Implementation notes: amd64, bolero, crypto_sign/sphincss128shake256

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_sign
Primitive: sphincss128shake256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
3710049056	`avx2`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
3723079060	`avx2`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
3806264252	`avx2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180924	20180818
3963943776	`avx2`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
4036729912	`avx2`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180924	20180818
4036923848	`avx2`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180924	20180818
4038973912	`avx2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180924	20180818
5325105880	`avx2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180924	20180818
5431757536	`avx2`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180924	20180818
5435025532	`avx2`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180924	20180818
6355378572	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
6360002732	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180924	20180818
6374444524	`avx2`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180924	20180818
6376046020	`avx2`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180924	20180818
6401741640	`avx2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180924	20180818
6405653392	`avx2`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180924	20180818
6408134436	`avx2`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180924	20180818
6482971452	`avx2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180924	20180818
6632650452	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20180924	20180818
6710587488	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20180924	20180818
6714926796	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180924	20180818
8098219304	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180924	20180818
8099630184	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180924	20180818
8101655620	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
8104530496	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20180924	20180818
8242711264	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20180924	20180818
8246130744	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
8247533032	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
8249100432	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
8249546936	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20180924	20180818
8312474952	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180924	20180818
8321205828	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20180924	20180818
8337561228	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20180924	20180818
8341251596	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20180924	20180818
8343160476	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20180924	20180818
8398253412	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180924	20180818
8429764416	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180924	20180818
8531005800	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180924	20180818
8531394776	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20180924	20180818
8544256896	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20180924	20180818
8544603948	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20180924	20180818
8546025248	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20180924	20180818
8547101100	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20180924	20180818
8547185992	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20180924	20180818
8563497208	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20180924	20180818
8563543464	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20180924	20180818
8603690452	`ref`	`gcc -O3 -fomit-frame-pointer`	20180924	20180818
8603853508	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20180924	20180818
8604388564	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20180924	20180818
8610751008	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20180924	20180818
8617573540	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20180924	20180818
8617722524	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20180924	20180818
8624871888	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20180924	20180818
8634601952	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20180924	20180818
8634637472	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20180924	20180818
8691871172	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20180924	20180818
8693061112	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20180924	20180818
8714230628	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20180924	20180818
8715179484	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20180924	20180818
8719335116	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20180924	20180818
8724286764	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20180924	20180818
8724613896	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20180924	20180818
8724667864	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20180924	20180818
8725222456	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20180924	20180818
8730629484	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180924	20180818
8731008396	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20180924	20180818
8790866632	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20180924	20180818
8867853564	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20180924	20180818
8995809608	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20180924	20180818
8995979392	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20180924	20180818
8996087248	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20180924	20180818
9045054368	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20180924	20180818
9046331244	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20180924	20180818
9060495392	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20180924	20180818
9066055208	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20180924	20180818
9067274780	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20180924	20180818
9097141584	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20180924	20180818
9098442564	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20180924	20180818
9102705832	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20180924	20180818
9104070548	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20180924	20180818
10173518632	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20180924	20180818
10180853892	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20180924	20180818
10193976332	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20180924	20180818
10204663296	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20180924	20180818
10212413064	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180924	20180818
10224739988	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20180924	20180818
10230576024	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20180924	20180818
10235701096	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20180924	20180818
10239135668	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20180924	20180818
10245541144	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20180924	20180818
10251295872	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20180924	20180818
10251338408	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20180924	20180818
10253800764	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20180924	20180818
10263502200	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180924	20180818
10272899104	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20180924	20180818
10273304620	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20180924	20180818
10302488764	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20180924	20180818
10303935396	`ref`	`gcc -O2 -fomit-frame-pointer`	20180924	20180818
10308282232	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20180924	20180818
10349715000	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20180924	20180818
10361242468	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20180924	20180818
10361795444	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180924	20180818
10364427612	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180924	20180818
10364539104	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20180924	20180818
10447147740	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20180924	20180818
10452183880	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20180924	20180818
10457547700	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20180924	20180818
10461592764	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20180924	20180818
10462575700	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180924	20180818
10462890448	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20180924	20180818
10463077116	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20180924	20180818
10484372204	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20180924	20180818
10511929020	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20180924	20180818
10512088572	`ref`	`gcc -O -fomit-frame-pointer`	20180924	20180818
10521293980	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20180924	20180818
10534458756	`ref`	`gcc -Os -fomit-frame-pointer`	20180924	20180818
10540854980	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20180924	20180818
10545728436	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20180924	20180818
10549079792	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20180924	20180818
10550220692	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20180924	20180818
10551338936	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20180924	20180818
10553003924	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20180924	20180818
10553201144	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20180924	20180818
10554794784	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20180924	20180818
10557904904	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20180924	20180818
10558415700	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20180924	20180818
10560043956	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20180924	20180818
10574855024	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20180924	20180818
10760445636	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20180924	20180818
10868237208	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20180924	20180818
10903310608	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20180924	20180818
11002684820	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20180924	20180818
11008123820	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20180924	20180818
11084134000	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20180924	20180818
30973537256	`ref`	`gcc`	20180924	20180818
30995730104	`ref`	`gcc -funroll-loops`	20180924	20180818
31000733364	`ref`	`cc`	20180924	20180818

Compiler output

Implementation: crypto_sign/sphincss128shake256/avx2
Compiler: cc

Number of similar (compiler,implementation) pairs: 87, namely:

Compiler	Implementations
cc	avx2
gcc	avx2
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	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/sphincss128shake256/avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes1 = LOAD256u( curData1[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:137:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes2 = LOAD256u( curData2[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:138:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.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/sphincss128shake256/avx2
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments

KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:140:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+0], lanes0 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:141:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+1], lanes1 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.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/sphincss128shake256/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: error: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: error: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.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/sphincss128shake256/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: error: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: error: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.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