Implementation notes: amd64, glyme, crypto_sign/3icp

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_sign
Primitive: 3icp

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
591512	`ref`	`g++ -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
592364	`ref`	`g++ -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
598644	`ref`	`g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
612200	`ref`	`clang++ -O3 -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
612912	`ref`	`g++ -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
619140	`ref`	`clang++ -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
619908	`ref`	`clang++ -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
620708	`ref`	`g++ -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
622576	`ref`	`g++ -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
625940	`ref`	`g++ -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
625992	`ref`	`clang++ -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
627776	`ref`	`g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
630696	`ref`	`g++ -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
642584	`ref`	`g++ -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
643364	`ref`	`g++ -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
643772	`ref`	`g++ -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
664584	`ref`	`g++ -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
674744	`ref`	`g++ -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
677936	`ref`	`g++ -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
680784	`ref`	`g++ -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
692092	`ref`	`g++ -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
696940	`ref`	`g++ -O3 -fomit-frame-pointer`	20170205	20170105
697532	`ref`	`g++ -m64 -O3 -fomit-frame-pointer`	20170205	20170105
703660	`ref`	`g++ -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
707240	`ref`	`g++ -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
707876	`ref`	`g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
708252	`ref`	`g++ -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
709092	`ref`	`g++ -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
709256	`ref`	`g++ -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
713596	`ref`	`g++ -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
713740	`ref`	`g++ -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
722380	`ref`	`g++ -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
723976	`ref`	`g++ -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
724280	`ref`	`g++ -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
728864	`ref`	`g++ -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
741816	`ref`	`g++ -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
743488	`ref`	`g++ -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
743892	`ref`	`g++ -O2 -fomit-frame-pointer`	20170205	20170105
747140	`ref`	`g++ -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
748364	`ref`	`g++ -m64 -O2 -fomit-frame-pointer`	20170205	20170105
755612	`ref`	`g++ -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
758080	`ref`	`g++ -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
783272	`ref`	`g++ -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
793220	`ref`	`g++ -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
793668	`ref`	`g++ -march=nocona -O -fomit-frame-pointer`	20170205	20170105
804104	`ref`	`g++ -m64 -O -fomit-frame-pointer`	20170205	20170105
805180	`ref`	`g++ -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
810244	`ref`	`g++ -O -fomit-frame-pointer`	20170205	20170105
810416	`ref`	`g++ -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
816828	`ref`	`g++ -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
819804	`ref`	`g++ -march=k8 -O -fomit-frame-pointer`	20170205	20170105
828096	`ref`	`g++ -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
889852	`ref`	`g++ -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
891344	`ref`	`g++ -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
894716	`ref`	`g++ -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
898004	`ref`	`g++ -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
901892	`ref`	`g++ -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
903940	`ref`	`g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
998348	`ref`	`g++ -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
1000140	`ref`	`g++ -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
1008060	`ref`	`g++ -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
1008908	`ref`	`g++ -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
1010552	`ref`	`g++ -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
1011760	`ref`	`g++ -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
1012080	`ref`	`g++ -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
1012480	`ref`	`g++ -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
1028488	`ref`	`g++ -Os -fomit-frame-pointer`	20170205	20170105
1035688	`ref`	`g++ -m64 -Os -fomit-frame-pointer`	20170205	20170105
7220668	`ref`	`CC`	20170205	20170105
9795212	`ref`	`g++`	20170205	20170105

Compiler output

Implementation: crypto_sign/3icp/ref
Compiler: clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

ThreeIC_p-test.cpp: In file included from ThreeIC_p-test.cpp:16:
ThreeIC_p-test.cpp: In file included from ./ThreeIC_p.h:6:
ThreeIC_p-test.cpp: ./tower.h:364:9: error: argument to '__builtin_ia32_palignr128' must be a constant integer
ThreeIC_p-test.cpp: return _mm_alignr_epi8(a1, a0, i*2);
ThreeIC_p-test.cpp: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
ThreeIC_p-test.cpp: /usr/bin/../lib/clang/3.8.0/include/tmmintrin.h:69:12: note: expanded from macro '_mm_alignr_epi8'
ThreeIC_p-test.cpp: (__m128i)__builtin_ia32_palignr128((__v16qi)(__m128i)(a), \
ThreeIC_p-test.cpp: ^
ThreeIC_p-test.cpp: In file included from ThreeIC_p-test.cpp:16:
ThreeIC_p-test.cpp: In file included from ./ThreeIC_p.h:6:
ThreeIC_p-test.cpp: ./tower.h:364:9: error: cannot initialize return object of type '__m128i' (vector of 2 'long long' values) with an rvalue of type 'void'
ThreeIC_p-test.cpp: return _mm_alignr_epi8(a1, a0, i*2);
ThreeIC_p-test.cpp: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
ThreeIC_p-test.cpp: /usr/bin/../lib/clang/3.8.0/include/tmmintrin.h:68:34: note: expanded from macro '_mm_alignr_epi8'
ThreeIC_p-test.cpp: #define _mm_alignr_epi8(a, b, n) __extension__ ({ \
ThreeIC_p-test.cpp: ^~~~~~~~~~~~~~~~~~
ThreeIC_p-test.cpp: 2 errors generated.

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

Compiler	Implementations
clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ref
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref