Implementation notes: amd64, gpu, crypto_kem/edonk192k16n112nu4l8

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: edonk192k16n112nu4l8
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
495644451? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2019101020190816
500117730? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2019101020190816
501260214? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019101020190816
502309575? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019101020190816
50234080559784 0 0101009 904 1624refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019101020190816
508246152? ? ?? ? ?refcc2019101020190816
509336925? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019101020190816
514811010? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019101020190816
875730504? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2019101020190816
880963536? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2019101020190816
924007239? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019101020190816
925946274? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2019101020190816
926635377? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019101020190816
928449270? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2019101020190816
928490286? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019101020190816
928500537? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019101020190816
928544658? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019101020190816
928668309? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2019101020190816
929154549? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019101020190816
929417028? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019101020190816
930104976? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019101020190816
930671394? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019101020190816
930683838? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019101020190816
930757902? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019101020190816
930929205? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2019101020190816
931496313? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019101020190816
93167183159784 0 0101009 904 1624refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019101020190816
931849533? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2019101020190816
932122494? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019101020190816
93253249259784 0 0101009 904 1624refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019101020190816
933031359? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2019101020190816
933311190? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019101020190816
933345276? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019101020190816
934061109? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2019101020190816
934168755? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019101020190816
934505343? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019101020190816
934566480? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019101020190816
934588164? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019101020190816
935004498? ? ?? ? ?refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019101020190816
935276766? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2019101020190816
935393196? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019101020190816
935397882? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2019101020190816
935431167? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2019101020190816
935981544? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2019101020190816
93639105359160 0 098033 904 1976refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019101020190816
936404274? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019101020190816
936459765? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2019101020190816
936484116? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2019101020190816
936543372? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2019101020190816
936560346? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019101020190816
936584949? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019101020190816
936586560? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2019101020190816
93673319758744 0 096785 904 1976refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019101020190816
936808026? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019101020190816
936967002? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2019101020190816
937081509? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2019101020190816
937346544? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2019101020190816
937466400? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2019101020190816
93818033459160 0 098033 904 1976refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019101020190816
938366058? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2019101020190816
938539296? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019101020190816
939061272? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2019101020190816
939512667? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2019101020190816
939878058? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019101020190816
940147170? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2019101020190816
940839603? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2019101020190816
94088049064841 0 0104737 904 1624refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019101020190816
940882197? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019101020190816
94098113758744 0 096785 904 1976refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019101020190816
940994754? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019101020190816
941013033? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2019101020190816
941134980? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2019101020190816
941225442? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019101020190816
941232327? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2019101020190816
942938124? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2019101020190816
944212155? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019101020190816
945518997? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019101020190816
946016361? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2019101020190816
946105551? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2019101020190816
946291431? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2019101020190816
947018322? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019101020190816
948319680? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2019101020190816
948601155? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2019101020190816
948712575? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019101020190816
952410426? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019101020190816
954376251? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2019101020190816
954750093? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2019101020190816
955080306? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019101020190816
955276458? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2019101020190816
955553769? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2019101020190816
957077340? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2019101020190816
957191343? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2019101020190816
957917931? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019101020190816
958817271? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2019101020190816
958941243? ? ?? ? ?refgcc2019101020190816
960246645? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2019101020190816
960964842? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2019101020190816
962639931? ? ?? ? ?refgcc_-funroll-loops2019101020190816
974007615? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019101020190816

Test failure

Implementation: ref
Security model: unknown
Compiler: gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer
error 111
crypto_kem_dec returns nonzero

Number of similar (compiler,implementation) pairs: 12, namely:
CompilerImplementations
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer ref
gcc -march=barcelona -O2 -fomit-frame-pointer ref
gcc -march=barcelona -O3 -fomit-frame-pointer ref
gcc -march=barcelona -O -fomit-frame-pointer ref
gcc -march=barcelona -Os -fomit-frame-pointer ref

Test failure

Implementation: ref
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
error 111
crypto_kem_dec returns nonzero
error 111
crypto_kem_dec returns nonzero

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

Test failure

Implementation: ref
Security model: unknown
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: ref
Security model: unknown
Compiler: cc
measure.c: /usr/bin/ld: /home/z/supercop/supercop-20190816/supercop-data/gpu/amd64/lib/fastrandombytes.o: relocation R_X86_64_32 against `.bss' can not be used when making a PIE object; recompile with -fPIC
measure.c: /usr/bin/ld: final link failed: Nonrepresentable section on output
measure.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 91, namely:
CompilerImplementations
cc ref
gcc ref
gcc -O2 -fomit-frame-pointer ref
gcc -O3 -fomit-frame-pointer ref
gcc -O -fomit-frame-pointer ref
gcc -Os -fomit-frame-pointer ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops ref
gcc -funroll-loops -O2 -fomit-frame-pointer ref
gcc -funroll-loops -O3 -fomit-frame-pointer ref
gcc -funroll-loops -O -fomit-frame-pointer ref
gcc -funroll-loops -Os -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer ref
gcc -m64 -O2 -fomit-frame-pointer ref
gcc -m64 -O3 -fomit-frame-pointer ref
gcc -m64 -O -fomit-frame-pointer ref
gcc -m64 -Os -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -march=k8 -O2 -fomit-frame-pointer ref
gcc -march=k8 -O3 -fomit-frame-pointer ref
gcc -march=k8 -O -fomit-frame-pointer ref
gcc -march=k8 -Os -fomit-frame-pointer ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv ref
gcc -march=nocona -O2 -fomit-frame-pointer ref
gcc -march=nocona -O3 -fomit-frame-pointer ref
gcc -march=nocona -O -fomit-frame-pointer ref
gcc -march=nocona -Os -fomit-frame-pointer ref

Compiler output

Implementation: ref
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
dec.c: dec.c:714:89: warning: for loop has empty body [-Wempty-body]
dec.c: for(i=0; i<(1<<(ErrorBasisDimension+1))+2; i++) Kclear(allcandidates[i]);
dec.c: ^
dec.c: dec.c:714:89: note: put the semicolon on a separate line to silence this warning
dec.c: dec.c:594:76: warning: for loop has empty body [-Wempty-body]
dec.c: for(i=0; i<(1<<(ErrorBasisDimension+1))+2; i++) Kinit(allcandidates[i]);
dec.c: ^
dec.c: dec.c:594:76: note: put the semicolon on a separate line to silence this warning
dec.c: dec.c:599:56: warning: for loop has empty body [-Wempty-body]
dec.c: for(i=0; i<NrColumns; i++) Kinit(Ciphertext.cph[i]);
dec.c: ^
dec.c: dec.c:599:56: note: put the semicolon on a separate line to silence this warning
dec.c: 3 warnings generated.
mpfq_2_192.c: mpfq_2_192.c:154:35: warning: passing 'char *' to parameter of type 'const unsigned char *' converts between pointers to integer types with different sign [-Wpointer-sign]
mpfq_2_192.c: int ret = mpn_set_str(zz, tmp, len, k->io_type);
mpfq_2_192.c: ^~~
mpfq_2_192.c: /home/z/supercop/supercop-20190816/supercop-data/gpu/amd64/include/gmp.h:1588:68: note: passing argument to parameter here
mpfq_2_192.c: __GMP_DECLSPEC mp_size_t mpn_set_str (mp_ptr, const unsigned char *, size_t, int);
mpfq_2_192.c: ^
mpfq_2_192.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments ref
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments ref
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ref
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ref
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ref
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments ref