Implementation notes: amd64, genji262, crypto_hash/nasha256

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20190910
Operation: crypto_hash
Primitive: nasha256
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1856831552 0 443395 792 131840opt_v4clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
1874442922 0 453443 792 131840opt_v4clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
1876631552 0 443395 792 131840opt_v4clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
1894229675 0 439009 784 131824opt_v4clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
225508636 0 018644 792 776optgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
2274812699 0 025299 792 752optclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
2292418710 0 030489 800 776optgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
2294610396 0 022403 792 752optclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
2312210396 0 022403 792 752optclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
2404628963 0 438100 776 131872opt_v4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
242448922 0 018241 784 736optclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091220190910
2512439725 0 451489 800 131872opt_v4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
2514632580 0 442732 792 131872opt_v4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
2530031785 0 441780 792 131872opt_v4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
270387938 0 017076 776 776optgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
280509499 0 019644 792 776optgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091220190910
3110854616 0 470349 840 131840opt_v4icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019091220190910
3110853000 0 468413 840 131840opt_v4icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019091220190910
3115253960 0 469341 840 131840opt_v4icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019091220190910
3117454616 0 470349 840 131840opt_v4icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019091220190910
3117453960 0 469341 840 131840opt_v4icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019091220190910
3119653960 0 469341 840 131840opt_v4icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019091220190910
3121853960 0 469341 840 131840opt_v4icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019091220190910
3132853688 0 469021 840 131840opt_v4icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019091220190910
3135053000 0 468413 840 131840opt_v4icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019091220190910
3139453688 0 469021 840 131840opt_v4icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019091220190910
3139453000 0 468413 840 131840opt_v4icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019091220190910
3139453000 0 468413 840 131840opt_v4icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019091220190910
3139453624 0 468957 840 131840opt_v4icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019091220190910
3146053688 0 469021 840 131840opt_v4icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019091220190910
3148254680 0 470413 840 131840opt_v4icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019091220190910
3152654616 0 470349 840 131840opt_v4icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019091220190910
3176853200 0 467285 840 131840opt_v4icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019091220190910
3203252320 0 466461 840 131840opt_v4icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019091220190910
3223035600 0 050981 840 744opticc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019091220190910
3251635600 0 050981 840 744opticc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019091220190910
3260435600 0 050981 840 744opticc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019091220190910
3260435600 0 050981 840 744opticc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019091220190910
3271436848 0 052581 840 744opticc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019091220190910
3271436848 0 052581 840 744opticc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019091220190910
3273634816 0 050229 840 744opticc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019091220190910
3275836848 0 052581 840 744opticc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019091220190910
3278035472 0 050805 840 744opticc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019091220190910
3282434816 0 050229 840 744opticc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019091220190910
3284635504 0 050837 840 744opticc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019091220190910
3284634528 0 048669 840 744opticc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019091220190910
3284634816 0 050229 840 744opticc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019091220190910
3306634816 0 050229 840 744opticc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019091220190910
3306636864 0 052597 840 744opticc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019091220190910
3311035504 0 050837 840 744opticc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019091220190910
3322035456 0 049541 840 744opticc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019091220190910
3348435504 0 050837 840 744opticc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019091220190910

Test failure

Implementation: crypto_hash/nasha256/opt
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 opt_v4
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer opt opt_v4
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer opt opt_v4
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer opt opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer opt opt_v4
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer opt opt_v4

Compiler output

Implementation: crypto_hash/nasha256/opt
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: 4, 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

Compiler output

Implementation: crypto_hash/nasha256/opt_v4
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: 4, 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

Compiler output

Implementation: crypto_hash/nasha256/opt_v4
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: crypto_hash/nasha256/opt_v4
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