Implementation notes: amd64, cannon, crypto_core/aes256decrypt

Computer: cannon
Architecture: amd64
CPU ID: GenuineIntel-00060663-bfebfbff
SUPERCOP version: 20190910
Operation: crypto_core
Primitive: aes256decrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
210	661 0 0	14077 808 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
212	644 0 0	14499 832 808	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
212	644 0 0	14819 832 808	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
214	644 0 0	14499 832 808	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
252	801 0 0	11364 800 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
252	790 0 0	11412 800 832	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
258	770 0 0	10532 784 800	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
620	7531 0 0	18132 800 832	`dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
634	11646 0 0	22244 800 832	`dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
636	7525 0 0	17316 784 800	`dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
640	5468 0 0	15252 784 800	`dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
640	11613 0 0	25467 832 808	`dolbeau/std-4rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
640	11613 0 0	25467 832 808	`dolbeau/std-4rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
640	11584 0 0	22161 824 760	`dolbeau/std-4rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
640	11646 0 0	25061 808 832	`dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
642	11613 0 0	25787 832 808	`dolbeau/std-4rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
654	5456 0 0	18869 808 832	`dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
656	11595 0 0	21380 784 800	`dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
664	5503 0 0	16100 800 832	`dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
676	11711 0 0	22356 800 832	`dolbeau/std-4rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
678	7561 0 0	18212 800 832	`dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
690	7559 0 0	20965 808 832	`dolbeau/std-2rt-nodk`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
698	7574 0 0	21739 832 808	`dolbeau/std-2rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
698	7574 0 0	21419 832 808	`dolbeau/std-2rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
700	5523 0 0	19371 832 808	`dolbeau/std-1rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
700	5523 0 0	19691 832 808	`dolbeau/std-1rt-nodk`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
700	5523 0 0	19371 832 808	`dolbeau/std-1rt-nodk`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
700	7574 0 0	21419 832 808	`dolbeau/std-2rt-nodk`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
704	5490 0 0	16065 824 760	`dolbeau/std-1rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
706	7552 0 0	18129 824 760	`dolbeau/std-2rt-nodk`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
714	5515 0 0	16164 800 832	`dolbeau/std-1rt-nodk`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
1340	187 0 0	14237 848 808	`openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
1340	187 0 0	10979 840 760	`openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
1342	189 0 0	10958 816 832	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
1348	187 0 0	14237 848 808	`openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
1348	200 0 0	11030 816 832	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
1348	191 0 0	10126 800 800	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
1354	187 0 0	14557 848 808	`openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
1354	189 0 0	13807 824 832	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
270162	5942 0 0	19413 808 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
485954	6328 0 0	20499 832 808	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
488968	3400 0 0	17251 832 808	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
488980	3400 0 0	17251 832 808	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
932324	2722 0 0	13281 824 760	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
948124	2514 0 0	13100 800 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
985820	2238 0 0	11988 784 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
993460	2473 0 0	13108 800 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910

Compiler output

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

Number of similar (compiler,implementation) pairs: 3, 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

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: clang -march=native -Os -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/clang/8.0.1/include/emmintrin.h:3567:32: 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/clang/8.0.1/include/emmintrin.h:3567:32: note: passing argument to parameter '__p' here
core.c: _mm_loadu_si128(__m128i const *__p)
core.c: ^
core.c: core.c:88:5: warning: loop not unrolled: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering [-Wpass-failed=transform-warning]
core.c: int crypto_core(
core.c: ^
core.c: ./crypto_core.h:6:21: note: expanded from macro 'crypto_core'
core.c: #define crypto_core crypto_core_aes256decrypt
core.c: ^
core.c: ./crypto_core_aes256decrypt.h:17:35: note: expanded from macro 'crypto_core_aes256decrypt'
core.c: #define crypto_core_aes256decrypt crypto_core_aes256decrypt_dolbeau_aesenc_int
core.c: ^
core.c: core.c:88:5: warning: loop not unrolled: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering [-Wpass-failed=transform-warning]
core.c: ./crypto_core.h:6:21: note: expanded from macro 'crypto_core'
core.c: #define crypto_core crypto_core_aes256decrypt
core.c: ^
core.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
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: 13 | __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 /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/xmmintrin.h:1255,
core.c: from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:29,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/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: | ~~~~~~~~~~~~~~~~~^~~
core.c: core.c:14:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
core.c: 14 | __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: | |
core.c: | const unsigned int *
core.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/xmmintrin.h:1255,
core.c: from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:29,
core.c: from core.c:9:
core.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/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