Implementation notes: amd64, utrecht, crypto_hash/keccak

Computer: utrecht
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: keccak

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
21447	`x86_64_asm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
21501	`x86_64_asm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
21510	`x86_64_asm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
21861	`x86_64_asm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
22104	`opt64lcu6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
24282	`x86_64_shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
24300	`x86_64_shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
24426	`x86_64_shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
24876	`x86_64_shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
25317	`opt64u6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
27351	`simple`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
27936	`inplace`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
32787	`opt64lcu24`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
33246	`sseu2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
33246	`sseu2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
34425	`sseu2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
34596	`sseu2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
35721	`inplace`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
36018	`inplace`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
37098	`opt64u6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
37197	`opt64u6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
37251	`simple`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
37953	`simple`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
38133	`simple`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
38340	`opt64lcu24shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
38772	`inplace`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
39843	`mmxu1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
39843	`opt64u6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
40572	`mmxu1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
40707	`mmxu1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
42021	`opt64lcu24`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
42183	`opt64lcu24`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
42588	`opt64lcu6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
42606	`opt64lcu6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
42768	`mmxu1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
43785	`opt64lcu24`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
45522	`opt64lcu24shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
45531	`opt64lcu24shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
46575	`opt64lcu6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
47223	`opt64lcu24shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
65682	`simple32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
67194	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
71397	`inplace32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
74412	`compact`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
74439	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
80523	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
82260	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
83709	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
87336	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
89829	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
91917	`simple32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
95103	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
96768	`opt32bi-rvku2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
97605	`simple32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
97848	`simple32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
112905	`inplace32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
114669	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
115272	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
118152	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
118998	`compact`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
119340	`compact`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731
120861	`inplace32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
123831	`compact`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
127431	`inplace32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
214839	`compact8`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160804	20160731
229635	`compact8`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160804	20160731
234657	`compact8`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160804	20160731
665208	`compact8`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160804	20160731

Compiler output

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

KeccakF-1600-opt64.c: KeccakF-1600-opt64.c: In function 'KeccakPermutationOnWords':
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: incompatible type for argument 2 of '_mm_xor_si128'
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/xmmintrin.h:1246:0,
KeccakF-1600-opt64.c: from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/x86intrin.h:34,
KeccakF-1600-opt64.c: from KeccakF-1600-opt64.c:74:
KeccakF-1600-opt64.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/emmintrin.h:1264:1: note: expected '__m128i' but argument is of type 'int'
KeccakF-1600-opt64.c: _mm_xor_si128 (__m128i __A, __m128i __B)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: incompatible type for argument 2 of '_mm_xor_si128'
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/xmmintrin.h:1246:0,
KeccakF-1600-opt64.c: from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/x86intrin.h:34,
KeccakF-1600-opt64.c: from KeccakF-1600-opt64.c:74:
KeccakF-1600-opt64.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/emmintrin.h:1264:1: note: expected '__m128i' but argument is of type 'int'
KeccakF-1600-opt64.c: _mm_xor_si128 (__m128i __A, __m128i __B)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: can't convert between vector values of different size
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: incompatible type for argument 2 of '_mm_xor_si128'
KeccakF-1600-opt64.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/xmmintrin.h:1246:0,
KeccakF-1600-opt64.c: from /usr/lib/gcc/x86_64-linux-gnu/4.8/include/x86intrin.h:34,
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