Implementation notes: amd64, gpu, crypto_decode/256x2

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_decode
Primitive: 256x2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1328	332 0 0	13533 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190820	20190816
1479	334 0 0	13389 768 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190820	20190816
1482	334 0 0	13453 768 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190820	20190816
1488	334 0 0	13333 768 800	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190820	20190816
1500	334 0 0	14806 776 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190820	20190816
1536	334 0 0	13389 768 800	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190820	20190816
1548	334 0 0	15446 776 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190820	20190816
1557	334 0 0	14806 776 800	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190820	20190816
1560	327 0 0	13613 768 800	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190820	20190816
1560	334 0 0	15534 776 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190820	20190816
1563	334 0 0	13389 768 800	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190820	20190816
1563	334 0 0	13333 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190820	20190816
1572	327 0 0	14590 776 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190820	20190816
1572	327 0 0	13605 768 800	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190820	20190816
1588	334 0 0	14806 776 800	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190820	20190816
1632	327 0 0	14590 776 800	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190820	20190816
1644	87 0 0	8969 752 768	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190820	20190816
1668	92 0 0	9805 768 800	`ref`	`gcc_-O_-fomit-frame-pointer`	20190820	20190816
1668	327 0 0	13117 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190820	20190816
1671	91 0 0	9845 768 800	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190820	20190816
1680	122 0 0	16397 760 744	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190820	20190816
1683	130 0 0	14701 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190820	20190816
1704	130 0 0	15357 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190820	20190816
1704	334 0 0	15446 776 800	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190820	20190816
1708	188 0 0	12606 776 800	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190820	20190816
1713	130 0 0	17741 760 744	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190820	20190816
1716	91 0 0	9821 768 800	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190820	20190816
1719	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190820	20190816
1725	130 0 0	14701 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190820	20190816
1725	327 0 0	13613 768 800	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190820	20190816
1740	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190820	20190816
1740	94 0 0	10069 768 800	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190820	20190816
1749	130 0 0	17741 760 744	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190820	20190816
1758	94 0 0	12062 776 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190820	20190816
1791	182 0 0	9789 768 800	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190820	20190816
1792	327 0 0	13613 768 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190820	20190816
1797	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190820	20190816
1800	95 0 0	12134 776 800	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190820	20190816
1812	327 0 0	13405 768 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190820	20190816
1833	94 0 0	9765 768 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190820	20190816
1836	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190820	20190816
1840	130 0 0	17741 760 744	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190820	20190816
1844	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190820	20190816
1848	334 0 0	13453 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190820	20190816
1848	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190820	20190816
1868	327 0 0	13405 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190820	20190816
1872	327 0 0	13117 768 800	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190820	20190816
1872	94 0 0	9757 768 800	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190820	20190816
1872	91 0 0	9805 768 800	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190820	20190816
1880	95 0 0	9757 768 800	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190820	20190816
1884	91 0 0	9789 768 800	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190820	20190816
1888	94 0 0	9757 768 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190820	20190816
1896	130 0 0	15357 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190820	20190816
1896	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190820	20190816
1899	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190820	20190816
1916	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190820	20190816
1936	95 0 0	9757 768 800	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190820	20190816
1940	334 0 0	15534 776 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190820	20190816
1940	94 0 0	12190 776 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190820	20190816
1944	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190820	20190816
1948	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190820	20190816
1956	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190820	20190816
1964	94 0 0	12126 776 800	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190820	20190816
1971	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190820	20190816
1972	327 0 0	13605 768 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190820	20190816
1972	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190820	20190816
1974	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190820	20190816
1977	88 0 0	11902 776 800	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190820	20190816
1980	332 0 0	13533 768 800	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190820	20190816
1984	94 0 0	12190 776 800	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190820	20190816
2004	88 0 0	11902 776 800	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190820	20190816
2016	92 0 0	9805 768 800	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190820	20190816
2020	188 0 0	10069 768 800	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190820	20190816
2020	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190820	20190816
2036	94 0 0	11974 776 800	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190820	20190816
2046	94 0 0	12438 776 800	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190820	20190816
2048	91 0 0	9845 768 800	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190820	20190816
2052	91 0 0	9821 768 800	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190820	20190816
2056	94 0 0	9805 768 800	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190820	20190816
2060	94 0 0	9757 768 800	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190820	20190816
2073	87 0 0	8969 752 768	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190820	20190816
2088	94 0 0	9805 768 800	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190820	20190816
2096	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190820	20190816
2100	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190820	20190816
2100	92 0 0	9805 768 800	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190820	20190816
2108	94 0 0	9765 768 800	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190820	20190816
2121	95 0 0	9757 768 800	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190820	20190816
2124	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190820	20190816
2124	94 0 0	9757 768 800	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190820	20190816
2136	95 0 0	12134 776 800	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190820	20190816
2140	94 0 0	12190 776 800	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190820	20190816
2148	94 0 0	12094 776 800	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190820	20190816
2152	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190820	20190816
2156	87 0 0	8969 752 768	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190820	20190816
2204	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190820	20190816
2217	88 0 0	9509 768 800	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190820	20190816
2217	88 0 0	9509 768 800	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190820	20190816
2238	91 0 0	8993 752 768	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190820	20190816
2244	87 0 0	8969 752 768	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190820	20190816
2248	94 0 0	9765 768 800	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190820	20190816
2252	94 0 0	12126 776 800	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190820	20190816
2252	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190820	20190816
2264	87 0 0	8969 752 768	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190820	20190816
2312	174 0 0	8969 752 768	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190820	20190816
2324	87 0 0	8969 752 768	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190820	20190816
2340	91 0 0	9805 768 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190820	20190816
2368	95 0 0	12134 776 800	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190820	20190816
2412	94 0 0	12438 776 800	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190820	20190816
2412	94 0 0	12606 776 800	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190820	20190816
2412	94 0 0	9757 768 800	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190820	20190816
2428	87 0 0	8969 752 768	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190820	20190816
2432	87 0 0	8969 752 768	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190820	20190816
4316	157 0 0	11454 760 760	`ref`	`gcc`	20190820	20190816
4356	157 0 0	11454 760 760	`ref`	`gcc_-funroll-loops`	20190820	20190816
4680	157 0 0	11454 760 760	`ref`	`cc`	20190820	20190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer

error 111

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

Compiler	Implementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: cc

Number of similar (compiler,implementation) pairs: 87, namely:

Compiler	Implementations
cc	avx
gcc	avx
gcc -O2 -fomit-frame-pointer	avx
gcc -O3 -fomit-frame-pointer	avx
gcc -O -fomit-frame-pointer	avx
gcc -Os -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	avx
gcc -fno-schedule-insns -O -fomit-frame-pointer	avx
gcc -fno-schedule-insns -Os -fomit-frame-pointer	avx
gcc -funroll-loops	avx
gcc -funroll-loops -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -O -fomit-frame-pointer	avx
gcc -funroll-loops -Os -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	avx
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	avx
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	avx
gcc -m64 -O2 -fomit-frame-pointer	avx
gcc -m64 -O3 -fomit-frame-pointer	avx
gcc -m64 -O -fomit-frame-pointer	avx
gcc -m64 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	avx
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -O -fomit-frame-pointer	avx
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	avx
gcc -m64 -march=k8 -O -fomit-frame-pointer	avx
gcc -m64 -march=k8 -Os -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	avx
gcc -m64 -march=nocona -O -fomit-frame-pointer	avx
gcc -m64 -march=nocona -Os -fomit-frame-pointer	avx
gcc -march=barcelona -O2 -fomit-frame-pointer	avx
gcc -march=barcelona -O3 -fomit-frame-pointer	avx
gcc -march=barcelona -O -fomit-frame-pointer	avx
gcc -march=barcelona -Os -fomit-frame-pointer	avx
gcc -march=k8 -O2 -fomit-frame-pointer	avx
gcc -march=k8 -O3 -fomit-frame-pointer	avx
gcc -march=k8 -O -fomit-frame-pointer	avx
gcc -march=k8 -Os -fomit-frame-pointer	avx
gcc -march=nocona -O2 -fomit-frame-pointer	avx
gcc -march=nocona -O3 -fomit-frame-pointer	avx
gcc -march=nocona -O -fomit-frame-pointer	avx
gcc -march=nocona -Os -fomit-frame-pointer	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

decode.c: decode.c:16:17: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: ^
decode.c: decode.c:18:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:18:31: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:5:14: note: expanded from macro 'COPY'
decode.c: #define COPY _mm256_set_epi64x(0x0303030303030303,0x0202020202020202,0x0101010101010101,0x0000000000000000)
decode.c: ^
decode.c: decode.c:20:9: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:20:31: error: always_inline function '_mm256_set1_epi64x' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:6:14: note: expanded from macro 'MASK'
decode.c: #define MASK _mm256_set1_epi64x(0x8040201008040201)
decode.c: ^
decode.c: decode.c:21:9: error: always_inline function '_mm256_cmpeq_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_cmpeq_epi8(x,_mm256_setzero_si256());
decode.c: ^
decode.c: decode.c:21:29: error: always_inline function '_mm256_setzero_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: ...

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

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

decode.c: decode.c:18:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:20:9: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:21:9: error: always_inline function '_mm256_cmpeq_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_cmpeq_epi8(x,_mm256_setzero_si256());
decode.c: ^
decode.c: 3 errors generated.

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	avx
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

decode.c: decode.c: In function 'crypto_decode_256x2_avx':
decode.c: decode.c:16:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
decode.c: __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: ^
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:925:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
decode.c: _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
decode.c: ^~~~~~~~~~~~~~~~~~~
decode.c: decode.c:23:5: note: called from here
decode.c: _mm256_storeu_si256(r,x);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1341:1: error: inlining failed in call to always_inline '_mm256_set1_epi64x': target specific option mismatch
decode.c: _mm256_set1_epi64x (long long __A)
decode.c: ^~~~~~~~~~~~~~~~~~
decode.c: decode.c:7:15: note: called from here
decode.c: #define MASK2 _mm256_set1_epi64x(0x0101010101010101)
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: decode.c:22:10: note: in expansion of macro 'MASK2'
decode.c: x &= MASK2;
decode.c: ^~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
decode.c: from decode.c:1:
decode.c: ...
decode.c: decode.c: In function 'crypto_decode_256x2_avx':
decode.c: decode.c:16:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
decode.c: __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: ^
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:925:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
decode.c: _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
decode.c: ^~~~~~~~~~~~~~~~~~~
decode.c: decode.c:23:5: note: called from here
decode.c: _mm256_storeu_si256(r,x);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1341:1: error: inlining failed in call to always_inline '_mm256_set1_epi64x': target specific option mismatch
decode.c: _mm256_set1_epi64x (long long __A)
decode.c: ^~~~~~~~~~~~~~~~~~
decode.c: decode.c:7:15: note: called from here
decode.c: #define MASK2 _mm256_set1_epi64x(0x0101010101010101)
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: decode.c:22:10: note: in expansion of macro 'MASK2'
decode.c: x &= MASK2;
decode.c: ^~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
decode.c: from decode.c:1:
decode.c: ...

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

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
decode.c: from decode.c:1:
decode.c: decode.c: In function 'crypto_decode_256x2_avx':
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:231:1: error: inlining failed in call to always_inline '_mm256_cmpeq_epi8': target specific option mismatch
decode.c: _mm256_cmpeq_epi8 (__m256i __A, __m256i __B)
decode.c: ^~~~~~~~~~~~~~~~~
decode.c: decode.c:21:7: note: called from here
decode.c: x = _mm256_cmpeq_epi8(x,_mm256_setzero_si256());
decode.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:186:1: error: inlining failed in call to always_inline '_mm256_andnot_si256': target specific option mismatch
decode.c: _mm256_andnot_si256 (__m256i __A, __m256i __B)
decode.c: ^~~~~~~~~~~~~~~~~~~
decode.c: decode.c:20:7: note: called from here
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
decode.c: from decode.c:1:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:588:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi8': target specific option mismatch
decode.c: _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
decode.c: ^~~~~~~~~~~~~~~~~~~
decode.c: decode.c:18:7: note: called from here
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: ...

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

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	avx
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	avx
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	avx
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	avx
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx