Implementation notes: amd64, bolero, crypto_sign/sphincss256shake256

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_sign
Primitive: sphincss256shake256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
5917659716	`avx2`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
5918718916	`avx2`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
6019702364	`avx2`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20181010	20180818
6019855240	`avx2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20181010	20180818
6040666804	`avx2`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
6040964680	`avx2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181010	20180818
6170061744	`avx2`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20181010	20180818
8237165140	`avx2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20181010	20180818
8462089404	`avx2`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20181010	20180818
8470083248	`avx2`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20181010	20180818
9255388696	`avx2`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20181010	20180818
9257043836	`avx2`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20181010	20180818
9468742852	`avx2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20181010	20180818
9473472412	`avx2`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20181010	20180818
9476045356	`avx2`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20181010	20180818
9664147108	`avx2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20181010	20180818
10260299672	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
10260569592	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181010	20180818
10517814556	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20181010	20180818
10518784800	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20181010	20180818
10704005316	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20181010	20180818
12827293924	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
12829490128	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181010	20180818
12839264204	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181010	20180818
12881551900	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20181010	20180818
13167619608	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13168613836	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13206883780	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13212400328	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20181010	20180818
13221247908	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20181010	20180818
13222921756	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20181010	20180818
13228180092	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20181010	20180818
13257217368	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20181010	20180818
13265359516	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20181010	20180818
13420059312	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20181010	20180818
13428040588	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20181010	20180818
13523598596	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20181010	20180818
13523958308	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20181010	20180818
13525512652	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20181010	20180818
13599216812	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20181010	20180818
13600346920	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20181010	20180818
13601033888	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20181010	20180818
13602298244	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20181010	20180818
13605238476	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20181010	20180818
13607233172	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20181010	20180818
13619104888	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20181010	20180818
13621340972	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20181010	20180818
13636582684	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20181010	20180818
13636618556	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20181010	20180818
13666722872	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20181010	20180818
13667901548	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20181010	20180818
13802067468	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20181010	20180818
13804162060	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20181010	20180818
13804581620	`ref`	`gcc -O3 -fomit-frame-pointer`	20181010	20180818
14025371940	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20181010	20180818
14027474272	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20181010	20180818
14037139148	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20181010	20180818
14037174396	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20181010	20180818
14087127576	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20181010	20180818
14087168232	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20181010	20180818
14087650424	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20181010	20180818
14114641544	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20181010	20180818
14118917908	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20181010	20180818
14457943936	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20181010	20180818
14459415484	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20181010	20180818
14478540812	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20181010	20180818
14478743776	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20181010	20180818
14479951496	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20181010	20180818
14510746552	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20181010	20180818
14510765464	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20181010	20180818
14602599004	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20181010	20180818
14627247804	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20181010	20180818
14664044260	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20181010	20180818
14666470796	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20181010	20180818
14675004176	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20181010	20180818
14681139264	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20181010	20180818
14782225708	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20181010	20180818
14799324400	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20181010	20180818
14845182072	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20181010	20180818
15503814084	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20181010	20180818
16054630616	`ref`	`gcc -O2 -fomit-frame-pointer`	20181010	20180818
16057956988	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20181010	20180818
16061216828	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20181010	20180818
16096607084	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20181010	20180818
16179496560	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20181010	20180818
16257206600	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20181010	20180818
16257446816	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20181010	20180818
16258163140	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20181010	20180818
16267387148	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20181010	20180818
16270844756	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20181010	20180818
16270991864	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20181010	20180818
16404143460	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20181010	20180818
16412025784	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20181010	20180818
16745219284	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20181010	20180818
16749707440	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20181010	20180818
16764364112	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20181010	20180818
16771714792	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20181010	20180818
16772847416	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20181010	20180818
16800051460	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20181010	20180818
16925083904	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20181010	20180818
16942420704	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20181010	20180818
17011233944	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20181010	20180818
17014180580	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20181010	20180818
17029193584	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20181010	20180818
17048720948	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20181010	20180818
17160223380	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20181010	20180818
17160519244	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20181010	20180818
17218131640	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20181010	20180818
17226558228	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20181010	20180818
17343585984	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20181010	20180818
17378851336	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20181010	20180818
17395251808	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20181010	20180818
17401642928	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20181010	20180818
17409332124	`ref`	`gcc -O -fomit-frame-pointer`	20181010	20180818
17409711312	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20181010	20180818
17411004312	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20181010	20180818
17412729184	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20181010	20180818
17413469244	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20181010	20180818
17414778932	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20181010	20180818
17417168960	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20181010	20180818
17419909408	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20181010	20180818
17976780292	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20181010	20180818
17979431960	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20181010	20180818
18440039952	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20181010	20180818
18445882988	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20181010	20180818
18468120896	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20181010	20180818
18469858560	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20181010	20180818
18476926880	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20181010	20180818
18481966836	`ref`	`gcc -Os -fomit-frame-pointer`	20181010	20180818
18485555836	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20181010	20180818
18545600516	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20181010	20180818
18547441224	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20181010	20180818
18547494016	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20181010	20180818
18549245136	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20181010	20180818

Test failure

Implementation: crypto_sign/sphincss256shake256/ref
Compiler: cc

error 142
Alarm clock

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

Compiler	Implementations
cc	ref
gcc	ref
gcc -funroll-loops	ref

Compiler output

Implementation: crypto_sign/sphincss256shake256/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/sphincss256shake256/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/sphincss256shake256/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/sphincss256shake256/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/sphincss256shake256/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