Implementation notes: x86, bolero, crypto_dh/ed448goldilocks

Computer: bolero
Architecture: x86
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_dh
Primitive: ed448goldilocks

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
10509764	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170905	20170725
10517216	`32`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20170905	20170725
10525480	`32`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170905	20170725
10656508	`32`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20170905	20170725
10659484	`32`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20170905	20170725
10678216	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170905	20170725
11629020	`32`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20170905	20170725
11637016	`32`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170905	20170725
11664364	`32`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20170905	20170725
11665896	`32`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20170905	20170725
11684480	`32`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170905	20170725
11688696	`32`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170905	20170725
11690684	`32`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170905	20170725
11690920	`32`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170905	20170725
11693100	`32`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20170905	20170725
11694556	`32`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170905	20170725
11701140	`32`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20170905	20170725
11710908	`32`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20170905	20170725
11715092	`32`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20170905	20170725
11725596	`32`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20170905	20170725
11730360	`32`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20170905	20170725
11737708	`32`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20170905	20170725
11745908	`32`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20170905	20170725
11748016	`32`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170905	20170725
11748176	`32`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20170905	20170725
11846496	`32`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170905	20170725
11868996	`32`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170905	20170725
11896896	`32`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20170905	20170725
11896924	`32`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20170905	20170725
11906984	`32`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20170905	20170725
11909676	`32`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20170905	20170725
11910536	`32`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20170905	20170725
11917408	`32`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20170905	20170725
11936468	`32`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170905	20170725
11959928	`32`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170905	20170725
12004180	`32`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20170905	20170725
12045212	`32`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20170905	20170725
12054904	`32`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20170905	20170725
12097188	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170905	20170725
12125212	`32`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170905	20170725
12149616	`32`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20170905	20170725
12275800	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170905	20170725
12465668	`32`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20170905	20170725
12465844	`32`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170905	20170725
12472736	`32`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170905	20170725
12495956	`32`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170905	20170725
12514612	`32`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20170905	20170725
12516736	`32`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20170905	20170725
12568308	`32`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20170905	20170725
12574108	`32`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20170905	20170725
12594376	`32`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170905	20170725
12661068	`32`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170905	20170725
12701036	`32`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20170905	20170725
12702240	`32`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20170905	20170725
12707816	`32`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170905	20170725
12711020	`32`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170905	20170725
12721104	`32`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20170905	20170725
12921488	`32`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20170905	20170725
12926744	`32`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20170905	20170725
12955928	`32`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20170905	20170725
12956176	`32`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20170905	20170725
12956856	`32`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20170905	20170725
12967068	`32`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20170905	20170725
13068384	`32`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20170905	20170725
13086740	`32`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20170905	20170725
13233340	`32`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20170905	20170725
13259088	`32`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20170905	20170725
13439088	`32`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170905	20170725
13446752	`32`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20170905	20170725
13458904	`32`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20170905	20170725
13546768	`32`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20170905	20170725
13570216	`32`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20170905	20170725
13670984	`32`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20170905	20170725
13801896	`32`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20170905	20170725
13806328	`32`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20170905	20170725
13930648	`32`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20170905	20170725
13935560	`32`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20170905	20170725
14015972	`32`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20170905	20170725
14020168	`32`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20170905	20170725
14384016	`32`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20170905	20170725

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