Implementation notes: amd64, hydra1, crypto_dh/surf2113

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_dh
Primitive: surf2113

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
3157666	`mpfq`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161024	20161009
3159872	`mpfq`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161024	20161009
3165186	`mpfq`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161024	20161009
3165780	`mpfq`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161024	20161009
3177053	`mpfq`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161024	20161009
3177803	`mpfq`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161024	20161009
3177921	`mpfq`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161024	20161009
3189326	`mpfq`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161024	20161009
3190094	`mpfq`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161024	20161009
3190362	`mpfq`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161024	20161009
3202538	`mpfq`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161024	20161009
3203043	`mpfq`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161024	20161009
3208665	`mpfq`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161024	20161009
3209227	`mpfq`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161024	20161009
3352443	`mpfq`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161024	20161009
3353394	`mpfq`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161024	20161009
3354226	`mpfq`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161024	20161009
3355104	`mpfq`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161024	20161009
3356284	`mpfq`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161024	20161009
3363882	`mpfq`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161024	20161009
3364431	`mpfq`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161024	20161009
3366404	`mpfq`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161024	20161009
3374906	`mpfq`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161024	20161009
3375130	`mpfq`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161024	20161009
3385109	`mpfq`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161024	20161009
3385799	`mpfq`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161024	20161009
3390578	`mpfq`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161024	20161009
3391374	`mpfq`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161024	20161009
3391841	`mpfq`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161024	20161009
3409926	`mpfq`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161024	20161009
3411087	`mpfq`	`gcc -m64 -O3 -fomit-frame-pointer`	20161024	20161009
3415165	`mpfq`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161024	20161009
3415281	`mpfq`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161024	20161009
3416067	`mpfq`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161024	20161009
3416214	`mpfq`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161024	20161009
3417472	`mpfq`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161024	20161009
3420118	`mpfq`	`gcc -O3 -fomit-frame-pointer`	20161024	20161009
3420866	`mpfq`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161024	20161009
3421507	`mpfq`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161024	20161009
3422006	`mpfq`	`gcc -O2 -fomit-frame-pointer`	20161024	20161009
3422453	`mpfq`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161024	20161009
3424415	`mpfq`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161024	20161009
3424604	`mpfq`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161024	20161009
3424667	`mpfq`	`gcc -m64 -O2 -fomit-frame-pointer`	20161024	20161009
3425398	`mpfq`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161024	20161009
3429752	`mpfq`	`gcc -march=k8 -O -fomit-frame-pointer`	20161024	20161009
3430957	`mpfq`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161024	20161009
3431434	`mpfq`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161024	20161009
3449469	`mpfq`	`gcc -m64 -O -fomit-frame-pointer`	20161024	20161009
3449759	`mpfq`	`gcc -O -fomit-frame-pointer`	20161024	20161009
3450718	`mpfq`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161024	20161009
3465120	`mpfq`	`gcc -march=nocona -O -fomit-frame-pointer`	20161024	20161009
3466096	`mpfq`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161024	20161009
3479152	`mpfq`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161024	20161009
3529150	`mpfq`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161024	20161009
3529830	`mpfq`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161024	20161009
3530652	`mpfq`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161024	20161009
3531627	`mpfq`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161024	20161009
3565664	`mpfq`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161024	20161009
3565834	`mpfq`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161024	20161009
3569578	`mpfq`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161024	20161009
3571833	`mpfq`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161024	20161009
3578635	`mpfq`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161024	20161009
3583251	`mpfq`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161024	20161009
3584475	`mpfq`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161024	20161009
3585013	`mpfq`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161024	20161009
3623528	`mpfq`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161024	20161009
3625048	`mpfq`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161024	20161009
3625145	`mpfq`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161024	20161009
3776730	`mpfq`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161024	20161009
3804213	`mpfq`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161024	20161009
3809248	`mpfq`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161024	20161009
3809309	`mpfq`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161024	20161009
3900458	`mpfq`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161024	20161009
3901066	`mpfq`	`gcc -Os -fomit-frame-pointer`	20161024	20161009
3903517	`mpfq`	`gcc -m64 -Os -fomit-frame-pointer`	20161024	20161009
3907217	`mpfq`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161024	20161009
3923301	`mpfq`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161024	20161009
3924861	`mpfq`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161024	20161009
3926918	`mpfq`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161024	20161009
3937993	`mpfq`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161024	20161009
3993024	`mpfq`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161024	20161009
3994030	`mpfq`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161024	20161009
17086203	`mpfq`	`gcc`	20161024	20161009
17087314	`mpfq`	`gcc -funroll-loops`	20161024	20161009
17098377	`mpfq`	`cc`	20161024	20161009

Test failure

Implementation: crypto_dh/surf2113/mpfq
Compiler: gcc -m64 -march=core2 -O3 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 10, namely:

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

Compiler output

Implementation: crypto_dh/surf2113/mpfq
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

Surf2_113.c: In file included from Surf2_113.c:11:
Surf2_113.c: In file included from ./field.h:1:
Surf2_113.c: In file included from ./mpfq_2_113.h:5:
Surf2_113.c: ./x86_64/mpfq_2_113.h:714:14: error: use of unknown builtin '__builtin_ia32_pslldqi128' [-Wimplicit-function-declaration]
Surf2_113.c: r.s = t0 ^ SHLD(t1, 64);
Surf2_113.c: ^
Surf2_113.c: ./x86_64/mpfq_2_113.h:571:25: note: expanded from macro 'SHLD'
Surf2_113.c: #define SHLD(x,r) (v2di)__builtin_ia32_pslldqi128 ((gcc43bugfix) (x),(r))
Surf2_113.c: ^
Surf2_113.c: ./x86_64/mpfq_2_113.h:714:14: error: invalid conversion between vector type 'v2di' (vector of 2 'uint64_t' values) and integer type 'int' of different size
Surf2_113.c: r.s = t0 ^ SHLD(t1, 64);
Surf2_113.c: ^~~~~~~~~~~~
Surf2_113.c: ./x86_64/mpfq_2_113.h:571:19: note: expanded from macro 'SHLD'
Surf2_113.c: #define SHLD(x,r) (v2di)__builtin_ia32_pslldqi128 ((gcc43bugfix) (x),(r))
Surf2_113.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Surf2_113.c: ./x86_64/mpfq_2_113.h:721:14: error: use of unknown builtin '__builtin_ia32_psrldqi128' [-Wimplicit-function-declaration]
Surf2_113.c: r.s = t2 ^ SHRD(t1, 64);
Surf2_113.c: ^
Surf2_113.c: ./x86_64/mpfq_2_113.h:572:25: note: expanded from macro 'SHRD'
Surf2_113.c: #define SHRD(x,r) (v2di)__builtin_ia32_psrldqi128 ((gcc43bugfix) (x),(r))
Surf2_113.c: ^
Surf2_113.c: ./x86_64/mpfq_2_113.h:721:14: error: invalid conversion between vector type 'v2di' (vector of 2 'uint64_t' values) and integer type 'int' of different size
Surf2_113.c: r.s = t2 ^ SHRD(t1, 64);
Surf2_113.c: ^~~~~~~~~~~~
Surf2_113.c: ./x86_64/mpfq_2_113.h:572:19: note: expanded from macro 'SHRD'
Surf2_113.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

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