Implementation notes: x86, rumba5, crypto_dh/ed448goldilocks

Computer: rumba5
Architecture: x86
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20181216
Operation: crypto_dh
Primitive: ed448goldilocks

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
9466016	`32`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20180529	20171218
9469600	`32`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180529	20171218
9507744	`32`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20180529	20171218
9515616	`32`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20180529	20171218
9525472	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180529	20171218
9664256	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180529	20171218
9790752	`32`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20180529	20171218
9816064	`32`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180529	20171218
9822784	`32`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180529	20171218
9827744	`32`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20180529	20171218
9842688	`32`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180529	20171218
9844736	`32`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180529	20171218
9848608	`32`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20180529	20171218
9849504	`32`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20180529	20171218
9862848	`32`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20180529	20171218
9875136	`32`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20180529	20171218
9882048	`32`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20180529	20171218
9947264	`32`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180529	20171218
9962432	`32`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20180529	20171218
10083488	`32`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180529	20171218
10162944	`32`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20180529	20171218
10171392	`32`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180529	20171218
10180256	`32`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20180529	20171218
10182784	`32`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180529	20171218
10187744	`32`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20180529	20171218
10188800	`32`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20180529	20171218
10197888	`32`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20180529	20171218
10206464	`32`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20180529	20171218
10208288	`32`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20180529	20171218
10227520	`32`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180529	20171218
10255360	`32`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20180529	20171218
10261312	`32`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180529	20171218
10419904	`32`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20180529	20171218
10431968	`32`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20180529	20171218
10443264	`32`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180529	20171218
10455904	`32`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180529	20171218
10466624	`32`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20180529	20171218
10467840	`32`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20180529	20171218
11162336	`32`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180529	20171218
11354976	`32`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20180529	20171218
11451456	`32`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20180529	20171218
11470528	`32`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20180529	20171218
11470624	`32`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20180529	20171218
11477216	`32`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20180529	20171218
11477312	`32`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20180529	20171218
11500896	`32`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20180529	20171218
11509408	`32`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20180529	20171218
11539648	`32`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20180529	20171218
11565440	`32`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180529	20171218
11578304	`32`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20180529	20171218
11580096	`32`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20180529	20171218
11620448	`32`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20180529	20171218
11623648	`32`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20180529	20171218
11685760	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20180529	20171218
11728448	`32`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20180529	20171218
12128448	`32`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20180529	20171218
12168544	`32`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180529	20171218
12175264	`32`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20180529	20171218
12195136	`32`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20180529	20171218
12223616	`32`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180529	20171218
12228224	`32`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20180529	20171218
12234240	`32`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20180529	20171218
12245984	`32`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20180529	20171218
12249056	`32`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180529	20171218
12255808	`32`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20180529	20171218
12267936	`32`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20180529	20171218
12283136	`32`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180529	20171218
12298976	`32`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180529	20171218
12308480	`32`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20180529	20171218
12314176	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180529	20171218
12378656	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180529	20171218
12384384	`32`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180529	20171218
12551520	`32`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20180529	20171218
12585792	`32`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20180529	20171218
12670240	`32`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20180529	20171218
12741824	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20180529	20171218
12900128	`32`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20180529	20171218
12937824	`32`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20180529	20171218
12998848	`32`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20180529	20171218
13212512	`32`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20180529	20171218

Checksum failure

Implementation: crypto_dh/ed448goldilocks/32
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

e21a908e50081483c253fed14699efd1f77499d42c3c6fcf08607b884bbfaad3

Number of similar (compiler,implementation) pairs: 160, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	32 arm32
gcc -m32 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -O -fomit-frame-pointer	32 arm32
gcc -m32 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=athlon -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=athlon -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=i486 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=i486 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=k6 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	32 arm32

Test failure

Implementation: crypto_dh/ed448goldilocks/32
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	32 arm32

Compiler output

Implementation: crypto_dh/ed448goldilocks/64
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 192, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	64 amd64
gcc -m32 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -O -fomit-frame-pointer	64 amd64
gcc -m32 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=athlon -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=athlon -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=i386 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=i386 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=i486 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=i486 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=k6 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	64 amd64

Compiler output

Implementation: crypto_dh/ed448goldilocks/64
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 152, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	64 amd64
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=k8 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=k8 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=nocona -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=nocona -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	64 amd64
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=prescott -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=prescott -Os -fomit-frame-pointer	64 amd64

Compiler output

Implementation: crypto_dh/ed448goldilocks/arm32
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 68, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	arm32
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -O -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	arm32
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	arm32
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	arm32
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=corei7 -O -fomit-frame-pointer	arm32
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=k8 -O -fomit-frame-pointer	arm32
gcc -m32 -march=k8 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=nocona -O -fomit-frame-pointer	arm32
gcc -m32 -march=nocona -Os -fomit-frame-pointer	arm32
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	arm32
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	arm32
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	arm32
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=prescott -O -fomit-frame-pointer	arm32
gcc -m32 -march=prescott -Os -fomit-frame-pointer	arm32

Compiler output

Implementation: crypto_dh/ed448goldilocks/32
Compiler: gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer

try.c: crypto_dh_ed448goldilocks.a(goldilocks.o): In function `goldilocks_init':
try.c: goldilocks.c:(.text+0x...): undefined reference to `__sync_val_compare_and_swap_4'
try.c: goldilocks.c:(.text+0x...): undefined reference to `__sync_bool_compare_and_swap_4'
try.c: goldilocks.c:(.text+0x...): undefined reference to `__sync_bool_compare_and_swap_4'
try.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	32 arm32
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	32 arm32
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	32 arm32
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	32 arm32
gcc -m32 -march=i386 -O -fomit-frame-pointer	32 arm32
gcc -m32 -march=i386 -Os -fomit-frame-pointer	32 arm32

Compiler output

Implementation: crypto_dh/ed448goldilocks/64
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

barrett_field.c: In file included from barrett_field.h:15:0,
barrett_field.c: from barrett_field.c:5:
barrett_field.c: word.h:34:9: error: unknown type name '__uint128_t'
barrett_field.c: typedef __uint128_t dword_t;
barrett_field.c: ^
barrett_field.c: word.h:37:9: error: unknown type name '__int128_t'
barrett_field.c: typedef __int128_t dsword_t;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'add_nr_ext_packed':
barrett_field.c: barrett_field.c:22:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c:26:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'add_nr_packed':
barrett_field.c: barrett_field.c:41:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'sub_nr_ext_packed':
barrett_field.c: barrett_field.c:59:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c:63:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ...
barrett_field.c: In file included from barrett_field.h:15:0,
barrett_field.c: from barrett_field.c:5:
barrett_field.c: word.h:34:9: error: unknown type name '__uint128_t'
barrett_field.c: typedef __uint128_t dword_t;
barrett_field.c: ^
barrett_field.c: word.h:37:9: error: unknown type name '__int128_t'
barrett_field.c: typedef __int128_t dsword_t;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'add_nr_ext_packed':
barrett_field.c: barrett_field.c:22:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c:26:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'add_nr_packed':
barrett_field.c: barrett_field.c:41:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c: In function 'sub_nr_ext_packed':
barrett_field.c: barrett_field.c:59:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ^
barrett_field.c: barrett_field.c:63:15: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
barrett_field.c: carry >gt;>gt;= WORD_BITS;
barrett_field.c: ...

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	64 amd64
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	64 amd64
gcc -m32 -march=barcelona -O -fomit-frame-pointer	64 amd64
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	64 amd64

Compiler output

Implementation: crypto_dh/ed448goldilocks/arm32
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

crandom.c: In file included from magic.h:15:0,
crandom.c: from crandom.c:11:
crandom.c: p448.h: In function 'p448_cond_swap':
crandom.c: p448.h:194:24: error: incompatible types when initializing type 'big_register_t {aka __vector(4) unsigned int}' using type 'mask_t {aka unsigned int}'
crandom.c: big_register_t m = doswap;
crandom.c: ^
crandom.c: p448.h: In function 'p448_cond_neg':
crandom.c: p448.h:270:24: error: incompatible types when initializing type 'big_register_t {aka __vector(4) unsigned int}' using type 'mask_t {aka unsigned int}'
crandom.c: big_register_t m = doNegate;
crandom.c: ^
crandom.c: In file included from magic.h:15:0,
crandom.c: from crandom.c:11:
crandom.c: p448.h: In function 'p448_cond_swap':
crandom.c: p448.h:194:24: error: incompatible types when initializing type 'big_register_t {aka __vector(4) unsigned int}' using type 'mask_t {aka unsigned int}'
crandom.c: big_register_t m = doswap;
crandom.c: ^
crandom.c: p448.h: In function 'p448_cond_neg':
crandom.c: p448.h:270:24: error: incompatible types when initializing type 'big_register_t {aka __vector(4) unsigned int}' using type 'mask_t {aka unsigned int}'
crandom.c: big_register_t m = doNegate;
crandom.c: ^

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=barcelona -O -fomit-frame-pointer	arm32
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	arm32

Compiler output

Implementation: crypto_dh/ed448goldilocks/arm32
Compiler: gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer

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

Compiler	Implementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	arm32
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	arm32
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	arm32
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	arm32
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	arm32
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	arm32