Implementation notes: amd64, waldorf, crypto_hash/keccakc1024

Computer: waldorf
Architecture: amd64
CPU ID: GenuineIntel-000106e5-bfebfbff
SUPERCOP version: 20160715
Operation: crypto_hash
Primitive: keccakc1024

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
79132	`x86_64_asm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
79940	`opt64lcu6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
80200	`opt64lcu6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
80476	`x86_64_shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
80560	`opt64lcu24shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
80664	`opt64lcu6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
81636	`opt64lcu6`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
82128	`opt64lcu24`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
83016	`x86_64_asm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
83132	`x86_64_shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
84752	`opt64u6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
84908	`opt64lcu24`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
85092	`simple`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
85384	`x86_64_shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
85420	`opt64lcu24`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
85544	`simple`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
85676	`sphlib`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
85980	`opt64lcu24shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
86188	`opt64u6`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
86632	`opt64lcu6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
87012	`opt64lcu24shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
87020	`x86_64_asm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
87144	`x86_64_asm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
87272	`sseu2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
87500	`x86_64_shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
87564	`opt64u6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
88064	`opt64lcu24shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
89492	`simple`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
89724	`inplace`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
89980	`sseu2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
90568	`opt64lcu24shld`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
90612	`inplace`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
91036	`opt64lcu24`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
91168	`sphlib`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
91400	`sphlib`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
91516	`inplace`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
91820	`opt64lcu24`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
92876	`sphlib-small`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
93216	`sseu2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
93672	`simple`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
94040	`opt64u6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
94856	`inplace`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
94944	`opt64u6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
95040	`sphlib-small`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
95532	`simple`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
96808	`sseu2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
97308	`sphlib`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
100204	`inplace`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
105756	`sphlib-small`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
107840	`sphlib-small`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
109388	`sphlib-small`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
112848	`mmxu1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
113448	`sseu2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
117560	`mmxu1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
119012	`mmxu1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
120800	`mmxu1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
128056	`mmxu1`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
159740	`sphlib`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
165728	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
177272	`simple32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
179844	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
180688	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
181164	`inplace32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
182024	`simple32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
182124	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
184292	`simple32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
186320	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
186384	`inplace32bi`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
186736	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
187196	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
187544	`opt32bi-s2lcu4`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
191060	`opt32bi-rvku2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
191360	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
194644	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
195844	`compact`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
197768	`opt32biT-s2lcu4`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
199220	`simple32bi`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
199844	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
205012	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
207560	`inplace32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
212908	`inplace32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
217416	`opt32bi-rvku2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
221772	`simple32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
224752	`inplace32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
232892	`compact`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
362040	`compact`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
373460	`compact`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
378108	`compact`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
735052	`compact8`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
741640	`compact8`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
793464	`compact8`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
842200	`compact8`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
1750320	`compact8`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715

Compiler output

Implementation: crypto_hash/keccakc1024/xopu24
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: warning: implicit declaration of function '_mm_roti_epi64' is invalid in C99 [-Wimplicit-function-declaration]
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
KeccakF-1600-opt64.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: ./KeccakF-1600-xop.macros:53:5: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
KeccakF-1600-opt64.c: computeD \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: ./KeccakF-1600-xop.macros:40:23: note: expanded from macro 'computeD'
KeccakF-1600-opt64.c: Dei = XOR128(Cae, ROL6464same(Cio, 1)); \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:102:33: note: expanded from macro 'ROL6464same'
KeccakF-1600-opt64.c: #define ROL6464same(a, o) _mm_roti_epi64(a, o)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:90:50: note: expanded from macro 'XOR128'
KeccakF-1600-opt64.c: #define XOR128(a, b) _mm_xor_si128(a, b)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: passing 'int' to parameter of incompatible type '__m128i' (vector of 2 'long long' values)
KeccakF-1600-opt64.c: rounds
KeccakF-1600-opt64.c: ^~~~~~
KeccakF-1600-opt64.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
KeccakF-1600-opt64.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
KeccakF-1600-opt64.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
KeccakF-1600-opt64.c: ./KeccakF-1600-xop.macros:53:5: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
KeccakF-1600-opt64.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	xopu24

Compiler output

Implementation: crypto_hash/keccakc1024/x86_64_asm
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:50:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ apState, %rdi
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:51:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ apInput, %rsi
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:52:18: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ aNbrWords, %rdx
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:55:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ xpState, %r9
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:58:12: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ rT1, %rax
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:59:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ rpState, %rdi
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:60:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ rpStack, %rsp
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:62:12: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: .equ rDa, %rbx
KeccakF-1600-x86-64-gas.s: ^
KeccakF-1600-x86-64-gas.s: KeccakF-1600-x86-64-gas.s:63:12: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	x86_64_asm

Compiler output

Implementation: crypto_hash/keccakc1024/x86_64_shld
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:50:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ apState, %rdi
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:51:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ apInput, %rsi
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:52:18: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ aNbrWords, %rdx
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:55:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ xpState, %r9
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:58:12: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ rT1, %rax
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:59:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ rpState, %rdi
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:60:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ rpStack, %rsp
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:62:12: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: .equ rDa, %rbx
KeccakF-1600-x86-64-shld-gas.s: ^
KeccakF-1600-x86-64-shld-gas.s: KeccakF-1600-x86-64-shld-gas.s:63:12: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	x86_64_shld

Compiler output

Implementation: crypto_hash/keccakc1024/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