Implementation notes: amd64, bolero, crypto_sign/sphincss256sha256

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_sign
Primitive: sphincss256sha256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
5154693320	`avx2`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20181009	20180818
5178072896	`avx2`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181009	20180818
5469661024	`avx2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181009	20180818
5553977808	`avx2`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20181009	20180818
5681479224	`avx2`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20181009	20180818
5699934892	`avx2`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20181009	20180818
5715367600	`avx2`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20181009	20180818
5718110780	`avx2`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20181009	20180818
5848409948	`avx2`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20181009	20180818
5851806788	`avx2`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20181009	20180818
6073106232	`avx2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20181009	20180818
6208108432	`avx2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20181009	20180818
6295414360	`avx2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20181009	20180818
7048963012	`avx2`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20181009	20180818
7051937996	`avx2`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20181009	20180818
7123291640	`avx2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20181009	20180818
13028070608	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181009	20180818
13028473020	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13031061552	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13031364016	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181009	20180818
13033486132	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181009	20180818
13089745168	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20181009	20180818
13092712416	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20181009	20180818
13106367052	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13107772132	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13115657612	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20181009	20180818
13120811664	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20181009	20180818
13174894680	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20181009	20180818
13175574960	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20181009	20180818
13176596508	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20181009	20180818
13177955216	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20181009	20180818
13188915924	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13195181428	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20181009	20180818
13206577532	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20181009	20180818
13207300368	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20181009	20180818
13219074384	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20181009	20180818
13220591636	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20181009	20180818
13223324708	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20181009	20180818
13225806664	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20181009	20180818
13233145656	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20181009	20180818
13233507940	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20181010	20180818
13233888124	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20181009	20180818
13236485856	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20181009	20180818
13241591992	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20181009	20180818
13242831456	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20181009	20180818
13243457440	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20181009	20180818
13246660628	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20181009	20180818
13247611844	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20181009	20180818
13248001776	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20181009	20180818
13248306372	`ref`	`gcc -O3 -fomit-frame-pointer`	20181009	20180818
13249210808	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20181009	20180818
13251442840	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20181009	20180818
13252357108	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20181009	20180818
13253969188	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20181009	20180818
13257279768	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20181009	20180818
13260547956	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20181009	20180818
13262401812	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20181009	20180818
13263163724	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20181009	20180818
13264435924	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20181009	20180818
13269591416	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20181009	20180818
13272078900	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20181009	20180818
13287374916	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181009	20180818
13287516732	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13290927084	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20181010	20180818
13291321356	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20181009	20180818
13291935868	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20181010	20180818
13293374040	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20181009	20180818
13297254836	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20181009	20180818
13297285220	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20181009	20180818
13317809668	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20181009	20180818
13327532296	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20181009	20180818
13339073312	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20181009	20180818
13341261988	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20181009	20180818
13343786852	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20181009	20180818
13344095720	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20181009	20180818
13345948740	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20181009	20180818
13348630764	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20181009	20180818
13352531024	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20181009	20180818
13354345488	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20181009	20180818
13354725188	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20181009	20180818
13359020592	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20181009	20180818
13360873860	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20181009	20180818
13362424432	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20181009	20180818
13362538536	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20181009	20180818
13364796388	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20181009	20180818
13365702132	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20181009	20180818
13370000484	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20181009	20180818
13373107728	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20181009	20180818
13374078504	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20181009	20180818
13374817164	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20181009	20180818
13378506280	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20181009	20180818
13379881052	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20181009	20180818
13382230048	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20181009	20180818
13382919500	`ref`	`gcc -O -fomit-frame-pointer`	20181009	20180818
13383360272	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20181010	20180818
13391155200	`ref`	`gcc -O2 -fomit-frame-pointer`	20181009	20180818
13392539008	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20181009	20180818
13396363272	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20181009	20180818
13396674308	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20181009	20180818
13397510984	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20181009	20180818
13415906732	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20181009	20180818
13425385476	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20181009	20180818
13425718608	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20181009	20180818
13443496488	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20181009	20180818
13449827628	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20181009	20180818
13451027424	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20181009	20180818
13488097164	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20181009	20180818
13729999080	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20181009	20180818
13731989432	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20181009	20180818
13732195272	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20181009	20180818
13737240688	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20181009	20180818
13746868596	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20181009	20180818
13746919408	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20181009	20180818
13750570256	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20181009	20180818
13754849164	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20181009	20180818
13754947004	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20181009	20180818
13755788728	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20181010	20180818
13766377360	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20181009	20180818
13776061188	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20181009	20180818
13785817816	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20181009	20180818
13801213276	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20181009	20180818
13803293704	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20181009	20180818
13808147248	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20181009	20180818
13808722140	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20181009	20180818
13810028784	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20181009	20180818
13810710328	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20181009	20180818
13816564508	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20181009	20180818
13816766512	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20181009	20180818
13817721532	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20181009	20180818
13817979296	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20181009	20180818
13822774536	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20181009	20180818
13824724668	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20181009	20180818
13826139768	`ref`	`gcc -Os -fomit-frame-pointer`	20181009	20180818
13830307340	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20181009	20180818
15003388888	`ref`	`gcc -funroll-loops`	20181009	20180818
15030085544	`ref`	`gcc`	20181009	20180818
15038497668	`ref`	`cc`	20181010	20180818

Compiler output

Implementation: crypto_sign/sphincss256sha256/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/sphincss256sha256/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/sphincss256sha256/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/sphincss256sha256/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/sphincss256sha256/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/sphincss256sha256/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