Implementation notes: amd64, glyme, crypto_dh/k277mon

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_dh
Primitive: k277mon

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1287380	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
1290008	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
1309436	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
1313968	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
1342472	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
1344040	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
1352560	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
1353336	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
1399084	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
1401308	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: cc

dh.c: In file included from dh.c:6:
dh.c: ./ffa.h:123:12: error: '__builtin_ia32_palignr128' needs target feature ssse3
dh.c: a_01 = _mm_alignr_epi8(a_02, a_01, 8);
dh.c: ^
dh.c: /usr/bin/../lib/clang/3.8.0/include/tmmintrin.h:69:12: note: expanded from macro '_mm_alignr_epi8'
dh.c: (__m128i)__builtin_ia32_palignr128((__v16qi)(__m128i)(a), \
dh.c: ^
dh.c: In file included from dh.c:6:
dh.c: ./ffa.h:132:5: error: '__builtin_ia32_pclmulqdq128' needs target feature pclmul
dh.c: FFA_RED_277_STP(a,P,m,t_00,mul);
dh.c: ^
dh.c: ./ffa.h:110:5: note: expanded from macro 'FFA_RED_277_STP'
dh.c: ffa_red_277_stp(A##_00,A##_01,A##_02,P##_00,P##_01,P##_02,\
dh.c: ^
dh.c: ./ffa.h:90:12: note: expanded from macro 'ffa_red_277_stp'
dh.c: m_00 = _mm_clmulepi64_si128(mul, P_00, 0x00);\
dh.c: ^
dh.c: /usr/bin/../lib/clang/3.8.0/include/__wmmintrin_pclmul.h:27:13: note: expanded from macro '_mm_clmulepi64_si128'
dh.c: ((__m128i)__builtin_ia32_pclmulqdq128((__v2di)(__m128i)(__X), \
dh.c: ^
dh.c: In file included from dh.c:6:
dh.c: ./ffa.h:132:5: error: '__builtin_ia32_pclmulqdq128' needs target feature pclmul
dh.c: ./ffa.h:110:5: note: expanded from macro 'FFA_RED_277_STP'
dh.c: ffa_red_277_stp(A##_00,A##_01,A##_02,P##_00,P##_01,P##_02,\
dh.c: ^
dh.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
cc	ref
clang -O3 -fomit-frame-pointer -Qunused-arguments	ref
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: gcc

dh.c: In file included from dh.c:6:0:
dh.c: ffa.h: In function 'ffa_red_277':
dh.c: ffa.h:123:10: error: '__builtin_ia32_palignr128' needs isa option -m32 -mssse3
dh.c: a_01 = _mm_alignr_epi8(a_02, a_01, 8);
dh.c: ^
dh.c: ffa.h:90:10: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
dh.c: m_00 = _mm_clmulepi64_si128(mul, P_00, 0x00);\
dh.c: ^
dh.c: ffa.h:110:5: note: in expansion of macro 'ffa_red_277_stp'
dh.c: ffa_red_277_stp(A##_00,A##_01,A##_02,P##_00,P##_01,P##_02,\
dh.c: ^~~~~~~~~~~~~~~
dh.c: ffa.h:132:5: note: in expansion of macro 'FFA_RED_277_STP'
dh.c: FFA_RED_277_STP(a,P,m,t_00,mul);
dh.c: ^~~~~~~~~~~~~~~
dh.c: ffa.h:91:10: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
dh.c: m_01 = _mm_clmulepi64_si128(mul, P_00, 0x10);\
dh.c: ^
dh.c: ffa.h:110:5: note: in expansion of macro 'ffa_red_277_stp'
dh.c: ffa_red_277_stp(A##_00,A##_01,A##_02,P##_00,P##_01,P##_02,\
dh.c: ^~~~~~~~~~~~~~~
dh.c: ffa.h:132:5: note: in expansion of macro 'FFA_RED_277_STP'
dh.c: FFA_RED_277_STP(a,P,m,t_00,mul);
dh.c: ^~~~~~~~~~~~~~~
dh.c: ffa.h:92:10: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
dh.c: m_02 = _mm_clmulepi64_si128(mul, P_01, 0x00);\
dh.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc	ref
gcc -funroll-loops	ref

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 67, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	ref
gcc -O3 -fomit-frame-pointer	ref
gcc -O -fomit-frame-pointer	ref
gcc -Os -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -O -fomit-frame-pointer	ref
gcc -funroll-loops -Os -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	ref
gcc -m64 -O2 -fomit-frame-pointer	ref
gcc -m64 -O3 -fomit-frame-pointer	ref
gcc -m64 -O -fomit-frame-pointer	ref
gcc -m64 -Os -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -march=barcelona -O -fomit-frame-pointer	ref
gcc -march=barcelona -Os -fomit-frame-pointer	ref
gcc -march=k8 -O2 -fomit-frame-pointer	ref
gcc -march=k8 -O3 -fomit-frame-pointer	ref
gcc -march=k8 -O -fomit-frame-pointer	ref
gcc -march=k8 -Os -fomit-frame-pointer	ref
gcc -march=nocona -O2 -fomit-frame-pointer	ref
gcc -march=nocona -O3 -fomit-frame-pointer	ref
gcc -march=nocona -O -fomit-frame-pointer	ref
gcc -march=nocona -Os -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer

dh.c: dh.c:3:17: fatal error: api.h: No such file or directory
dh.c: compilation terminated.
dh.c: from dh.c:2:
dh.c: ffa.h: In function 'ffa_red_277':
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:148:13: note: called from here
dh.c: *c_02 = _mm_alignr_epi8(a_02, a_01, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:147:13: note: called from here
dh.c: *c_01 = _mm_alignr_epi8(a_01, a_00, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: ...

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

Compiler	Implementations
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: ffa.h: In function 'ffa_red_277':
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:148:13: note: called from here
dh.c: *c_02 = _mm_alignr_epi8(a_02, a_01, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:147:13: note: called from here
dh.c: *c_01 = _mm_alignr_epi8(a_01, a_00, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: ...
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: ffa.h: In function 'ffa_red_277':
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:148:13: note: called from here
dh.c: *c_02 = _mm_alignr_epi8(a_02, a_01, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:147:13: note: called from here
dh.c: *c_01 = _mm_alignr_epi8(a_01, a_00, 8);
dh.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:39:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
dh.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -O -fomit-frame-pointer	ref
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_dh/k277mon/ref
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:45:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: ffa.h: In function 'ffa_red_277':
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
dh.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
dh.c: ^~~~~~~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:94:10: note: called from here
dh.c: m_04 = _mm_clmulepi64_si128(mul, P_02, 0x00);\
dh.c: ^
dh.c: ffa.h:110:5: note: in expansion of macro 'ffa_red_277_stp'
dh.c: ffa_red_277_stp(A##_00,A##_01,A##_02,P##_00,P##_01,P##_02,\
dh.c: ^~~~~~~~~~~~~~~
dh.c: ffa.h:142:5: note: in expansion of macro 'FFA_RED_277_STP'
dh.c: FFA_RED_277_STP(a,P,m,t_00,mul);
dh.c: ^~~~~~~~~~~~~~~
dh.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/x86intrin.h:45:0,
dh.c: from lib.h:2,
dh.c: from dh.c:2:
dh.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
dh.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
dh.c: ^~~~~~~~~~~~~~~~~~~~
dh.c: In file included from dh.c:6:0:
dh.c: ffa.h:93:10: note: called from here
dh.c: ...

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	ref