Implementation notes: amd64, waldorf, crypto_hash/keccakc768

Computer: waldorf
Architecture: amd64
CPU ID: GenuineIntel-000106e5-bfebfbff
SUPERCOP version: 20160715
Operation: crypto_hash
Primitive: keccakc768

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
53884	`opt64lcu6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
53968	`opt64u6`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
55344	`opt64lcu24shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
55412	`opt64lcu6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
56008	`opt64lcu24shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
56280	`opt64lcu6`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
56424	`inplace`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
56484	`opt64lcu24`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
57680	`x86_64_asm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
57984	`x86_64_asm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
58140	`x86_64_asm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
58208	`inplace`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
58332	`opt64lcu24`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
58828	`x86_64_shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
59104	`x86_64_shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
59136	`opt64lcu6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
59372	`x86_64_asm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
59460	`x86_64_shld`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
59608	`inplace`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
59608	`simple`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
59632	`opt64u6`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
59700	`x86_64_shld`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
59868	`simple`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
60108	`opt64lcu24`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
60196	`opt64lcu24`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
60552	`opt64lcu24shld`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
60748	`opt64lcu6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
60992	`inplace`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
61492	`opt64lcu24`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
61616	`sseu2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
61884	`sseu2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
62344	`opt64lcu24shld`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
62348	`opt64u6`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
62600	`inplace`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
63312	`sseu2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
63328	`opt64lcu24shld`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
64228	`sseu2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
65108	`simple`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
65404	`simple`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
65504	`opt64u6`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
65584	`opt64u6`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
66132	`simple`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
72832	`mmxu1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
75288	`mmxu1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
79168	`sseu2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
79616	`mmxu1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
84164	`mmxu1`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
84952	`mmxu1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
113812	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
117980	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
125876	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
126188	`opt32bi-rvku2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
126324	`inplace32bi`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
127508	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
129336	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
129828	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
131604	`inplace32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
131920	`compact`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
131980	`opt32bi-s2lcu4`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
132360	`simple32bi`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
132828	`opt32biT-s2lcu4`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
135296	`opt32biT-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
136268	`opt32bi-s2lcu4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
137468	`simple32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
137604	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
143464	`simple32bi`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
144660	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
145192	`inplace32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
145788	`opt32bi-rvku2`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
148148	`simple32bi`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
149516	`opt32bi-rvku2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
152720	`inplace32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
156048	`compact`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
156056	`simple32bi`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
156260	`inplace32bi`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
243940	`compact`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715
258872	`compact`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
260200	`compact`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
516480	`compact8`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160718	20160715
570700	`compact8`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160718	20160715
582616	`compact8`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160718	20160715
601532	`compact8`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160718	20160715
1084788	`compact8`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160718	20160715

Compiler output

Implementation: crypto_hash/keccakc768/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/keccakc768/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/keccakc768/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/keccakc768/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