467668	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180920	20180818
1635479188	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20180920	20180818
1635879696	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180920	20180818
1635999560	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180920	20180818
1636509684	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20180920	20180818
1637682656	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180920	20180818
1637827932	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20180920	20180818
1638031592	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20180920	20180818
1638044084	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20180920	20180818
1638353504	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20180920	20180818
1638566536	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20180920	20180818
1638794428	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20180920	20180818
1640855828	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20180920	20180818
1640936028	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20180920	20180818
1641138808	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20180920	20180818
1641168760	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180920	20180818
1641814280	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20180920	20180818
1642019296	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20180920	20180818
1642247092	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20180920	20180818
1642739124	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20180920	20180818
1642810368	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20180920	20180818
1642996692	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20180920	20180818
1643029560	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20180920	20180818
1644462084	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20180920	20180818
1644788180	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20180920	20180818
1645555428	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20180920	20180818
1645810896	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20180920	20180818
1646938708	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20180920	20180818
1647230116	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20180920	20180818
1647538740	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20180920	20180818
1647621964	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20180920	20180818
1647737412	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20180920	20180818
1647760276	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20180920	20180818
1647867120	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180920	20180818
1648191880	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180920	20180818
1650385444	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20180920	20180818
1651165280	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180920	20180818
1651705476	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180920	20180818
1653229300	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20180920	20180818
1653369316	`ref`	`gcc -O -fomit-frame-pointer`	20180920	20180818
1656589684	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20180920	20180818
1657424988	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20180920	20180818
1678246264	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180920	20180818
1684601464	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20180920	20180818
1684933816	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20180920	20180818
1687248640	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20180920	20180818
1687280580	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20180920	20180818
1687307092	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180920	20180818
1687459564	`ref`	`gcc -Os -fomit-frame-pointer`	20180920	20180818
1687873612	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20180920	20180818
1688095428	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20180920	20180818
1688434436	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20180920	20180818
1688463728	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20180920	20180818
1688769168	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20180920	20180818
1691461620	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20180920	20180818
1692023220	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20180920	20180818
1692295776	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20180920	20180818
1692647280	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180920	20180818
1692884820	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180920	20180818
1693494336	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20180920	20180818
1695930556	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180920	20180818
1696514624	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20180920	20180818
1696571280	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20180920	20180818
1704864824	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20180920	20180818
1705260408	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20180920	20180818
1705570328	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20180920	20180818
1705611616	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20180920	20180818
1705649668	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20180920	20180818
1705754420	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20180920	20180818
1706091116	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20180920	20180818
1851444352	`ref`	`gcc -funroll-loops`	20180920	20180818
1854824188	`ref`	`gcc`	20180920	20180818
1878580776	`ref`	`cc`	20180920	20180818

Compiler output

Implementation: crypto_sign/sphincsf256sha256/avx2
Compiler: cc

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	avx2
gcc	avx2
gcc -funroll-loops	avx2

Compiler output

Implementation: crypto_sign/sphincsf256sha256/avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

sha256avx.c: sha256avx.c:10:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[0] = _mm256_unpacklo_epi32(s[0], s[1]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:11:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[1] = _mm256_unpackhi_epi32(s[0], s[1]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:12:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[2] = _mm256_unpacklo_epi32(s[2], s[3]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:13:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[3] = _mm256_unpackhi_epi32(s[2], s[3]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:14:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[4] = _mm256_unpacklo_epi32(s[4], s[5]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:15:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[5] = _mm256_unpackhi_epi32(s[4], s[5]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:16:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[6] = _mm256_unpacklo_epi32(s[6], s[7]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:17:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: tmp0[7] = _mm256_unpackhi_epi32(s[6], s[7]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:18:15: error: always_inline function '_mm256_unpacklo_epi64' requires target feature 'sse4.2', but would be inlined into function 'transpose' that is compiled without support for 'sse4.2'
sha256avx.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2

Compiler output

Implementation: crypto_sign/sphincsf256sha256/avx2
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments

sha256avx.c: sha256avx.c:10:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[0] = _mm256_unpacklo_epi32(s[0], s[1]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:11:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[1] = _mm256_unpackhi_epi32(s[0], s[1]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:12:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[2] = _mm256_unpacklo_epi32(s[2], s[3]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:13:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[3] = _mm256_unpackhi_epi32(s[2], s[3]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:14:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[4] = _mm256_unpacklo_epi32(s[4], s[5]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:15:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[5] = _mm256_unpackhi_epi32(s[4], s[5]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:16:15: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[6] = _mm256_unpacklo_epi32(s[6], s[7]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:17:15: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: tmp0[7] = _mm256_unpackhi_epi32(s[6], s[7]);
sha256avx.c: ^
sha256avx.c: sha256avx.c:18:15: error: always_inline function '_mm256_unpacklo_epi64' requires target feature 'avx2', but would be inlined into function 'transpose' that is compiled without support for 'avx2'
sha256avx.c: ...

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

Compiler	Implementations
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx2

Compiler output

Implementation: crypto_sign/sphincsf256sha256/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/sphincsf256sha256/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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
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/sphincsf256sha256/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: sha256avx.c: In function 'transpose':
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[7] = _mm256_permute2x128_si256(tmp1[3], tmp1[7], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: called from here
sha256avx.c: s[6] = _mm256_permute2x128_si256(tmp1[2], tmp1[6], 0x31);
sha256avx.c: ^
sha256avx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
sha256avx.c: from sha256avx.h:3,
sha256avx.c: from sha256avx.c:4:
sha256avx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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