Implementation notes: amd64, h4atom, crypto_hash/keccakc512

Computer: h4atom
Architecture: amd64
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: keccakc512
TimeImplementationCompilerBenchmark dateSUPERCOP version
34960opt64lcu6clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
35016opt64lcu24clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
37544opt64lcu24gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
38648opt64u6clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
39120opt64lcu6gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
40872opt64lcu6gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
41016opt64lcu24gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
41280opt64lcu24gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
41568opt64u6gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
41632opt64lcu6gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
42032simpleclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
42464inplacegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
42608sphlibclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
43208simplegcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
43952sphlib-smallclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
43984simplegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
44800inplaceclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
44984x86_64_asmgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
45024x86_64_asmgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
45096x86_64_asmgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
45368x86_64_asmgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
45736inplacegcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
45752opt64u6gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
46544opt64u6gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
47376inplacegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
47480simplegcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
51208sphlibgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
51976sphlibgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
52352opt64lcu24gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
53312sphlibgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
54144opt64lcu6gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
55128sphlib-smallgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
56808sphlib-smallgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
58080sseu2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
58088sseu2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
58336sphlib-smallgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
58528sseu2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
62328sseu2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
63464simplegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
63976opt64u6gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
65304inplacegcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
68168sphlibgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
71904sphlib-smallgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
74608sseu2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
79376mmxu1clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
80512mmxu1gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
81624mmxu1gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
81632mmxu1gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
88128opt32bi-s2lcu4clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
91512mmxu1gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
94152simple32biclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
95272opt32bi-rvku2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
96552inplace32biclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
98768opt32bi-s2lcu4gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
99904opt32bi-s2lcu4gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
100432opt32bi-rvku2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
100616simple32bigcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
104096opt32biT-s2lcu4clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
106688opt32bi-s2lcu4gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
108960opt32biT-s2lcu4gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
110440inplace32bigcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
110752opt32bi-rvku2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
112000simple32bigcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
112120opt32bi-rvku2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
113816compactgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
115304simple32bigcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
116680opt32biT-s2lcu4gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
117024opt32biT-s2lcu4gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
117488inplace32bigcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
122080opt64lcu24shldgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
124632opt64lcu24shldgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
124760opt64lcu24shldgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
125032inplace32bigcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
126704opt64lcu24shldclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
128568x86_64_shldgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
128592x86_64_shldgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
128688x86_64_shldgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
128912x86_64_shldgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
132952opt64lcu24shldgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
134064opt32bi-s2lcu4gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
144736opt32biT-s2lcu4gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
156200simple32bigcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
156600inplace32bigcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
157944compactclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
158072opt32bi-rvku2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
217936compactgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
241512compactgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
271744compactgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806
370152compact8gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2016081220160806
431024compact8gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2016081220160806
450696compact8clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2016081220160806
510496compact8gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2016081220160806
565424compact8gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2016081220160806

Checksum failure

Implementation: crypto_hash/keccakc512/gil/singlefile
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments
ebbed3a47232047ad399cb77b6324d6c902f4715de871750545b1a3b12046ebe
Number of similar (compiler,implementation) pairs: 10, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments gil/singlefile gil/singlefile_unrolled
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv gil/singlefile gil/singlefile_unrolled
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv gil/singlefile gil/singlefile_unrolled
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv gil/singlefile gil/singlefile_unrolled
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv gil/singlefile gil/singlefile_unrolled

Compiler output

Implementation: crypto_hash/keccakc512/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/keccakc512/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/keccakc512/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/keccakc512/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