Implementation notes: amd64, pmnod003, crypto_core/aes128encrypt

Computer: pmnod003
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20190910
Operation: crypto_core
Primitive: aes128encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
162	512 0 0	17021 856 832	`dolbeau/aesenc-int`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
162	512 0 0	16925 856 832	`dolbeau/aesenc-int`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
164	461 0 0	13731 832 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
164	480 0 0	16307 856 768	`dolbeau/aesenc-int`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
164	480 0 0	16339 856 768	`dolbeau/aesenc-int`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
164	480 0 0	17117 856 832	`dolbeau/aesenc-int`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
164	480 0 0	16589 856 832	`dolbeau/aesenc-int`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
164	480 0 0	16339 856 768	`dolbeau/aesenc-int`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
164	480 0 0	16693 856 768	`dolbeau/aesenc-int`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
166	480 0 0	16307 856 768	`dolbeau/aesenc-int`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
166	480 0 0	16277 856 768	`dolbeau/aesenc-int`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
170	592 0 0	15263 856 768	`dolbeau/aesenc-int`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
172	592 0 0	15335 856 768	`dolbeau/aesenc-int`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
172	592 0 0	15139 856 768	`dolbeau/aesenc-int`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
172	592 0 0	15195 856 768	`dolbeau/aesenc-int`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
178	510 0 0	11038 824 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
178	507 0 0	10126 808 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
180	509 0 0	10998 824 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
314	6962 0 0	20235 832 800	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
320	9280 0 0	24055 856 768	`dolbeau/std-4ft`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
322	6215 0 0	16766 824 800	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
322	9296 0 0	25677 856 832	`dolbeau/std-4ft`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
322	9280 0 0	23883 856 768	`dolbeau/std-4ft`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
326	9232 0 0	23779 856 768	`dolbeau/std-4ft`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
330	9232 0 0	23935 856 768	`dolbeau/std-4ft`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
332	9264 0 0	25837 856 832	`dolbeau/std-4ft`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
332	9296 0 0	25341 856 832	`dolbeau/std-4ft`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
332	9264 0 0	25741 856 832	`dolbeau/std-4ft`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
338	6190 0 0	15854 808 800	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
340	9360 0 0	25219 856 768	`dolbeau/std-4ft`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
340	9360 0 0	25219 856 768	`dolbeau/std-4ft`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
340	9296 0 0	25093 856 768	`dolbeau/std-4ft`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
342	4968 0 0	18235 832 800	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
342	9264 0 0	25477 856 768	`dolbeau/std-4ft`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
344	6204 0 0	16726 824 800	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
344	9344 0 0	25235 856 768	`dolbeau/std-4ft`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
344	9344 0 0	25235 856 768	`dolbeau/std-4ft`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
354	4158 0 0	13822 808 800	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
356	3967 0 0	17243 832 800	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
356	4199 0 0	14750 824 800	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
366	3122 0 0	12782 808 800	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
366	6720 0 0	21495 856 768	`dolbeau/std-1ft`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
366	4204 0 0	14726 824 800	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
366	7840 0 0	24221 856 832	`dolbeau/std-2ft`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
368	6784 0 0	22829 856 832	`dolbeau/std-1ft`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
368	6848 0 0	21551 856 768	`dolbeau/std-1ft`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
370	3201 0 0	13758 824 800	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
370	6720 0 0	21323 856 768	`dolbeau/std-1ft`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
370	7760 0 0	24333 856 832	`dolbeau/std-2ft`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
370	7840 0 0	23885 856 832	`dolbeau/std-2ft`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
370	7760 0 0	23973 856 768	`dolbeau/std-2ft`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
370	7840 0 0	23637 856 768	`dolbeau/std-2ft`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
370	7760 0 0	24237 856 832	`dolbeau/std-2ft`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
370	7696 0 0	22243 856 768	`dolbeau/std-2ft`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
372	6832 0 0	23045 856 768	`dolbeau/std-1ft`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
372	6784 0 0	22581 856 768	`dolbeau/std-1ft`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
372	7856 0 0	22631 856 768	`dolbeau/std-2ft`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
372	7856 0 0	22459 856 768	`dolbeau/std-2ft`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
374	6832 0 0	23405 856 832	`dolbeau/std-1ft`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
374	6832 0 0	23309 856 832	`dolbeau/std-1ft`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
374	7696 0 0	22399 856 768	`dolbeau/std-2ft`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
378	7936 0 0	23827 856 768	`dolbeau/std-2ft`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
382	6848 0 0	22739 856 768	`dolbeau/std-1ft`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
382	6848 0 0	21395 856 768	`dolbeau/std-1ft`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
382	7936 0 0	23827 856 768	`dolbeau/std-2ft`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
382	7776 0 0	23635 856 768	`dolbeau/std-2ft`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
384	6848 0 0	22739 856 768	`dolbeau/std-1ft`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
384	6784 0 0	23165 856 832	`dolbeau/std-1ft`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
386	3189 0 0	13718 824 800	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
390	6960 0 0	22819 856 768	`dolbeau/std-1ft`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
390	7776 0 0	23635 856 768	`dolbeau/std-2ft`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
392	6960 0 0	22819 856 768	`dolbeau/std-1ft`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
540	144 0 0	16393 872 832	`openssl`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
540	144 0 0	16207 872 768	`openssl`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
542	138 0 0	13623 848 800	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
542	144 0 0	16175 872 768	`openssl`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
542	144 0 0	16921 872 832	`openssl`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
542	144 0 0	14935 872 768	`openssl`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	16207 872 768	`openssl`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	16175 872 768	`openssl`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	16561 872 768	`openssl`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	16145 872 768	`openssl`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	16729 872 832	`openssl`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	15003 872 768	`openssl`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
544	144 0 0	15075 872 768	`openssl`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
546	138 0 0	10874 840 800	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
546	140 0 0	9930 824 800	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
548	144 0 0	16825 872 832	`openssl`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
550	144 0 0	14879 872 768	`openssl`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
556	139 0 0	10834 840 800	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
175164	3518 0 0	16811 832 800	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
401890	12080 0 0	28573 856 832	`ref`	`icc_-xCORE-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
409236	11440 0 0	27837 856 832	`ref`	`icc_-xCORE-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
423090	11696 0 0	28285 856 832	`ref`	`icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer`	20190912	20190910
429132	11728 0 0	27789 856 832	`ref`	`icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer`	20190912	20190910
456780	12800 0 0	29029 856 768	`ref`	`icc_-xCORE-AVX2_-O2_-fomit-frame-pointer`	20190912	20190910
462032	11744 0 0	27557 856 768	`ref`	`icc_-xCORE-AVX2_-O3_-fomit-frame-pointer`	20190912	20190910
473470	15712 0 0	30315 856 768	`ref`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20190912	20190910
473506	15712 0 0	30455 856 768	`ref`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20190912	20190910
474164	16192 0 0	30863 856 768	`ref`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20190912	20190910
474190	16192 0 0	30739 856 768	`ref`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20190912	20190910
476704	16304 0 0	32131 856 768	`ref`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20190912	20190910
476718	16304 0 0	32131 856 768	`ref`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20190912	20190910
476720	16192 0 0	32051 856 768	`ref`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20190912	20190910
478344	16192 0 0	32051 856 768	`ref`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20190912	20190910
586246	1687 0 0	12190 824 800	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
588822	1538 0 0	11134 808 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910
604360	1717 0 0	12262 824 800	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190912	20190910

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 'aes128ni_setkey_encrypt':
core.c: core.c:12:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
core.c: 12 | __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: | |
core.c: | const unsigned int *
core.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/xmmintrin.h:1255,
core.c: from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/immintrin.h:29,
core.c: from core.c:9:
core.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/emmintrin.h:701:35: note: expected 'const __vector(2) long long int *' but argument is of type 'const unsigned int *'
core.c: 701 | _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

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: icc -xAVX -O2 -fomit-frame-pointer

core.c: core.c(12): warning #167: argument of type "const unsigned int *" is incompatible with parameter of type "const union __m128i *"
core.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
core.c: ^
core.c:

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
icc -xAVX -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xAVX -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCOMMON-AVX512 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCOMMON-AVX512 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX-I -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX-I -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX2 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX2 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX512 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xCORE-AVX512 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xSSE4.1 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xSSE4.1 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xSSE4.2 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -xSSE4.2 -O3 -fomit-frame-pointer	dolbeau/aesenc-int