Implementation notes: amd64, pmnod076, crypto_stream/aes128ctr

Computer: pmnod076
Architecture: amd64
CPU ID: GenuineIntel-00050657-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_stream
Primitive: aes128ctr

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1168	3672 0 0	20421 856 824	`dolbeau/aesenc-int`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191023	20191017
1168	3672 0 0	20421 856 824	`dolbeau/aesenc-int`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191023	20191017
1168	3672 0 0	20421 856 824	`dolbeau/aesenc-int`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191023	20191017
1172	3672 0 0	20821 856 824	`dolbeau/aesenc-int`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191023	20191017
1172	3672 0 0	20821 856 824	`dolbeau/aesenc-int`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191023	20191017
1172	3672 0 0	20821 856 824	`dolbeau/aesenc-int`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191023	20191017
1172	3672 0 0	20421 856 824	`dolbeau/aesenc-int`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191023	20191017
1176	4176 0 0	22133 856 856	`dolbeau/aesenc-int`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191023	20191017
1176	4224 0 0	21541 856 856	`dolbeau/aesenc-int`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191023	20191017
1178	3672 0 0	20821 856 824	`dolbeau/aesenc-int`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191023	20191017
1196	4160 0 0	21765 856 856	`dolbeau/aesenc-int`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191023	20191017
1198	4240 0 0	21669 856 856	`dolbeau/aesenc-int`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191023	20191017
1200	4402 0 0	18803 832 856	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
1214	3472 0 0	20253 856 824	`dolbeau/aesenc-int`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191023	20191017
1218	3472 0 0	20253 856 824	`dolbeau/aesenc-int`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191023	20191017
1218	3472 0 0	20253 856 824	`dolbeau/aesenc-int`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191023	20191017
1222	3832 0 0	19301 856 824	`dolbeau/aesenc-int`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191023	20191017
1236	3472 0 0	20253 856 824	`dolbeau/aesenc-int`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191023	20191017
1272	3456 0 0	20269 856 824	`dolbeau/aesenc-int`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191023	20191017
1272	3456 0 0	20269 856 824	`dolbeau/aesenc-int`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191023	20191017
1274	3784 0 0	19309 856 824	`dolbeau/aesenc-int`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191023	20191017
1280	3456 0 0	20269 856 824	`dolbeau/aesenc-int`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191023	20191017
1282	3456 0 0	20269 856 824	`dolbeau/aesenc-int`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191023	20191017
1570	720 0 0	18258 912 824	`openssl`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191023	20191017
1570	720 0 0	18210 912 824	`openssl`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191023	20191017
1572	358 0 0	11427 864 824	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
1574	720 0 0	16930 912 824	`openssl`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191023	20191017
1574	720 0 0	18226 912 824	`openssl`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191023	20191017
1574	720 0 0	18258 912 824	`openssl`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191023	20191017
1576	720 0 0	18610 912 824	`openssl`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191023	20191017
1576	720 0 0	18210 912 824	`openssl`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191023	20191017
1576	720 0 0	18610 912 824	`openssl`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191023	20191017
1578	720 0 0	18210 912 824	`openssl`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191023	20191017
1578	720 0 0	18258 912 824	`openssl`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191023	20191017
1578	720 0 0	18610 912 824	`openssl`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191023	20191017
1580	720 0 0	18610 912 824	`openssl`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191023	20191017
1580	720 0 0	18226 912 824	`openssl`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191023	20191017
1580	720 0 0	18258 912 824	`openssl`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191023	20191017
1580	720 0 0	18226 912 824	`openssl`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191023	20191017
1582	654 0 0	15768 888 856	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
1582	720 0 0	16986 912 824	`openssl`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191023	20191017
1582	720 0 0	18778 912 856	`openssl`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191023	20191017
1582	720 0 0	18210 912 824	`openssl`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191023	20191017
1584	720 0 0	18890 912 856	`openssl`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191023	20191017
1586	437 0 0	12712 888 856	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
1586	720 0 0	19066 912 856	`openssl`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191023	20191017
1590	472 0 0	12856 888 856	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
1616	720 0 0	18226 912 824	`openssl`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191023	20191017
1756	720 0 0	19418 912 856	`openssl`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191023	20191017
3544	21038 2800 0	1354556 144871 10264	`cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3544	2939 0 0	14558 824 856	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3562	20196 2800 0	1353353 144879 10264	`cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3562	32664 2760 0	1401659 155271 10312	`cryptopp`	`icpc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191023	20191017
3562	32664 2760 0	1401659 155271 10312	`cryptopp`	`icpc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191023	20191017
3564	32664 2760 0	1401659 155271 10312	`cryptopp`	`icpc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191023	20191017
3572	32328 2760 0	1401347 155271 10312	`cryptopp`	`icpc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191023	20191017
3572	2893 0 0	14406 824 856	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3574	32400 2760 0	1402299 155271 10312	`cryptopp`	`icpc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191023	20191017
3574	32664 2760 0	1402347 155271 10312	`cryptopp`	`icpc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191023	20191017
3580	32664 2760 0	1402067 155271 10312	`cryptopp`	`icpc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191023	20191017
3582	32328 2760 0	1401347 155271 10312	`cryptopp`	`icpc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191023	20191017
3584	32664 2760 0	1401659 155271 10312	`cryptopp`	`icpc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191023	20191017
3586	32328 2760 0	1401347 155271 10312	`cryptopp`	`icpc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191023	20191017
3586	32664 2760 0	1402227 155271 10312	`cryptopp`	`icpc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191023	20191017
3588	32664 2760 0	1402067 155271 10312	`cryptopp`	`icpc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191023	20191017
3590	32232 2760 0	1399963 155271 10312	`cryptopp`	`icpc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191023	20191017
3590	32232 2760 0	1400011 155271 10312	`cryptopp`	`icpc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191023	20191017
3590	32664 2760 0	1402067 155271 10312	`cryptopp`	`icpc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191023	20191017
3602	32664 2760 0	1402067 155271 10312	`cryptopp`	`icpc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191023	20191017
3606	32328 2760 0	1401371 155271 10312	`cryptopp`	`icpc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191023	20191017
3608	32328 2760 0	1401371 155271 10312	`cryptopp`	`icpc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191023	20191017
3610	32328 2760 0	1401371 155271 10312	`cryptopp`	`icpc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191023	20191017
3614	32328 2760 0	1401371 155271 10312	`cryptopp`	`icpc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191023	20191017
3624	32400 2760 0	1402667 155271 10312	`cryptopp`	`icpc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191023	20191017
3632	21454 2800 0	1357700 144871 10264	`cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3634	8157 2960 0	1342485 145639 10264	`cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
3644	32328 2760 0	1401347 155271 10312	`cryptopp`	`icpc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191023	20191017
4400	1707 0 0	12190 808 824	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017

Test failure

Implementation: cryptopp
Security model: unknown
Compiler: icpc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer

error 111

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

Compiler	Implementations
icpc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	cryptopp
icpc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	cryptopp
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	openssl
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	openssl

Compiler output

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

aesenc-int.c: aesenc-int.c: In function 'aesni_key128_expand':
aesenc-int.c: aesenc-int.c:28:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
aesenc-int.c: 28 | __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
aesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: | |
aesenc-int.c: | const unsigned int *
aesenc-int.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,
aesenc-int.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,
aesenc-int.c: from aesenc-int.c:12:
aesenc-int.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 *'
aesenc-int.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
aesenc-int.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

aesenc-int.c: aesenc-int.c(28): warning #167: argument of type "const unsigned int *" is incompatible with parameter of type "const union __m128i *"
aesenc-int.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
aesenc-int.c: ^
aesenc-int.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