Implementation notes: amd64, gpu, crypto_core/invsntrup857

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: invsntrup857

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
10571955	2275 0 0	15480 784 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190822	20190816
16234268	2275 0 0	15576 784 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
16365030	2275 0 0	15576 784 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
16990976	2275 0 0	15576 784 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
18419331	2379 0 0	15624 784 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
18612587	2379 0 0	15472 784 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
18826364	2379 0 0	15560 784 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
30758752	3033 0 0	16264 784 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
31145270	8944 0 0	25288 784 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
31228229	6910 0 0	20496 784 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
31379122	14028 0 0	20760 784 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
31430821	8840 0 0	25072 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
31435317	8840 0 0	25072 784 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
31498688	4155 0 0	19792 784 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
31913868	3725 0 0	19128 784 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
31977792	2526 0 0	15840 784 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190822	20190816
31979032	6910 0 0	20496 784 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
32516306	2526 0 0	15840 784 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
32520291	3725 0 0	19128 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
32603259	2526 0 0	15840 784 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
33021438	2718 0 0	15800 784 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
34068108	8944 0 0	25288 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
34427193	4155 0 0	19792 784 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190822	20190816
35302175	4155 0 0	19792 784 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
35769419	7014 0 0	20760 784 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
36476093	2718 0 0	15800 784 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
40792305	1042 0 0	11805 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190822	20190816
48924772	5948 0 0	21037 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
49181126	4807 0 0	20541 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
49932188	4807 0 0	20541 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
50803503	5948 0 0	21037 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
56987991	2607 0 0	20733 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
58049457	2607 0 0	20733 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
58161788	2607 0 0	19405 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
58938684	3763 0 0	17901 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190822	20190816
59086844	3763 0 0	17901 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
59147056	3763 0 0	17901 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
60164902	3926 0 0	18109 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
60245475	3870 0 0	17925 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
60975387	3870 0 0	17925 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
63480048	2607 0 0	20733 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
64074362	3179 0 0	17421 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
66199674	3926 0 0	18109 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
66258795	3179 0 0	17221 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
66485106	2352 0 0	12309 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
66532752	1105 0 0	11917 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
66589360	1105 0 0	11917 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
67274548	1105 0 0	11925 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
67335373	1176 0 0	12309 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
67426460	3183 0 0	17445 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190822	20190816
67590022	3183 0 0	17445 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
67926111	1105 0 0	11925 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
68201748	1105 0 0	11965 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
68406402	1105 0 0	11917 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190822	20190816
68664104	1105 0 0	11917 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
69267648	1080 0 0	11949 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
69316596	1105 0 0	11925 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
69705731	3179 0 0	17221 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
69845004	3179 0 0	17421 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
70280403	1105 0 0	11965 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
70407768	1037 0 0	11893 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
70438776	1042 0 0	11853 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190822	20190816
70696873	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
70714711	3183 0 0	17445 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190822	20190816
71055859	1105 0 0	11917 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
71249771	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
71427366	1037 0 0	11893 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
71470695	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
71525709	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
72318093	1042 0 0	11853 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190822	20190816
72810144	2074 0 0	11837 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
73084086	1080 0 0	11949 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
73889772	1042 0 0	11853 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
74769252	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
74844072	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
74898462	1042 0 0	11805 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
75675483	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
75717253	1105 0 0	11965 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190822	20190816
76860960	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
77059104	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
77169162	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
77303430	868 0 0	10805 760 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
77410617	868 0 0	10805 760 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
77414825	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
78111639	868 0 0	10805 760 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
78257004	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
78370620	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
78578772	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
78755355	868 0 0	10805 760 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190822	20190816
78787620	1037 0 0	11837 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
78932331	868 0 0	10805 760 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190822	20190816
78964953	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
79100226	868 0 0	10805 760 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
79605635	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190822	20190816
79985687	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
79988366	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
80272169	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
80473864	868 0 0	10805 760 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
81420984	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
81667586	1736 0 0	10805 760 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
84670739	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
85145802	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
85667952	868 0 0	10805 760 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
86092551	909 0 0	10877 760 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
106963599	2582 0 0	16429 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
111928950	2582 0 0	16429 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
114285441	3248 0 0	17525 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
114681216	1309 0 0	11925 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
117564578	1082 0 0	11997 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
117616716	1309 0 0	11925 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
118382309	3248 0 0	17525 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
118679091	1082 0 0	11997 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
214161569	1752 0 0	13902 760 792	`ref`	`gcc_-funroll-loops`	20190822	20190816
218501256	1752 0 0	13902 760 792	`ref`	`cc`	20190822	20190816
219264239	1752 0 0	13902 760 792	`ref`	`gcc`	20190822	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

recip.c: recip.c:83:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i f0vec = _mm256_set1_epi16(f0);
recip.c: ^
recip.c: recip.c:84:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i g0vec = _mm256_set1_epi16(g0);
recip.c: ^
recip.c: recip.c:85:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:85:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:86:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:86:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:87:21: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.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

recip.c: recip.c:85:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:86:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:92:21: error: always_inline function '_mm256_blendv_epi8' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i finew = _mm256_blendv_epi8(fi,gi,maskvec);
recip.c: ^
recip.c: recip.c:93:21: error: always_inline function '_mm256_blendv_epi8' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: __m256i ginew = _mm256_blendv_epi8(gi,fi,maskvec);
recip.c: ^
recip.c: recip.c:94:13: error: always_inline function '_mm256_sub_epi16' requires target feature 'avx2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'avx2'
recip.c: ginew = _mm256_sub_epi16(montproduct(ginew,f0vec,f0vecqinv),montproduct(finew,g0vec,g0vecqinv));
recip.c: ^
recip.c: recip.c:75:7: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'montproduct' that is compiled without support for 'avx2'
recip.c: d = _mm256_mullo_epi16(x,yqinv);
recip.c: ^
recip.c: recip.c:76:8: error: always_inline function '_mm256_mulhi_epi16' requires target feature 'avx2', but would be inlined into function 'montproduct' that is compiled without support for 'avx2'
recip.c: hi = _mm256_mulhi_epi16(x,y);
recip.c: ^
recip.c: recip.c:77:7: error: always_inline function '_mm256_mulhi_epi16' requires target feature 'avx2', but would be inlined into function 'montproduct' that is compiled without support for 'avx2'
recip.c: e = _mm256_mulhi_epi16(d,qvec);
recip.c: ^
recip.c: recip.c:78:10: error: always_inline function '_mm256_sub_epi16' requires target feature 'avx2', but would be inlined into function 'montproduct' that is compiled without support for 'avx2'
recip.c: ...

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

recip.c: recip.c: In function 'montproduct':
recip.c: recip.c:72:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
recip.c: {
recip.c: ^
recip.c: recip.c:71:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
recip.c: static inline __m256i montproduct(__m256i x,__m256i y,__m256i yqinv)
recip.c: ^~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
recip.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~
recip.c: recip.c:78:10: note: called from here
recip.c: return _mm256_sub_epi16(hi,e);
recip.c: ^~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:546:1: error: inlining failed in call to always_inline '_mm256_mulhi_epi16': target specific option mismatch
recip.c: _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~~~
recip.c: recip.c:77:5: note: called from here
recip.c: e = _mm256_mulhi_epi16(d,qvec);
recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
recip.c: from recip.c:1:
recip.c: ...
recip.c: recip.c: In function 'montproduct':
recip.c: recip.c:72:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
recip.c: {
recip.c: ^
recip.c: recip.c:71:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
recip.c: static inline __m256i montproduct(__m256i x,__m256i y,__m256i yqinv)
recip.c: ^~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
recip.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~
recip.c: recip.c:78:10: note: called from here
recip.c: return _mm256_sub_epi16(hi,e);
recip.c: ^~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:546:1: error: inlining failed in call to always_inline '_mm256_mulhi_epi16': target specific option mismatch
recip.c: _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~~~
recip.c: recip.c:77:5: note: called from here
recip.c: e = _mm256_mulhi_epi16(d,qvec);
recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
recip.c: from recip.c:1:
recip.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

recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: recip.c: In function 'montproduct':
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
recip.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~
recip.c: recip.c:78:10: note: called from here
recip.c: return _mm256_sub_epi16(hi,e);
recip.c: ^~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:546:1: error: inlining failed in call to always_inline '_mm256_mulhi_epi16': target specific option mismatch
recip.c: _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~~~
recip.c: recip.c:77:5: note: called from here
recip.c: e = _mm256_mulhi_epi16(d,qvec);
recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:546:1: error: inlining failed in call to always_inline '_mm256_mulhi_epi16': target specific option mismatch
recip.c: _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
recip.c: ^~~~~~~~~~~~~~~~~~
recip.c: recip.c:76:6: note: called from here
recip.c: hi = _mm256_mulhi_epi16(x,y);
recip.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~
recip.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