Implementation notes: amd64, h4atom, crypto_hash/keccakc768

Computer: h4atom
Architecture: amd64
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: keccakc768
TimeImplementationCompilerBenchmark dateSUPERCOP version
43176opt64lcu24clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
44384opt64lcu6clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
46128opt64lcu24gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
47736opt64lcu6gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
47792opt64u6clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
50480opt64lcu6gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
50896opt64lcu24gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
50904opt64lcu24gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
51664opt64lcu6gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
51792opt64u6gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
51840simpleclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
52472inplacegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
53408simplegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
54360simplegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
55224inplaceclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
55504x86_64_asmgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
55552x86_64_asmgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
55592x86_64_asmgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
55856x86_64_asmgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
56536inplacegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
56808opt64u6gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
57840opt64u6gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
58936inplacegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
59088simplegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
65432opt64lcu24gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
67336opt64lcu6gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
69112sseu2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
74232sseu2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
74240sseu2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
76520sseu2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
78456simplegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
79696opt64u6gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
80928inplacegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
92648sseu2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
100104mmxu1gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
100944mmxu1clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
101720mmxu1gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
101808mmxu1gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
108288opt32bi-s2lcu4clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
114112mmxu1gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
115448simple32biclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
116800opt32bi-rvku2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
118440inplace32biclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
118968opt32bi-s2lcu4gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
121256opt32bi-rvku2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
122096simple32bigcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
122880opt32biT-s2lcu4clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
123640opt32bi-s2lcu4gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
128768opt32bi-s2lcu4gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
129480opt32biT-s2lcu4gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
134376inplace32bigcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
134792opt32bi-rvku2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
138664simple32bigcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
138816opt32bi-rvku2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
139304opt32biT-s2lcu4gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
139968opt32biT-s2lcu4gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
140408simple32bigcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
141976compactgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
145064inplace32bigcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
151824opt64lcu24shldgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
152576inplace32bigcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
155840opt64lcu24shldgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
155872opt64lcu24shldgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
157888opt64lcu24shldclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
160008x86_64_shldgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
160056x86_64_shldgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
160152x86_64_shldgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
160328x86_64_shldgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
164328opt32bi-s2lcu4gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
165672opt64lcu24shldgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
174304opt32biT-s2lcu4gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
191872simple32bigcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
191928inplace32bigcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
194496opt32bi-rvku2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
196704compactclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
271872compactgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
301320compactgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
338920compactgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
461944compact8gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
538744compact8gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
563224compact8clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
637672compact8gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
706176compact8gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806

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: error: '__builtin_ia32_vprotqi' needs target feature xop
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: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/xopintrin.h:250:12: note: expanded from macro '_mm_roti_epi64'
KeccakF-1600-opt64.c: (__m128i)__builtin_ia32_vprotqi((__v2di)(__m128i)(A), (N)); })
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: error: '__builtin_ia32_vprotqi' needs target feature xop
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: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
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:50:16: error: missing 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: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:52:18: error: missing 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:55:16: error: missing 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:58:12: error: missing 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:60:16: error: unknown token in expression
KeccakF-1600-x86-64-gas.s: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
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:50:16: error: missing 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: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:52:18: error: missing 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:55:16: error: missing 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:58:12: error: missing 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:60:16: error: unknown token in expression
KeccakF-1600-x86-64-shld-gas.s: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
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/5/include/x86intrin.h:41:0,
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/5/include/smmintrin.h:216:1: error: inlining failed in call to always_inline '_mm_blend_pd': target specific option mismatch
KeccakF-1600-opt64.c: _mm_blend_pd (__m128d __X, __m128d __Y, const int __M)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:97:43: error: called from here
KeccakF-1600-opt64.c: #define GET64LOHI(a, b) ((__m128i)_mm_blend_pd((__m128d)a, (__m128d)b, 2))
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:94:51: note: in definition of macro 'SWAP64'
KeccakF-1600-opt64.c: #define SWAP64(a) _mm_shuffle_epi32(a, 0x4E)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:98:40: note: in expansion of macro 'GET64LOHI'
KeccakF-1600-opt64.c: #define GET64HILO(a, b) SWAP64(GET64LOHI(b, a))
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-xop.macros:106:13: note: in expansion of macro 'GET64HILO'
KeccakF-1600-opt64.c: Bsosu = GET64HILO(Bsiso, Bsusa); \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-xop.macros:123:36: note: in expansion of macro 'thetaRhoPiChiIotaPrepareTheta'
KeccakF-1600-opt64.c: #define thetaRhoPiChiIota(i, A, E) thetaRhoPiChiIotaPrepareTheta(i, A, E)
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-unrolling.macros:40:5: note: in expansion of macro 'thetaRhoPiChiIota'
KeccakF-1600-opt64.c: thetaRhoPiChiIota(23, E, A) \
KeccakF-1600-opt64.c: ^
KeccakF-1600-opt64.c: KeccakF-1600-opt64.c:185:5: note: in expansion of macro 'rounds'
KeccakF-1600-opt64.c: ...

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