Implementation notes: amd64, genji262, crypto_hash/nasha512

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20191017
Operation: crypto_hash
Primitive: nasha512
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
2365049503 0 459779 792 131824opt_v4clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2373831552 0 443443 792 131840opt_v4clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2391442922 0 453491 792 131840opt_v4clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2393631552 0 443443 792 131840opt_v4clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2681818710 0 030569 800 776optgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
2787412699 0 025347 792 752optclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
279408636 0 018644 792 776optgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
2838010396 0 022451 792 752optclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2842410396 0 022451 792 752optclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
284688922 0 018305 784 736optclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
2851214435 0 026755 792 736optclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017
3297828963 0 438100 776 131872opt_v4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
345629499 0 019724 792 776optgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
3592639725 0 451569 800 131872opt_v4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
3594832580 0 442812 792 131872opt_v4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
362567938 0 017076 776 776optgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
3830231785 0 441780 792 131872opt_v4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102420191017
3858853624 0 468957 840 131840opt_v4icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019102420191017
3863253960 0 469341 840 131840opt_v4icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019102420191017
3865453688 0 469021 840 131840opt_v4icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019102420191017
3865453960 0 469341 840 131840opt_v4icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019102420191017
3865453960 0 469341 840 131840opt_v4icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019102420191017
3869854616 0 470349 840 131840opt_v4icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019102420191017
3869853688 0 469021 840 131840opt_v4icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019102420191017
3869853960 0 469341 840 131840opt_v4icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019102420191017
3872054616 0 470349 840 131840opt_v4icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019102420191017
3872053688 0 469021 840 131840opt_v4icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019102420191017
3872053000 0 468413 840 131840opt_v4icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019102420191017
3874253000 0 468413 840 131840opt_v4icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019102420191017
3874253000 0 468413 840 131840opt_v4icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019102420191017
3874254616 0 470349 840 131840opt_v4icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019102420191017
3883053000 0 468413 840 131840opt_v4icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019102420191017
3931454680 0 470413 840 131840opt_v4icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019102420191017
3946853200 0 467285 840 131840opt_v4icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019102420191017
3946852320 0 466461 840 131840opt_v4icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019102420191017
4131635504 0 050837 840 744opticc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019102420191017
4136035504 0 050837 840 744opticc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019102420191017
4138235504 0 050837 840 744opticc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019102420191017
4166835472 0 050805 840 744opticc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019102420191017
4175636848 0 052581 840 744opticc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019102420191017
4175636848 0 052581 840 744opticc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019102420191017
4177834528 0 048669 840 744opticc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019102420191017
4184436864 0 052597 840 744opticc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019102420191017
4188834816 0 050229 840 744opticc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019102420191017
4188834816 0 050229 840 744opticc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019102420191017
4197634816 0 050229 840 744opticc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019102420191017
4199834816 0 050229 840 744opticc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019102420191017
4202036848 0 052581 840 744opticc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019102420191017
4226235456 0 049541 840 744opticc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019102420191017
4261435600 0 050981 840 744opticc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019102420191017
4263635600 0 050981 840 744opticc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019102420191017
4274635600 0 050981 840 744opticc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019102420191017
4287835600 0 050981 840 744opticc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019102420191017
4499029675 0 439057 784 131824opt_v4clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102420191017

Test failure

Implementation: opt
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 12, namely:
CompilerImplementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer opt
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer opt
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer opt
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer opt
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer opt
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer opt
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer opt_v4
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer opt_v4
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer opt_v4
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer opt_v4

Compiler output

Implementation: opt
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Nasha.c: Nasha.c:627:1: warning: control may reach end of non-void function [-Wreturn-type]
Nasha.c: }
Nasha.c: ^
Nasha.c: Nasha.c:646:1: warning: control may reach end of non-void function [-Wreturn-type]
Nasha.c: }
Nasha.c: ^
Nasha.c: 2 warnings generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt

Compiler output

Implementation: opt_v4
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
Nasha.c: Nasha.c:815:29: warning: incompatible pointer to integer conversion assigning to 'uint_16t' (aka 'unsigned short') from 'uint_16t [256]' [-Wint-conversion]
Nasha.c: ssbox[i][j] = ssbox[i^j];
Nasha.c: ^ ~~~~~~~~~~
Nasha.c: Nasha.c:854:1: warning: control may reach end of non-void function [-Wreturn-type]
Nasha.c: }
Nasha.c: ^
Nasha.c: Nasha.c:873:1: warning: control may reach end of non-void function [-Wreturn-type]
Nasha.c: }
Nasha.c: ^
Nasha.c: 3 warnings generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt_v4
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt_v4
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt_v4
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt_v4
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE opt_v4

Compiler output

Implementation: opt_v4
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
Nasha.c: Nasha.c: In function 'Init':
Nasha.c: Nasha.c:815:29: warning: assignment to 'uint_16t' {aka 'short unsigned int'} from 'uint_16t *' {aka 'short unsigned int *'} makes integer from pointer without a cast [-Wint-conversion]
Nasha.c: 815 | ssbox[i][j] = ssbox[i^j];
Nasha.c: | ^

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE opt_v4
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE opt_v4
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE opt_v4
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE opt_v4

Compiler output

Implementation: opt_v4
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer
Nasha.c: Nasha.c(815): warning #810: conversion from "uint_16t={crypto_uint16={unsigned short}} *" to "uint_16t={crypto_uint16={unsigned short}}" may lose significant bits
Nasha.c: ssbox[i][j] = ssbox[i^j];
Nasha.c: ^
Nasha.c:

Number of similar (compiler,implementation) pairs: 24, namely:
CompilerImplementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer opt_v4
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer opt_v4
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer opt_v4
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer opt_v4
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer opt_v4
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer opt_v4
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer opt_v4
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer opt_v4
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer opt_v4
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer opt_v4
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer opt_v4
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer opt_v4
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer opt_v4
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer opt_v4
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer opt_v4
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer opt_v4
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer opt_v4
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer opt_v4
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer opt_v4
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer opt_v4
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer opt_v4
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer opt_v4