Implementation notes: amd64, hydra9, crypto_aead/led80n6t4silcv3

Computer: hydra9
Architecture: amd64
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: led80n6t4silcv3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
53198919? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017091020170725
53516854? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017091020170725
53766602? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017091020170725
53877020? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017091020170725
53902024? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017091020170725
53905094? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017091020170725
53907548? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017091020170725
54025574? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017091020170725
54196357? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017091020170725
56490404? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017091020170725
56500576? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017091020170725
56515506? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017091020170725
56559701? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017091020170725
56573971? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017091020170725
56737381? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017091020170725
56876250? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017091020170725
57120313? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017091020170725
57181052? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017091020170725
57290928? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017091020170725
57525681? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017091020170725
57845303? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017091020170725
57888432? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091020170725
57916457? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091020170725
58084070? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091020170725
58198304? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091020170725
58305939? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017091020170725
58325753? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091020170725
58341558? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091020170725
58354956? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091020170725
58513425? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017091020170725
58699547? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017091020170725
58947533? ? ?? ? ?refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091020170725
59030521? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017091020170725
59233589? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017091020170725
59248225? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017091020170725
64677135? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017091020170725
64682498? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017091020170725
64702985? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017091020170725
65028205? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017091020170725
65061384? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017091020170725
65078307? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017091020170725
65106360? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017091020170725
66984191? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017091020170725
67087913? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017091020170725
97535523? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091020170725
97716530? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091020170725
98779395? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017091020170725
98870448? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091020170725
99028749? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091020170725
99770439? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017091020170725
100156845? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017091020170725
100418897? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091020170725
101018278? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091020170725
105307095? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017091020170725
107001755? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017091020170725
109460370? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091020170725
109517091? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017091020170725
109581174? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017091020170725
109947170? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017091020170725
110535276? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091020170725
111665668? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017091020170725
119872693? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091020170725
119877964? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017091020170725
119958593? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091020170725
119963183? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091020170725
119988799? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017091020170725
120111735? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017091020170725
120295135? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091020170725
120385228? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091020170725
120503346? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091020170725
122320386? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017091020170725
122779988? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017091020170725
123463243? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017091020170725
123684178? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017091020170725
123943752? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017091020170725
124211645? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017091020170725
124680004? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017091020170725
127223475? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017091020170725
129509347? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017091020170725
131213389? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091020170725
131498490? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017091020170725
131582287? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091020170725
137349941? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017091020170725
137626273? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017091020170725
137664406? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017091020170725
137970551? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017091020170725
138448505? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017091020170725
138469698? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017091020170725
138610243? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017091020170725
139291828? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017091020170725
139378611? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017091020170725
139407887? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091020170725
139450574? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091020170725
139835162? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091020170725
139952528? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017091020170725
140109618? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017091020170725
140332926? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091020170725
140404119? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091020170725
140411382? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017091020170725
140656551? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017091020170725
140728232? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017091020170725
140747250? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017091020170725
140779384? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091020170725
141417897? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017091020170725
553377155? ? ?? ? ?refgcc_-funroll-loops2017091020170725
553442817? ? ?? ? ?refgcc2017091020170725
554150051? ? ?? ? ?refcc2017091020170725

Test failure

Implementation: crypto_aead/led80n6t4silcv3/ref
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref

Compiler output

Implementation: crypto_aead/led80n6t4silcv3/vperm
Compiler: cc
encrypt.c: In file included from common.h:7:0,
encrypt.c: from led.h:1,
encrypt.c: from silc.h:2,
encrypt.c: from encrypt.c:4:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/tmmintrin.h:31:3: error: #error "SSSE3 instruction set not enabled"
encrypt.c: # error "SSSE3 instruction set not enabled"
encrypt.c: ^

Number of similar (compiler,implementation) pairs: 71, namely:
CompilerImplementations
cc vperm
gcc vperm
gcc -O2 -fomit-frame-pointer vperm
gcc -O3 -fomit-frame-pointer vperm
gcc -O -fomit-frame-pointer vperm
gcc -Os -fomit-frame-pointer vperm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer vperm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer vperm
gcc -fno-schedule-insns -O -fomit-frame-pointer vperm
gcc -fno-schedule-insns -Os -fomit-frame-pointer vperm
gcc -funroll-loops vperm
gcc -funroll-loops -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -O -fomit-frame-pointer vperm
gcc -funroll-loops -Os -fomit-frame-pointer vperm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer vperm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -O -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -Os -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer vperm
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer vperm
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer vperm
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer vperm
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer vperm
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer vperm
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer vperm
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer vperm
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer vperm
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer vperm
gcc -m64 -O2 -fomit-frame-pointer vperm
gcc -m64 -O3 -fomit-frame-pointer vperm
gcc -m64 -O -fomit-frame-pointer vperm
gcc -m64 -Os -fomit-frame-pointer vperm
gcc -m64 -march=k8 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=k8 -O3 -fomit-frame-pointer vperm
gcc -m64 -march=k8 -O -fomit-frame-pointer vperm
gcc -m64 -march=k8 -Os -fomit-frame-pointer vperm
gcc -m64 -march=nocona -O2 -fomit-frame-pointer vperm
gcc -m64 -march=nocona -O3 -fomit-frame-pointer vperm
gcc -m64 -march=nocona -O -fomit-frame-pointer vperm
gcc -m64 -march=nocona -Os -fomit-frame-pointer vperm
gcc -march=barcelona -O2 -fomit-frame-pointer vperm
gcc -march=barcelona -O3 -fomit-frame-pointer vperm
gcc -march=barcelona -O -fomit-frame-pointer vperm
gcc -march=barcelona -Os -fomit-frame-pointer vperm
gcc -march=k8 -O2 -fomit-frame-pointer vperm
gcc -march=k8 -O3 -fomit-frame-pointer vperm
gcc -march=k8 -O -fomit-frame-pointer vperm
gcc -march=k8 -Os -fomit-frame-pointer vperm
gcc -march=nocona -O2 -fomit-frame-pointer vperm
gcc -march=nocona -O3 -fomit-frame-pointer vperm
gcc -march=nocona -O -fomit-frame-pointer vperm
gcc -march=nocona -Os -fomit-frame-pointer vperm

Compiler output

Implementation: crypto_aead/led80n6t4silcv3/vperm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
encrypt.c: In file included from common.h:7:0,
encrypt.c: from led.h:1,
encrypt.c: from silc.h:2,
encrypt.c: from encrypt.c:4:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/tmmintrin.h:31:3: error: #error "SSSE3 instruction set not enabled"
encrypt.c: # error "SSSE3 instruction set not enabled"
encrypt.c: ^
encrypt.c: In file included from common.h:7:0,
encrypt.c: from led.h:1,
encrypt.c: from silc.h:2,
encrypt.c: from encrypt.c:4:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/tmmintrin.h:31:3: error: #error "SSSE3 instruction set not enabled"
encrypt.c: # error "SSSE3 instruction set not enabled"
encrypt.c: ^

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer vperm
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer vperm
gcc -m64 -march=barcelona -O -fomit-frame-pointer vperm
gcc -m64 -march=barcelona -Os -fomit-frame-pointer vperm

Compiler output

Implementation: crypto_aead/led80n6t4silcv3/vperm
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
led.c: led.c: In function 'LED80_enc':
led.c: led.c:242:2: error: 'for' loop initial declarations are only allowed in C99 mode
led.c: for(int i=0; i<RN/4; i++){
led.c: ^
led.c: led.c:242:2: note: use option -std=c99 or -std=gnu99 to compile your code
led.c: led.c:243:3: error: 'for' loop initial declarations are only allowed in C99 mode
led.c: for(int j=0; j<4; j++){
led.c: ^

Number of similar (compiler,implementation) pairs: 35, namely:
CompilerImplementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer vperm
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer vperm
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer vperm
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer vperm
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer vperm
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer vperm
gcc -m64 -march=core2 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -O3 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -O -fomit-frame-pointer vperm
gcc -m64 -march=core2 -Os -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer vperm
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer vperm
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer vperm
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer vperm
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer vperm
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer vperm
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer vperm
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer vperm
gcc -m64 -march=corei7 -O -fomit-frame-pointer vperm
gcc -m64 -march=corei7 -Os -fomit-frame-pointer vperm
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer vperm
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer vperm
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer vperm
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer vperm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv vperm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv vperm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv vperm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv vperm