Implementation notes: amd64, genji239, crypto_aead/aeadaes256ocbtaglen128v1

Computer: genji239
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_aead
Primitive: aeadaes256ocbtaglen128v1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6356	9736 0 0	32453 856 864	`dolbeau/aesenc-int`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191020	20191017
6384	9752 0 0	32565 856 864	`dolbeau/aesenc-int`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191020	20191017
6386	9752 0 0	32565 856 864	`dolbeau/aesenc-int`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191020	20191017
6386	9736 0 0	32453 856 864	`dolbeau/aesenc-int`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191020	20191017
6392	9736 0 0	32453 856 864	`dolbeau/aesenc-int`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191020	20191017
6392	9752 0 0	32565 856 864	`dolbeau/aesenc-int`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191020	20191017
6392	9752 0 0	32565 856 864	`dolbeau/aesenc-int`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191020	20191017
6394	9736 0 0	32453 856 864	`dolbeau/aesenc-int`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191020	20191017
6394	10120 0 0	32901 856 864	`dolbeau/aesenc-int`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191020	20191017
6396	10120 0 0	32901 856 864	`dolbeau/aesenc-int`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191020	20191017
6398	10120 0 0	32901 856 864	`dolbeau/aesenc-int`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191020	20191017
6398	10120 0 0	32901 856 864	`dolbeau/aesenc-int`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191020	20191017
6402	10312 0 0	33429 856 864	`dolbeau/aesenc-int`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191020	20191017
6404	10312 0 0	33429 856 864	`dolbeau/aesenc-int`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191020	20191017
6406	10312 0 0	33429 856 864	`dolbeau/aesenc-int`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191020	20191017
6408	10312 0 0	33429 856 864	`dolbeau/aesenc-int`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191020	20191017
6436	10496 0 0	32021 856 864	`dolbeau/aesenc-int`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191020	20191017
6482	10776 0 0	32245 856 864	`dolbeau/aesenc-int`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191020	20191017
6530	10979 0 0	30233 816 896	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
6600	8920 0 0	32877 856 928	`dolbeau/aesenc-int`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191020	20191017
6604	9088 24 0	32637 896 928	`opt`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191020	20191017
6606	8920 0 0	32525 856 928	`dolbeau/aesenc-int`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191020	20191017
6606	8920 0 0	32317 856 928	`dolbeau/aesenc-int`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191020	20191017
6612	8920 0 0	32205 856 928	`dolbeau/aesenc-int`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191020	20191017
6620	9072 24 0	33149 896 928	`opt`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191020	20191017
6676	8928 24 0	32365 896 928	`opt`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191020	20191017
6780	8928 24 0	32653 896 928	`opt`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191020	20191017
6990	9056 24 0	32325 896 864	`opt`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191020	20191017
7010	8944 24 0	31877 896 864	`opt`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191020	20191017
7028	8944 24 0	31877 896 864	`opt`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191020	20191017
7110	9056 24 0	32325 896 864	`opt`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191020	20191017
7140	9056 24 0	32325 896 864	`opt`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191020	20191017
7206	8944 24 0	31877 896 864	`opt`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191020	20191017
7262	9056 24 0	32325 896 864	`opt`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191020	20191017
7298	8944 24 0	31813 896 864	`opt`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191020	20191017
7312	8944 24 0	31813 896 864	`opt`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191020	20191017
7314	10559 21 0	30025 861 896	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
7334	8880 24 0	31845 896 864	`opt`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191020	20191017
7350	8880 24 0	31845 896 864	`opt`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191020	20191017
7396	8880 24 0	31845 896 864	`opt`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191020	20191017
7490	8944 24 0	31813 896 864	`opt`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191020	20191017
7528	8880 24 0	31845 896 864	`opt`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191020	20191017
7550	8944 24 0	31813 896 864	`opt`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191020	20191017
7624	5843 0 0	22396 808 896	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
8192	5387 0 0	21724 808 896	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
10060	4235 0 0	19276 792 896	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
10720	8944 24 0	31877 896 864	`opt`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191020	20191017
11666	6296 21 0	23113 861 896	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
12876	7600 20 0	30114 964 864	`opt`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191020	20191017
14046	6364 21 0	22953 861 896	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
17240	7584 20 0	30154 964 864	`opt`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191020	20191017
19310	4997 21 0	20188 837 896	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
243580	12840 0 0	36749 888 928	`ref`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191020	20191017
244012	12712 0 0	36973 888 928	`ref`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191020	20191017
246874	13896 0 0	37629 888 928	`ref`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191020	20191017
247282	14056 0 0	37677 888 928	`ref`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191020	20191017
249398	18632 0 0	41781 888 864	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191020	20191017
249566	18200 0 0	40061 888 864	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191020	20191017
249816	18456 0 0	41509 888 864	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191020	20191017
249846	18632 0 0	41781 888 864	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191020	20191017
250020	18632 0 0	41781 888 864	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191020	20191017
250066	18456 0 0	41509 888 864	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191020	20191017
250066	18824 0 0	41941 888 864	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191020	20191017
250090	19496 0 0	42949 888 864	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191020	20191017
250156	18456 0 0	41509 888 864	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191020	20191017
250166	19496 0 0	42949 888 864	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191020	20191017
250300	18456 0 0	41509 888 864	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191020	20191017
250542	19496 0 0	42949 888 864	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191020	20191017
250724	18824 0 0	41941 888 864	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191020	20191017
250858	18472 0 0	40277 888 864	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191020	20191017
250936	19496 0 0	42949 888 864	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191020	20191017
251020	18632 0 0	41781 888 864	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191020	20191017
251190	18824 0 0	41941 888 864	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191020	20191017
256536	18824 0 0	41941 888 864	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191020	20191017
258168	8915 0 0	28545 848 896	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
290230	3459 0 0	20380 840 896	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
293760	3112 0 0	19820 840 896	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017
298020	1988 0 0	17356 824 896	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191020	20191017

Test failure

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	opt
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	opt
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	ref
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	ref

Compiler output

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

encrypt.c: encrypt.c: In function 'aes256ni_setkey_encrypt':
encrypt.c: encrypt.c:74:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
encrypt.c: 74 | __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
encrypt.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: | |
encrypt.c: | const unsigned int *
encrypt.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,
encrypt.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,
encrypt.c: from encrypt.c:45:
encrypt.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 *'
encrypt.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
encrypt.c: | ~~~~~~~~~~~~~~~~~^~~
encrypt.c: encrypt.c:75:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
encrypt.c: 75 | __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
encrypt.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: | |
encrypt.c: | const unsigned int *
encrypt.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,
encrypt.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,
encrypt.c: from encrypt.c:45:
encrypt.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 *'
encrypt.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
encrypt.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 -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer

encrypt.c: encrypt.c(74): warning #167: argument of type "const unsigned int *" is incompatible with parameter of type "const union __m128i *"
encrypt.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
encrypt.c: ^
encrypt.c:
encrypt.c: encrypt.c(75): warning #167: argument of type "const unsigned int *" is incompatible with parameter of type "const union __m128i *"
encrypt.c: __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
encrypt.c: ^
encrypt.c:

Number of similar (compiler,implementation) pairs: 24, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	dolbeau/aesenc-int
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	dolbeau/aesenc-int