Implementation notes: amd64, pmnod076, crypto_stream/aes128ctr

Computer: pmnod076
Architecture: amd64
CPU ID: GenuineIntel-00050657-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_stream
Primitive: aes128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
11683672 0 020421 856 824dolbeau/aesenc-inticc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019102320191017
11683672 0 020421 856 824dolbeau/aesenc-inticc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019102320191017
11683672 0 020421 856 824dolbeau/aesenc-inticc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019102320191017
11723672 0 020821 856 824dolbeau/aesenc-inticc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019102320191017
11723672 0 020821 856 824dolbeau/aesenc-inticc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019102320191017
11723672 0 020821 856 824dolbeau/aesenc-inticc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019102320191017
11723672 0 020421 856 824dolbeau/aesenc-inticc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019102320191017
11764176 0 022133 856 856dolbeau/aesenc-inticc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019102320191017
11764224 0 021541 856 856dolbeau/aesenc-inticc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019102320191017
11783672 0 020821 856 824dolbeau/aesenc-inticc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019102320191017
11964160 0 021765 856 856dolbeau/aesenc-inticc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019102320191017
11984240 0 021669 856 856dolbeau/aesenc-inticc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019102320191017
12004402 0 018803 832 856dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
12143472 0 020253 856 824dolbeau/aesenc-inticc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019102320191017
12183472 0 020253 856 824dolbeau/aesenc-inticc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019102320191017
12183472 0 020253 856 824dolbeau/aesenc-inticc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019102320191017
12223832 0 019301 856 824dolbeau/aesenc-inticc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019102320191017
12363472 0 020253 856 824dolbeau/aesenc-inticc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019102320191017
12723456 0 020269 856 824dolbeau/aesenc-inticc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019102320191017
12723456 0 020269 856 824dolbeau/aesenc-inticc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019102320191017
12743784 0 019309 856 824dolbeau/aesenc-inticc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019102320191017
12803456 0 020269 856 824dolbeau/aesenc-inticc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019102320191017
12823456 0 020269 856 824dolbeau/aesenc-inticc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019102320191017
1570720 0 018258 912 824opensslicc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019102320191017
1570720 0 018210 912 824opensslicc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019102320191017
1572358 0 011427 864 824opensslgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
1574720 0 016930 912 824opensslicc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019102320191017
1574720 0 018226 912 824opensslicc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019102320191017
1574720 0 018258 912 824opensslicc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019102320191017
1576720 0 018610 912 824opensslicc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019102320191017
1576720 0 018210 912 824opensslicc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019102320191017
1576720 0 018610 912 824opensslicc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019102320191017
1578720 0 018210 912 824opensslicc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019102320191017
1578720 0 018258 912 824opensslicc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019102320191017
1578720 0 018610 912 824opensslicc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019102320191017
1580720 0 018610 912 824opensslicc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019102320191017
1580720 0 018226 912 824opensslicc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019102320191017
1580720 0 018258 912 824opensslicc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019102320191017
1580720 0 018226 912 824opensslicc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019102320191017
1582654 0 015768 888 856opensslgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
1582720 0 016986 912 824opensslicc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019102320191017
1582720 0 018778 912 856opensslicc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019102320191017
1582720 0 018210 912 824opensslicc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019102320191017
1584720 0 018890 912 856opensslicc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019102320191017
1586437 0 012712 888 856opensslgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
1586720 0 019066 912 856opensslicc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019102320191017
1590472 0 012856 888 856opensslgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
1616720 0 018226 912 824opensslicc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019102320191017
1756720 0 019418 912 856opensslicc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019102320191017
354421038 2800 01354556 144871 10264cryptoppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
35442939 0 014558 824 856dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
356220196 2800 01353353 144879 10264cryptoppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
356232664 2760 01401659 155271 10312cryptoppicpc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019102320191017
356232664 2760 01401659 155271 10312cryptoppicpc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019102320191017
356432664 2760 01401659 155271 10312cryptoppicpc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019102320191017
35722893 0 014406 824 856dolbeau/aesenc-intgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
357232328 2760 01401347 155271 10312cryptoppicpc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019102320191017
357432400 2760 01402299 155271 10312cryptoppicpc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019102320191017
357432664 2760 01402347 155271 10312cryptoppicpc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019102320191017
358032664 2760 01402067 155271 10312cryptoppicpc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019102320191017
358232328 2760 01401347 155271 10312cryptoppicpc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019102320191017
358432664 2760 01401659 155271 10312cryptoppicpc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019102320191017
358632328 2760 01401347 155271 10312cryptoppicpc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019102320191017
358632664 2760 01402227 155271 10312cryptoppicpc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019102320191017
358832664 2760 01402067 155271 10312cryptoppicpc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019102320191017
359032232 2760 01399963 155271 10312cryptoppicpc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019102320191017
359032232 2760 01400011 155271 10312cryptoppicpc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019102320191017
359032664 2760 01402067 155271 10312cryptoppicpc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019102320191017
360232664 2760 01402067 155271 10312cryptoppicpc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019102320191017
360632328 2760 01401371 155271 10312cryptoppicpc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019102320191017
360832328 2760 01401371 155271 10312cryptoppicpc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019102320191017
361032328 2760 01401371 155271 10312cryptoppicpc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019102320191017
361432328 2760 01401371 155271 10312cryptoppicpc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019102320191017
362432400 2760 01402667 155271 10312cryptoppicpc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019102320191017
363221454 2800 01357700 144871 10264cryptoppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
36348157 2960 01342485 145639 10264cryptoppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
364432328 2760 01401347 155271 10312cryptoppicpc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019102320191017
44001707 0 012190 808 824dolbeau/aesenc-intgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017

Test failure

Implementation: crypto_stream/aes128ctr/dolbeau/aesenc-int
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer dolbeau/aesenc-int openssl
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer dolbeau/aesenc-int openssl
icpc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer cryptopp
icpc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer cryptopp

Compiler output

Implementation: crypto_stream/aes128ctr/dolbeau/aesenc-int
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:
CompilerImplementations
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: crypto_stream/aes128ctr/dolbeau/aesenc-int
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:
CompilerImplementations
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