Implementation notes: amd64, slide, crypto_hash/keccakc448

Computer: slide
Architecture: amd64
CPU ID: GenuineIntel-00040651-bfebfbff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: keccakc448

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
13556	`inplace`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
13652	`inplace`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
13704	`x86_64_shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
13740	`x86_64_shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
13780	`inplace`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
13840	`simple`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
13932	`simple`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
14000	`opt64u6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
14044	`opt64u6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
14060	`simple`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
14076	`simple`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
14144	`opt64u6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
14176	`opt64u6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
14352	`inplace`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
15000	`opt64lcu24`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
15016	`opt64lcu24shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
15320	`opt64lcu6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
15412	`x86_64_shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
15524	`x86_64_shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
15528	`opt64lcu6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
15568	`opt64lcu24`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
15600	`opt64lcu6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
15620	`opt64lcu24`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
15688	`opt64lcu24`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
15792	`opt64lcu6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
16192	`opt64lcu24shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
16192	`opt64lcu24shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
16220	`opt64lcu24shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
16420	`x86_64_asm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
16428	`x86_64_asm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
16568	`x86_64_asm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
16680	`x86_64_asm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
17550	`sseu2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
19760	`sseu2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
19804	`sseu2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
19848	`sseu2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
29176	`mmxu1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
31348	`mmxu1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
32064	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
32208	`mmxu1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
32384	`mmxu1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
34128	`opt32bi-rvku2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
34612	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
34624	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
35955	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
36964	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
37744	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
38064	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
38284	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
39464	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
40060	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
40692	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
42104	`compact`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
67784	`compact`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
71392	`compact`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
78748	`compact`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
145724	`compact8`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
149984	`compact8`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
157052	`compact8`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
213152	`compact8`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806

Compiler output

Implementation: crypto_hash/keccakc448/inplace32bi
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

Keccak-inplace32BI.c: Keccak-inplace32BI.c: In function 'crypto_hash_keccakc448_inplace32bi':
Keccak-inplace32BI.c: Keccak-inplace32BI.c:73:6: error: #error "The output size must be a multiple of the lane size in this simple implementation."
Keccak-inplace32BI.c: #error "The output size must be a multiple of the lane size in this simple implementation."
Keccak-inplace32BI.c: ^

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	inplace32bi
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	inplace32bi
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	inplace32bi
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	inplace32bi

Compiler output

Implementation: crypto_hash/keccakc448/simple32bi
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

Keccak-simple32BI.c: Keccak-simple32BI.c: In function 'crypto_hash_keccakc448_simple32bi':
Keccak-simple32BI.c: Keccak-simple32BI.c:73:6: error: #error "The output size must be a multiple of the lane size in this simple implementation."
Keccak-simple32BI.c: #error "The output size must be a multiple of the lane size in this simple implementation."
Keccak-simple32BI.c: ^

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	simple32bi
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	simple32bi
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	simple32bi
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	simple32bi

Compiler output

Implementation: crypto_hash/keccakc448/xopu24
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

KeccakF-1600-opt64.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.9/include/x86intrin.h:52:0,
KeccakF-1600-opt64.c: from KeccakF-1600-opt64.c:74:
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c: In function 'KeccakPermutationOnWords':
KeccakF-1600-opt64.c: /usr/lib/gcc/x86_64-linux-gnu/4.9/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
KeccakF-1600-opt64.c: _mm_roti_epi64(__m128i __A, const int __B)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:90:33: error: called from here
KeccakF-1600-opt64.c: #define XOR128(a, b) _mm_xor_si128(a, b)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-xop.macros:40:11: note: in expansion of macro 'XOR128'
KeccakF-1600-opt64.c: Dei = XOR128(Cae, ROL6464same(Cio, 1)); \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-xop.macros:53:5: note: in expansion of macro 'computeD'
KeccakF-1600-opt64.c: computeD \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-unrolling.macros:17:5: note: in expansion of macro 'thetaRhoPiChiIotaPrepareTheta'
KeccakF-1600-opt64.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: note: in expansion of macro 'rounds'
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.9/include/x86intrin.h:52:0,
KeccakF-1600-opt64.c: from KeccakF-1600-opt64.c:74:
KeccakF-1600-opt64.c: /usr/lib/gcc/x86_64-linux-gnu/4.9/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
KeccakF-1600-opt64.c: _mm_roti_epi64(__m128i __A, const int __B)
KeccakF-1600-opt64.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	xopu24
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	xopu24
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	xopu24
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	xopu24