Implementation notes: amd64, bolero, crypto_dh/surf2113

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_dh
Primitive: surf2113
TimeImplementationCompilerBenchmark dateSUPERCOP version
2288068mpfqgcc -march=barcelona -O -fomit-frame-pointer2017110620171020
2288384mpfqgcc -m64 -O -fomit-frame-pointer2017110620171020
2288940mpfqgcc -O -fomit-frame-pointer2017110620171020
2290908mpfqgcc -m64 -march=barcelona -O -fomit-frame-pointer2017110620171020
2291440mpfqgcc -fno-schedule-insns -O -fomit-frame-pointer2017110620171020
2292884mpfqgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017110620171020
2294076mpfqgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2017110620171020
2294804mpfqgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017110620171020
2295044mpfqgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2017110620171020
2298208mpfqgcc -m64 -march=core2 -O -fomit-frame-pointer2017110620171020
2298456mpfqgcc -march=k8 -O -fomit-frame-pointer2017110620171020
2299136mpfqgcc -m64 -march=k8 -O -fomit-frame-pointer2017110620171020
2300304mpfqgcc -funroll-loops -O -fomit-frame-pointer2017110620171020
2300524mpfqgcc -m64 -march=nocona -O -fomit-frame-pointer2017110620171020
2301040mpfqgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2017110620171020
2301256mpfqgcc -march=nocona -O -fomit-frame-pointer2017110620171020
2302232mpfqgcc -funroll-loops -m64 -O -fomit-frame-pointer2017110620171020
2328012mpfqgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2017110620171020
2328380mpfqgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2017110620171020
2328680mpfqgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2017110620171020
2330228mpfqgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2017110620171020
2356624mpfqgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2017110620171020
2357116mpfqgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2017110620171020
2382088mpfqgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2017110620171020
2384336mpfqgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2017110620171020
2384580mpfqgcc -funroll-loops -Os -fomit-frame-pointer2017110620171020
2385372mpfqgcc -funroll-loops -m64 -Os -fomit-frame-pointer2017110620171020
2385836mpfqgcc -funroll-loops -O3 -fomit-frame-pointer2017110620171020
2386396mpfqgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2017110620171020
2386540mpfqgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2017110620171020
2387572mpfqgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2017110620171020
2388684mpfqgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2017110620171020
2390768mpfqgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2017110620171020
2398160mpfqgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2017110620171020
2400052mpfqgcc -march=barcelona -O3 -fomit-frame-pointer2017110620171020
2404436mpfqgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2017110620171020
2405084mpfqgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2017110620171020
2405432mpfqgcc -march=k8 -O3 -fomit-frame-pointer2017110620171020
2405620mpfqgcc -m64 -march=k8 -O3 -fomit-frame-pointer2017110620171020
2406028mpfqgcc -m64 -march=core2 -O3 -fomit-frame-pointer2017110620171020
2416984mpfqgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2017110620171020
2419468mpfqgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2017110620171020
2422844mpfqgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017110620171020
2423244mpfqgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2017110620171020
2423604mpfqgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2017110620171020
2432460mpfqgcc -march=barcelona -O2 -fomit-frame-pointer2017110620171020
2433076mpfqgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2017110620171020
2433436mpfqgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017110620171020
2434444mpfqgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017110620171020
2435096mpfqgcc -O2 -fomit-frame-pointer2017110620171020
2435168mpfqgcc -m64 -O2 -fomit-frame-pointer2017110620171020
2435676mpfqgcc -fno-schedule-insns -O2 -fomit-frame-pointer2017110620171020
2435824mpfqgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017110620171020
2436936mpfqgcc -m64 -O3 -fomit-frame-pointer2017110620171020
2437068mpfqgcc -fno-schedule-insns -O3 -fomit-frame-pointer2017110620171020
2437100mpfqgcc -O3 -fomit-frame-pointer2017110620171020
2437240mpfqgcc -m64 -march=core2 -O2 -fomit-frame-pointer2017110620171020
2438132mpfqgcc -m64 -march=barcelona -Os -fomit-frame-pointer2017110620171020
2440168mpfqgcc -march=k8 -O2 -fomit-frame-pointer2017110620171020
2440456mpfqgcc -m64 -march=k8 -O2 -fomit-frame-pointer2017110620171020
2442460mpfqgcc -march=barcelona -Os -fomit-frame-pointer2017110620171020
2446212mpfqgcc -funroll-loops -O2 -fomit-frame-pointer2017110620171020
2446344mpfqgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2017110620171020
2447908mpfqgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2017110620171020
2456616mpfqgcc -march=nocona -O2 -fomit-frame-pointer2017110620171020
2456792mpfqgcc -m64 -march=nocona -O2 -fomit-frame-pointer2017110620171020
2461772mpfqgcc -march=nocona -O3 -fomit-frame-pointer2017110620171020
2464440mpfqgcc -m64 -Os -fomit-frame-pointer2017110620171020
2464608mpfqgcc -fno-schedule-insns -Os -fomit-frame-pointer2017110620171020
2464664mpfqgcc -Os -fomit-frame-pointer2017110620171020
2464840mpfqgcc -m64 -march=nocona -O3 -fomit-frame-pointer2017110620171020
2465000mpfqgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2017110620171020
2466212mpfqgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2017110620171020
2466572mpfqgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2017110620171020
2467304mpfqgcc -march=k8 -Os -fomit-frame-pointer2017110620171020
2467732mpfqgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2017110620171020
2467872mpfqgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017110620171020
2468800mpfqgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2017110620171020
2470220mpfqgcc -m64 -march=k8 -Os -fomit-frame-pointer2017110620171020
2471984mpfqgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2017110620171020
2473992mpfqgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2017110620171020
2475300mpfqgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2017110620171020
2497060mpfqgcc -march=nocona -Os -fomit-frame-pointer2017110620171020
2498632mpfqgcc -m64 -march=nocona -Os -fomit-frame-pointer2017110620171020
2502624mpfqgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017110620171020
2504028mpfqgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017110620171020
2506628mpfqgcc -m64 -march=core2 -Os -fomit-frame-pointer2017110620171020
2545848mpfqgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017110620171020
2545892mpfqgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2017110620171020
2738916mpfqgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2017110620171020
2741196mpfqgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017110620171020
2743204mpfqgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2017110620171020
2745060mpfqgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2017110620171020
2745540mpfqgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2017110620171020
2745796mpfqgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017110620171020
2746172mpfqgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2017110620171020
2747772mpfqgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017110620171020
2749704mpfqgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2017110620171020
2750772mpfqgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017110620171020
2791756mpfqgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017110620171020
2792228mpfqgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017110620171020
2794912mpfqgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2017110620171020
2796116mpfqgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2017110620171020
2797736mpfqgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2017110620171020
3019388mpfqgcc -m64 -march=corei7 -Os -fomit-frame-pointer2017110620171020
3121724mpfqgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017110620171020
3135152mpfqgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017110620171020
3162628mpfqgcc -m64 -march=corei7 -O -fomit-frame-pointer2017110620171020
8106764mpfqgcc2017110620171020
8107652mpfqgcc -funroll-loops2017110620171020
8123292mpfqcc2017110620171020

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: 10, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments mpfq
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments mpfq
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments mpfq
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments mpfq
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments mpfq
clang -O3 -fwrapv -mavx -maes -mpclmul -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