Implementation notes: amd64, bitvise, crypto_core/aes256encrypt

Computer: bitvise
Architecture: amd64
CPU ID: GenuineIntel-000906ea-bfebfbff
SUPERCOP version: 20190910
Operation: crypto_core
Primitive: aes256encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
210	588 0 0	13849 776 776	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
210	588 0 0	13865 776 776	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
210	588 0 0	13849 776 776	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
215	606 0 0	14726 776 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
226	705 0 0	11405 768 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
228	619 0 0	10311 768 760	`dolbeau/aesenc-int`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
234	708 0 0	11453 768 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
236	700 0 0	10553 752 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
419	6272 0 0	17005 768 832	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
425	6108 0 0	19369 776 776	`dolbeau/std-4ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
425	6108 0 0	19385 776 776	`dolbeau/std-4ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
425	6108 0 0	19369 776 776	`dolbeau/std-4ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
430	6093 0 0	15783 768 760	`dolbeau/std-4ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
434	6333 0 0	20454 776 832	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
449	6336 0 0	17117 768 832	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
451	4289 0 0	15021 768 832	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
456	4051 0 0	13735 768 760	`dolbeau/std-2ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
457	4074 0 0	17337 776 776	`dolbeau/std-2ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
460	4074 0 0	17353 776 776	`dolbeau/std-2ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
460	4321 0 0	18454 776 832	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
464	4074 0 0	17337 776 776	`dolbeau/std-2ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
466	3031 0 0	16297 776 776	`dolbeau/std-1ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
466	3021 0 0	12711 768 760	`dolbeau/std-1ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
467	4325 0 0	14201 752 800	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
468	3031 0 0	16297 776 776	`dolbeau/std-1ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
470	3031 0 0	16313 776 776	`dolbeau/std-1ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
470	6371 0 0	16249 752 800	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
476	3275 0 0	14013 768 832	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
476	3306 0 0	17430 776 832	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
481	4308 0 0	15085 768 832	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
489	3290 0 0	13161 752 800	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
528	3284 0 0	14061 768 832	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
711	137 0 0	13615 792 776	`openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
712	137 0 0	13615 792 776	`openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
714	192 0 0	14541 808 800	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
715	137 0 0	10045 784 760	`openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
715	192 0 0	11116 800 800	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
715	194 0 0	10232 784 800	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
718	137 0 0	13615 792 776	`openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
718	195 0 0	11180 800 800	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
265335	4220 0 0	18366 776 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
412367	3013 0 0	16297 776 776	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
412781	2901 0 0	16185 776 776	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
412925	2901 0 0	16185 776 776	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910
796887	1969 0 0	12685 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
801041	1832 0 0	12597 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
827188	1659 0 0	11497 752 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190914	20190910
851714	1997 0 0	11655 768 760	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190914	20190910

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

core.c: core.c:13:34: warning: incompatible pointer types passing 'const unsigned int *' to parameter of type 'const __m128i *' [-Wincompatible-pointer-types]
core.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/emmintrin.h:3561:32: note: passing argument to parameter '__p' here
core.c: _mm_loadu_si128(__m128i const *__p)
core.c: ^
core.c: core.c:14:34: warning: incompatible pointer types passing 'const unsigned int *' to parameter of type 'const __m128i *' [-Wincompatible-pointer-types]
core.c: __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/emmintrin.h:3561:32: note: passing argument to parameter '__p' here
core.c: _mm_loadu_si128(__m128i const *__p)
core.c: ^
core.c: 2 warnings generated.

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

core.c: core.c: In function 'aes256ni_setkey_encrypt':
core.c: core.c:13:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
core.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
core.c: ^
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/xmmintrin.h:1252:0,
core.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:29,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/emmintrin.h:701:1: note: expected 'const __vector(2) long long int *' but argument is of type 'const unsigned int *'
core.c: _mm_loadu_si128 (__m128i_u const *__P)
core.c: ^~~~~~~~~~~~~~~
core.c: core.c:14:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
core.c: __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
core.c: ^
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/xmmintrin.h:1252:0,
core.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:29,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/emmintrin.h:701:1: note: expected 'const __vector(2) long long int *' but argument is of type 'const unsigned int *'
core.c: _mm_loadu_si128 (__m128i_u const *__P)
core.c: ^~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int