Implementation notes: amd64, skylake, crypto_hash/essence224

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: essence224

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
72166	`gcc`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161215	20161026
72316	`gcc`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161215	20161026
72422	`gcc`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161215	20161026
72670	`gcc`	`gcc -O3 -fomit-frame-pointer`	20161215	20161026
72700	`gcc`	`gcc -m64 -O3 -fomit-frame-pointer`	20161215	20161026
73214	`gcc`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
73334	`gcc`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
73378	`gcc`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161215	20161026
73674	`gcc`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
73980	`gcc`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
74008	`gcc`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
74042	`gcc`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
74072	`gcc`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
74114	`gcc`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161215	20161026
74166	`gcc`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
74216	`gcc`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
74264	`gcc`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
74278	`gcc`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
74378	`gcc`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
74416	`gcc`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161215	20161026
74516	`gcc`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161215	20161026
74680	`gcc`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
74728	`gcc`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161215	20161026
74792	`gcc`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
74814	`gcc`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
74848	`gcc`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
74958	`gcc`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
75210	`gcc`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161215	20161026
75388	`gcc`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
75414	`gcc`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161215	20161026
75464	`gcc`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161215	20161026
75486	`gcc`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
75544	`gcc`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161215	20161026
75734	`gcc`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161215	20161026
75950	`gcc`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
75958	`gcc`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
75998	`gcc`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
76022	`gcc`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
76324	`gcc`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
76504	`gcc`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
76848	`gcc`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
76998	`gcc`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
78236	`gcc`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
78370	`gcc`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
78530	`gcc`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
78940	`gcc`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
79386	`gcc`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161215	20161026
79540	`gcc`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161215	20161026
79676	`gcc`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161215	20161026
79946	`gcc`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161215	20161026
80388	`gcc`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161215	20161026
80426	`gcc`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
80718	`gcc`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161215	20161026
80996	`gcc`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
81866	`gcc`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161215	20161026
81932	`gcc`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161215	20161026
81982	`gcc`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
82114	`gcc`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161215	20161026
82224	`gcc`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
82350	`gcc`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
86030	`gcc`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161215	20161026
86930	`gcc`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161215	20161026
86992	`gcc`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161215	20161026
87800	`gcc`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
87828	`gcc`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
90126	`gcc`	`gcc -m64 -Os -fomit-frame-pointer`	20161215	20161026
90150	`gcc`	`gcc -Os -fomit-frame-pointer`	20161215	20161026
90270	`gcc`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
90282	`gcc`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
90514	`gcc`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
91102	`gcc`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161215	20161026
91170	`gcc`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161215	20161026
91314	`gcc`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161215	20161026
91314	`gcc`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
91348	`gcc`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161215	20161026
91378	`gcc`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161215	20161026
91400	`gcc`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
91474	`gcc`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161215	20161026
91500	`gcc`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
91534	`gcc`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161215	20161026
91626	`gcc`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
91644	`gcc`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161215	20161026
91756	`gcc`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
91844	`gcc`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161215	20161026
92140	`gcc`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
92140	`gcc`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161215	20161026
92206	`gcc`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161215	20161026
92282	`gcc`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161215	20161026
92328	`gcc`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
92350	`gcc`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161215	20161026
92354	`gcc`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
92524	`gcc`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161215	20161026
92606	`gcc`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161215	20161026
92640	`gcc`	`gcc -m64 -O2 -fomit-frame-pointer`	20161215	20161026
92702	`gcc`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
92818	`gcc`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
92972	`gcc`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161215	20161026
93046	`gcc`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
93134	`gcc`	`gcc -march=nocona -O -fomit-frame-pointer`	20161215	20161026
93154	`gcc`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
93198	`gcc`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161215	20161026
93234	`gcc`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161215	20161026
93256	`gcc`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
93320	`gcc`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
93352	`gcc`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161215	20161026
93436	`gcc`	`gcc -O2 -fomit-frame-pointer`	20161215	20161026
93492	`gcc`	`gcc -march=k8 -O -fomit-frame-pointer`	20161215	20161026
93680	`gcc`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
93692	`gcc`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
94164	`gcc`	`gcc -m64 -O -fomit-frame-pointer`	20161215	20161026
94374	`gcc`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
94476	`gcc`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161215	20161026
94870	`gcc`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
95328	`gcc`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
95456	`gcc`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
95792	`gcc`	`gcc -O -fomit-frame-pointer`	20161215	20161026
97808	`gcc`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161215	20161026
97934	`gcc`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
321402	`gcc`	`gcc -funroll-loops`	20161215	20161026
321694	`gcc`	`gcc`	20161215	20161026
322874	`gcc`	`cc`	20161215	20161026

Compiler output

Implementation: crypto_hash/essence224/gcc
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

essence_L_tables.c: In file included from essence_L_tables.c:12:
essence_L_tables.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
essence_L_tables.c: #ifndef _ESSENCE_API_H_
essence_L_tables.c: ^~~~~~~~~~~~~~~
essence_L_tables.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
essence_L_tables.c: #define _ESSENCE_H_API_
essence_L_tables.c: ^~~~~~~~~~~~~~~
essence_L_tables.c: _ESSENCE_API_H_
essence_L_tables.c: 1 warning generated.
essence_api.c: In file included from essence_api.c:11:
essence_api.c: In file included from ./essence.h:11:
essence_api.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
essence_api.c: #ifndef _ESSENCE_API_H_
essence_api.c: ^~~~~~~~~~~~~~~
essence_api.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
essence_api.c: #define _ESSENCE_H_API_
essence_api.c: ^~~~~~~~~~~~~~~
essence_api.c: _ESSENCE_API_H_
essence_api.c: 1 warning generated.
essence_compress_256.c: In file included from essence_compress_256.c:11:
essence_compress_256.c: In file included from ./essence.h:11:
essence_compress_256.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
essence_compress_256.c: #ifndef _ESSENCE_API_H_
essence_compress_256.c: ^~~~~~~~~~~~~~~
essence_compress_256.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
essence_compress_256.c: #define _ESSENCE_H_API_
essence_compress_256.c: ^~~~~~~~~~~~~~~
essence_compress_256.c: _ESSENCE_API_H_
essence_compress_256.c: 1 warning generated.
essence_compress_256_dual.c: In file included from essence_compress_256_dual.c:11:
essence_compress_256_dual.c: In file included from ./essence.h:11:
essence_compress_256_dual.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
essence_compress_256_dual.c: #ifndef _ESSENCE_API_H_
essence_compress_256_dual.c: ^~~~~~~~~~~~~~~
essence_compress_256_dual.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
essence_compress_256_dual.c: #define _ESSENCE_H_API_
essence_compress_256_dual.c: ^~~~~~~~~~~~~~~
essence_compress_256_dual.c: _ESSENCE_API_H_
essence_compress_256_dual.c: 1 warning generated.
essence_compress_512.c: In file included from essence_compress_512.c:10:
essence_compress_512.c: In file included from ./essence.h:11:
essence_compress_512.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
essence_compress_512.c: #ifndef _ESSENCE_API_H_
essence_compress_512.c: ^~~~~~~~~~~~~~~
essence_compress_512.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
essence_compress_512.c: #define _ESSENCE_H_API_
essence_compress_512.c: ^~~~~~~~~~~~~~~
essence_compress_512.c: _ESSENCE_API_H_
essence_compress_512.c: 1 warning generated.
hash.c: In file included from hash.c:2:
hash.c: ./essence_api.h:13:9: warning: '_ESSENCE_API_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard]
hash.c: #ifndef _ESSENCE_API_H_
hash.c: ^~~~~~~~~~~~~~~
hash.c: ./essence_api.h:14:9: note: '_ESSENCE_H_API_' is defined here; did you mean '_ESSENCE_API_H_'?
hash.c: #define _ESSENCE_H_API_
hash.c: ^~~~~~~~~~~~~~~
hash.c: _ESSENCE_API_H_
hash.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	gcc
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	gcc
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	gcc
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	gcc
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	gcc
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	gcc
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	gcc
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	gcc
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	gcc
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	gcc