Implementation notes: amd64, gsm2, crypto_aead/led80n6t4silcv3

Computer: gsm2
Architecture: amd64
CPU ID: GenuineIntel-000306e4-bfebfbff
SUPERCOP version: 20170725
Operation: crypto_aead
Primitive: led80n6t4silcv3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
60119904? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2017080620170725
79750592? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2017080620170725
79875812? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2017080620170725
83010404? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2017080620170725
84999524? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2017080620170725
85718668? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2017080620170725
85719044? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2017080620170725
86928084? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017080620170725
90186476? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2017080620170725
91492512? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2017080620170725
91858876? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2017080620170725
92256784? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2017080620170725
92290368? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2017080520170725
92341740? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017080620170725
92398832? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2017080620170725
92836872? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2017080620170725
93004696? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2017080620170725
93103332? ? ?? ? ?refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017080620170725
93283776? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2017080620170725
93886684? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017080620170725
93894160? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017080620170725
94262836? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017080620170725
94326820? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017080620170725
94730372? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2017080620170725
94791824? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2017080520170725
95342444? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017080620170725
95764304? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2017080620170725
96146844? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017080520170725
96452368? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017080520170725
96772396? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2017080620170725
97080748? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2017080620170725
97212056? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2017080620170725
97874472? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2017080620170725
97914608? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017080620170725
98834752? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2017080620170725
99134556? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2017080620170725
100232716? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2017080620170725
101458448? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2017080620170725
106126404? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2017080620170725
108369824? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2017080620170725
108455020? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2017080620170725
108988624? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2017080620170725
109414728? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2017080620170725
109531200? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2017080620170725
111442012? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2017080620170725
122215296? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2017080620170725
127155260? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017080520170725
145834732? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2017080620170725
146190456? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2017080620170725
153971396? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2017080620170725
161175600? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2017080620170725
161496984? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017080520170725
162362440? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2017080620170725
163231372? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017080520170725
163711480? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2017080520170725
163889192? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017080620170725
164213452? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017080620170725
165532332? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2017080620170725
165628144? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017080620170725
165822940? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017080620170725
166688900? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2017080620170725
170112764? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2017080620170725
171905684? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2017080620170725
172195772? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017080620170725
172545884? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2017080620170725
172922828? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2017080620170725
174165508? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017080620170725
175284436? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017080620170725
175501784? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2017080620170725
175846624? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2017080520170725
175934256? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017080620170725
176031364? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017080520170725
176051512? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017080620170725
176264804? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017080620170725
176299832? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017080620170725
176566280? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017080620170725
177824396? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2017080620170725
177967808? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2017080620170725
178097424? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017080620170725
179041808? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2017080620170725
179059864? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017080620170725
179090728? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2017080620170725
179444388? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2017080620170725
179552964? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2017080620170725
180291208? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017080520170725
180700496? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2017080520170725
180877708? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2017080620170725
181606068? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2017080620170725
181922028? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2017080620170725
182024520? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2017080620170725
182109104? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017080620170725
182231360? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017080520170725
183417716? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2017080620170725
183863152? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2017080620170725
186314296? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2017080620170725
186329960? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2017080620170725
186350344? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2017080620170725
186861688? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2017080620170725
187018000? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017080620170725
187140436? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2017080620170725
188209948? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2017080620170725
188283904? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017080620170725
190984368? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2017080620170725
191636868? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2017080620170725
660922592? ? ?? ? ?refgcc2017080620170725
672777460? ? ?? ? ?refgcc_-funroll-loops2017080620170725
673586364? ? ?? ? ?refcc2017080620170725

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