Implementation notes: amd64, katana, crypto_aead/paeq64

Computer: katana
Architecture: amd64
CPU ID: GenuineIntel-000006f6-bfebfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: paeq64

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3119192	? ? ?	? ? ?	`ref`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161024	20161009
3123144	? ? ?	? ? ?	`ref`	`clang++_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20161024	20161009
3128448	? ? ?	? ? ?	`ref`	`clang++_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161024	20161009
3129312	? ? ?	? ? ?	`ref`	`clang++_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161024	20161009
3134408	? ? ?	? ? ?	`ref`	`clang++_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161024	20161009
3170400	? ? ?	? ? ?	`ref`	`clang++_-O3_-fomit-frame-pointer_-Qunused-arguments`	20161024	20161009
5573064	? ? ?	? ? ?	`ref`	`g++_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20161024	20161009
5617408	? ? ?	? ? ?	`ref`	`g++_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20161024	20161009
5618064	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-O3_-fomit-frame-pointer`	20161024	20161009
5620216	? ? ?	? ? ?	`ref`	`g++_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20161024	20161009
5634216	? ? ?	? ? ?	`ref`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20161024	20161009
5642536	? ? ?	? ? ?	`ref`	`g++_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20161024	20161009
5645664	? ? ?	? ? ?	`ref`	`g++_-m64_-O3_-fomit-frame-pointer`	20161024	20161009
5669552	? ? ?	? ? ?	`ref`	`g++_-O3_-fomit-frame-pointer`	20161024	20161009
8074432	? ? ?	? ? ?	`ref`	`g++_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20161024	20161009
8080000	? ? ?	? ? ?	`ref`	`g++_-march=k8_-O3_-fomit-frame-pointer`	20161024	20161009
8131832	? ? ?	? ? ?	`ref`	`g++_-m64_-march=k8_-O3_-fomit-frame-pointer`	20161024	20161009
8133760	? ? ?	? ? ?	`ref`	`g++_-march=barcelona_-O3_-fomit-frame-pointer`	20161024	20161009
8242392	? ? ?	? ? ?	`ref`	`g++_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20161024	20161009
8242568	? ? ?	? ? ?	`ref`	`g++_-march=nocona_-O3_-fomit-frame-pointer`	20161024	20161009
9299640	? ? ?	? ? ?	`ref`	`g++_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20161024	20161009
11919816	? ? ?	? ? ?	`ref`	`g++_-m64_-march=k8_-O2_-fomit-frame-pointer`	20161024	20161009
11966304	? ? ?	? ? ?	`ref`	`g++_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20161024	20161009
11968992	? ? ?	? ? ?	`ref`	`g++_-march=nocona_-O2_-fomit-frame-pointer`	20161024	20161009
11999112	? ? ?	? ? ?	`ref`	`g++_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20161024	20161009
12002096	? ? ?	? ? ?	`ref`	`g++_-march=barcelona_-O2_-fomit-frame-pointer`	20161024	20161009
12048560	? ? ?	? ? ?	`ref`	`g++_-m64_-O2_-fomit-frame-pointer`	20161024	20161009
12052664	? ? ?	? ? ?	`ref`	`g++_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20161024	20161009
12055544	? ? ?	? ? ?	`ref`	`g++_-march=k8_-O2_-fomit-frame-pointer`	20161024	20161009
12057880	? ? ?	? ? ?	`ref`	`g++_-O2_-fomit-frame-pointer`	20161024	20161009
12100016	? ? ?	? ? ?	`ref`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20161024	20161009
12102064	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20161024	20161009
12113680	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20161024	20161009
12128312	? ? ?	? ? ?	`ref`	`g++_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20161024	20161009
12129080	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-O2_-fomit-frame-pointer`	20161024	20161009
12161880	? ? ?	? ? ?	`ref`	`g++_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20161024	20161009
12324872	? ? ?	? ? ?	`ref`	`g++_-march=barcelona_-O_-fomit-frame-pointer`	20161024	20161009
12331016	? ? ?	? ? ?	`ref`	`g++_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20161024	20161009
12331952	? ? ?	? ? ?	`ref`	`g++_-m64_-O_-fomit-frame-pointer`	20161024	20161009
12332432	? ? ?	? ? ?	`ref`	`g++_-O_-fomit-frame-pointer`	20161024	20161009
12357104	? ? ?	? ? ?	`ref`	`g++_-m64_-march=k8_-O_-fomit-frame-pointer`	20161024	20161009
12404608	? ? ?	? ? ?	`ref`	`g++_-m64_-march=nocona_-O_-fomit-frame-pointer`	20161024	20161009
12457352	? ? ?	? ? ?	`ref`	`g++_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20161024	20161009
12459432	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20161024	20161009
12462488	? ? ?	? ? ?	`ref`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20161024	20161009
12466592	? ? ?	? ? ?	`ref`	`g++_-m64_-march=corei7_-O_-fomit-frame-pointer`	20161024	20161009
12467256	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-O_-fomit-frame-pointer`	20161024	20161009
12495168	? ? ?	? ? ?	`ref`	`g++_-fno-schedule-insns_-O_-fomit-frame-pointer`	20161024	20161009
12501800	? ? ?	? ? ?	`ref`	`g++_-march=k8_-O_-fomit-frame-pointer`	20161024	20161009
12561808	? ? ?	? ? ?	`ref`	`g++_-march=nocona_-O_-fomit-frame-pointer`	20161024	20161009
12665336	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20161024	20161009
17591608	? ? ?	? ? ?	`ref`	`g++_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20161024	20161009
18421000	? ? ?	? ? ?	`ref`	`g++_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20161024	20161009
18685312	? ? ?	? ? ?	`ref`	`g++_-march=nocona_-Os_-fomit-frame-pointer`	20161024	20161009
18940008	? ? ?	? ? ?	`ref`	`g++_-march=barcelona_-Os_-fomit-frame-pointer`	20161024	20161009
18940544	? ? ?	? ? ?	`ref`	`g++_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20161024	20161009
18945224	? ? ?	? ? ?	`ref`	`g++_-Os_-fomit-frame-pointer`	20161024	20161009
18945584	? ? ?	? ? ?	`ref`	`g++_-m64_-Os_-fomit-frame-pointer`	20161024	20161009
18945808	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-Os_-fomit-frame-pointer`	20161024	20161009
18979176	? ? ?	? ? ?	`ref`	`g++_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20161024	20161009
19147936	? ? ?	? ? ?	`ref`	`g++_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20161024	20161009
19156656	? ? ?	? ? ?	`ref`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20161024	20161009
19203744	? ? ?	? ? ?	`ref`	`g++_-m64_-march=k8_-Os_-fomit-frame-pointer`	20161024	20161009
19208512	? ? ?	? ? ?	`ref`	`g++_-march=k8_-Os_-fomit-frame-pointer`	20161024	20161009
19210792	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20161024	20161009
19219072	? ? ?	? ? ?	`ref`	`g++_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20161024	20161009
19342024	? ? ?	? ? ?	`ref`	`g++_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20161024	20161009
46213272	? ? ?	? ? ?	`ref`	`g++`	20161024	20161009

Compiler output

Implementation: crypto_aead/paeq64/aesni
Compiler: clang++ -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.cpp: encrypt.cpp:166:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc0 = _mm_aesenc_si128(acc0, roundkey0);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:167:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc1 = _mm_aesenc_si128(acc1, roundkey1);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:168:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc2 = _mm_aesenc_si128(acc2, roundkey2);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:169:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc3 = _mm_aesenc_si128(acc3, roundkey3);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:171:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc4 = _mm_aesenc_si128(acc4, roundkey0);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:172:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc5 = _mm_aesenc_si128(acc5, roundkey1);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:173:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc6 = _mm_aesenc_si128(acc6, roundkey2);
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:174:11: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'DoubleFPermAsm' that is compiled without support for 'aes'
encrypt.cpp: acc7 = _mm_aesenc_si128(acc7, roundkey3);
encrypt.cpp: ^
encrypt.cpp: 8 errors generated.

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

Compiler	Implementations
clang++ -O3 -fomit-frame-pointer -Qunused-arguments	aesni
clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	aesni
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni
clang++ -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni
clang++ -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni
clang++ -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni

Compiler output

Implementation: crypto_aead/paeq64/aesni
Compiler: g++

Number of similar (compiler,implementation) pairs: 58, namely:

Compiler	Implementations
g++	aesni
g++ -O2 -fomit-frame-pointer	aesni
g++ -O3 -fomit-frame-pointer	aesni
g++ -O -fomit-frame-pointer	aesni
g++ -Os -fomit-frame-pointer	aesni
g++ -fno-schedule-insns -O2 -fomit-frame-pointer	aesni
g++ -fno-schedule-insns -O3 -fomit-frame-pointer	aesni
g++ -fno-schedule-insns -O -fomit-frame-pointer	aesni
g++ -fno-schedule-insns -Os -fomit-frame-pointer	aesni
g++ -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	aesni
g++ -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	aesni
g++ -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	aesni
g++ -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	aesni
g++ -m64 -O2 -fomit-frame-pointer	aesni
g++ -m64 -O3 -fomit-frame-pointer	aesni
g++ -m64 -O -fomit-frame-pointer	aesni
g++ -m64 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -O3 -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -O -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4 -O -fomit-frame-pointer	aesni
g++ -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=corei7 -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=corei7 -O -fomit-frame-pointer	aesni
g++ -m64 -march=corei7 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=k8 -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=k8 -O3 -fomit-frame-pointer	aesni
g++ -m64 -march=k8 -O -fomit-frame-pointer	aesni
g++ -m64 -march=k8 -Os -fomit-frame-pointer	aesni
g++ -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	aesni
g++ -m64 -march=native -mtune=native -O -fomit-frame-pointer	aesni
g++ -m64 -march=native -mtune=native -Os -fomit-frame-pointer	aesni
g++ -m64 -march=nocona -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=nocona -O3 -fomit-frame-pointer	aesni
g++ -m64 -march=nocona -O -fomit-frame-pointer	aesni
g++ -m64 -march=nocona -Os -fomit-frame-pointer	aesni
g++ -march=barcelona -O2 -fomit-frame-pointer	aesni
g++ -march=barcelona -O3 -fomit-frame-pointer	aesni
g++ -march=barcelona -O -fomit-frame-pointer	aesni
g++ -march=barcelona -Os -fomit-frame-pointer	aesni
g++ -march=k8 -O2 -fomit-frame-pointer	aesni
g++ -march=k8 -O3 -fomit-frame-pointer	aesni
g++ -march=k8 -O -fomit-frame-pointer	aesni
g++ -march=k8 -Os -fomit-frame-pointer	aesni
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	aesni
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	aesni
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	aesni
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	aesni
g++ -march=nocona -O2 -fomit-frame-pointer	aesni
g++ -march=nocona -O3 -fomit-frame-pointer	aesni
g++ -march=nocona -O -fomit-frame-pointer	aesni
g++ -march=nocona -Os -fomit-frame-pointer	aesni

Compiler output

Implementation: crypto_aead/paeq64/aesni
Compiler: g++ -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h: In function 'void DoubleFPermAsm(const __m128i*, const __m128i*, __m128i*, __m128i*)':
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:174:44: error: called from here
encrypt.cpp: acc7 = _mm_aesenc_si128(acc7, roundkey3);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:173:44: error: called from here
encrypt.cpp: acc6 = _mm_aesenc_si128(acc6, roundkey2);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:172:44: error: called from here
encrypt.cpp: acc5 = _mm_aesenc_si128(acc5, roundkey1);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ...
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h: In function 'void DoubleFPermAsm(const __m128i*, const __m128i*, __m128i*, __m128i*)':
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:174:44: error: called from here
encrypt.cpp: acc7 = _mm_aesenc_si128(acc7, roundkey3);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:173:44: error: called from here
encrypt.cpp: acc6 = _mm_aesenc_si128(acc6, roundkey2);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ^
encrypt.cpp: encrypt.cpp:172:44: error: called from here
encrypt.cpp: acc5 = _mm_aesenc_si128(acc5, roundkey1);
encrypt.cpp: ^
encrypt.cpp: In file included from encrypt.cpp:13:0:
encrypt.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '__m128i _mm_aesenc_si128(__m128i, __m128i)': target specific option mismatch
encrypt.cpp: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.cpp: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
g++ -m64 -march=barcelona -O2 -fomit-frame-pointer	aesni
g++ -m64 -march=barcelona -O3 -fomit-frame-pointer	aesni
g++ -m64 -march=barcelona -O -fomit-frame-pointer	aesni
g++ -m64 -march=barcelona -Os -fomit-frame-pointer	aesni