Implementation notes: amd64, gpu, crypto_core/invhrss701

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: invhrss701

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
4686988	10690 0 0	26381 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
5517804	7295 0 0	25357 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
5538352	7295 0 0	25357 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
6747145	6060 0 0	19192 784 832	`simpler`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190821	20190816
6897940	5895 0 0	19112 784 832	`simpler`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190821	20190816
6910752	5895 0 0	19112 784 832	`simpler`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190821	20190816
6938500	5895 0 0	19112 784 832	`simpler`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190821	20190816
7335200	6342 0 0	19480 784 832	`simpler`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190821	20190816
7456080	6028 0 0	19040 784 832	`simpler`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190821	20190816
7468501	6028 0 0	19128 784 832	`simpler`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190821	20190816
7551720	6256 0 0	21808 784 832	`simpler`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190821	20190816
7598296	6028 0 0	19192 784 832	`simpler`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190821	20190816
7601368	5147 0 0	18294 776 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190821	20190816
7621748	6256 0 0	21808 784 832	`simpler`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
7693956	5147 0 0	18294 776 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190821	20190816
7695612	7004 0 0	23272 784 832	`simpler`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
7857896	5099 0 0	18150 776 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190821	20190816
7894288	6256 0 0	21808 784 832	`simpler`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
7901016	6037 0 0	19704 784 832	`simpler`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
7907756	5147 0 0	18294 776 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190821	20190816
7944991	6005 0 0	19504 784 832	`simpler`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
7949432	4583 0 0	17808 784 832	`simpler`	`gcc_-O3_-fomit-frame-pointer`	20190821	20190816
7981600	6916 0 0	23072 784 832	`simpler`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
7985632	4583 0 0	17808 784 832	`simpler`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
7987932	12074 0 0	19704 784 832	`simpler`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
7990308	6916 0 0	23072 784 832	`simpler`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8004120	4526 0 0	17528 784 832	`simpler`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8062864	6218 0 0	21528 784 832	`simpler`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8076876	4583 0 0	17808 784 832	`simpler`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
8126940	4526 0 0	17528 784 832	`simpler`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8141604	7004 0 0	23272 784 832	`simpler`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
8168288	6005 0 0	19504 784 832	`simpler`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8453648	6218 0 0	21528 784 832	`simpler`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8528536	10690 0 0	26381 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
8883956	8370 0 0	23421 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
9059644	8370 0 0	23421 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
9480777	4740 0 0	17750 776 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190821	20190816
9586732	4740 0 0	17662 776 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190821	20190816
9670264	4740 0 0	17814 776 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190821	20190816
9678446	4740 0 0	17814 776 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190821	20190816
9851216	7295 0 0	25357 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
9853592	7295 0 0	24029 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
10915140	9430 0 0	24878 776 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190821	20190816
10921075	9430 0 0	24878 776 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
11078248	9430 0 0	24878 776 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
11417928	9453 0 0	24670 776 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
11713716	9903 0 0	25958 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
11748840	9846 0 0	26006 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
11955720	9903 0 0	25958 776 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
12002562	9453 0 0	24670 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
12122843	9846 0 0	26006 776 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
12491136	6885 0 0	20454 776 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
12629941	6816 0 0	20214 776 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
12826184	6816 0 0	20214 776 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
12926747	13770 0 0	20454 776 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
13012475	4524 0 0	17662 776 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190821	20190816
13155606	4450 0 0	17358 776 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
13189996	4450 0 0	17358 776 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
13211462	4524 0 0	17662 776 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
13404088	4524 0 0	17662 776 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
20562792	4560 0 0	19573 760 1128	`simpler`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
20639861	4896 0 0	20565 760 1128	`simpler`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
21017011	4560 0 0	19573 760 1128	`simpler`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
21142832	4896 0 0	20565 760 1128	`simpler`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
21750581	4656 0 0	22709 760 776	`simpler`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
22091056	4656 0 0	21381 760 776	`simpler`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
22439512	4656 0 0	22709 760 776	`simpler`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
22493324	4656 0 0	22709 760 776	`simpler`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
36794455	2812 0 0	16997 768 832	`simpler`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
39671279	2652 0 0	16429 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
39843140	2669 0 0	16749 768 832	`simpler`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
39878684	2669 0 0	16749 768 832	`simpler`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190821	20190816
40366360	2717 0 0	16845 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
40550520	2669 0 0	16749 768 832	`simpler`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
40706664	2653 0 0	16645 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
40775180	2653 0 0	16645 768 832	`simpler`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
41854952	2717 0 0	16845 768 832	`simpler`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
42350940	2652 0 0	16429 768 832	`simpler`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
42849240	2793 0 0	16773 768 832	`simpler`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
42894499	2812 0 0	16997 768 832	`simpler`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190821	20190816
42925606	2759 0 0	16965 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
42952708	2793 0 0	16957 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
42972904	2793 0 0	16957 768 832	`simpler`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
43040202	2793 0 0	16773 768 832	`simpler`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
43109394	2759 0 0	16965 768 832	`simpler`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
43221827	903 0 0	11709 768 832	`simpler`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
43234071	920 0 0	11669 768 832	`simpler`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190821	20190816
43298148	920 0 0	11669 768 832	`simpler`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190821	20190816
43366180	922 0 0	11677 768 832	`simpler`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190821	20190816
43591300	1870 0 0	12005 768 832	`simpler`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
43641624	920 0 0	11709 768 832	`simpler`	`gcc_-O2_-fomit-frame-pointer`	20190821	20190816
43665397	2812 0 0	16997 768 832	`simpler`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190821	20190816
43791745	920 0 0	11661 768 832	`simpler`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190821	20190816
43885796	860 0 0	11413 768 832	`simpler`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
43995612	920 0 0	11709 768 832	`simpler`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
44303776	920 0 0	11709 768 832	`simpler`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
44770051	935 0 0	12005 768 832	`simpler`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
45300740	920 0 0	11661 768 832	`simpler`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190821	20190816
45409789	920 0 0	11661 768 832	`simpler`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190821	20190816
45442170	920 0 0	11661 768 832	`simpler`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190821	20190816
45504366	920 0 0	11669 768 832	`simpler`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190821	20190816
45999692	860 0 0	11413 768 832	`simpler`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
46478028	903 0 0	11709 768 832	`simpler`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
46931656	895 0 0	11685 768 832	`simpler`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
47026107	909 0 0	11597 768 832	`simpler`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190821	20190816
47116458	909 0 0	11645 768 832	`simpler`	`gcc_-O_-fomit-frame-pointer`	20190821	20190816
47162668	909 0 0	11757 768 832	`simpler`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
47186496	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190821	20190816
47236208	909 0 0	11645 768 832	`simpler`	`gcc_-m64_-O_-fomit-frame-pointer`	20190821	20190816
47475100	909 0 0	11645 768 832	`simpler`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
47477636	909 0 0	11757 768 832	`simpler`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
47642583	1790 0 0	11629 768 832	`simpler`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
47812094	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190821	20190816
47860240	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190821	20190816
48003412	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190821	20190816
48445283	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190821	20190816
48716900	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190821	20190816
48806744	895 0 0	11685 768 832	`simpler`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
49437064	895 0 0	11629 768 832	`simpler`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
50291028	909 0 0	11597 768 832	`simpler`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190821	20190816
57174116	754 0 0	10529 752 800	`simpler`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
57481288	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190821	20190816
57628122	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190821	20190816
58107796	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
58274626	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190821	20190816
58287072	754 0 0	10529 752 800	`simpler`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
58395408	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190821	20190816
58725502	754 0 0	10529 752 800	`simpler`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
58781536	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190821	20190816
59029797	1508 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
59277846	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190821	20190816
59822416	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190821	20190816
59877584	754 0 0	10529 752 800	`simpler`	`gcc_-Os_-fomit-frame-pointer`	20190821	20190816
60022939	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
60033145	754 0 0	10529 752 800	`simpler`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
60138644	758 0 0	10545 752 800	`simpler`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190821	20190816
60268004	754 0 0	10529 752 800	`simpler`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
61143864	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
61997092	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
62212547	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
62226201	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
62705660	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
64177694	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190821	20190816
64491196	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
65336068	4751 0 0	18805 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190821	20190816
66192604	4558 0 0	18517 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
66211131	4751 0 0	18805 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
66517852	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
66925044	4501 0 0	18253 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
67011205	4751 0 0	18805 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
67232556	795 0 0	10601 752 800	`simpler`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
67233840	4701 0 0	18805 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
67611734	4558 0 0	18517 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
68031889	4701 0 0	18805 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
69088024	4501 0 0	18253 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
69368411	4568 0 0	18733 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
72190263	4499 0 0	18677 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
72448068	4563 0 0	18509 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
73903984	2968 0 0	12541 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
73944954	4563 0 0	18509 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
74053036	4568 0 0	18733 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190821	20190816
74421514	4414 0 0	18557 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
74816073	1316 0 0	12109 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
75164080	1316 0 0	12109 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
75212160	4414 0 0	18557 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
75242753	1436 0 0	12165 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190821	20190816
75288684	1436 0 0	12165 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190821	20190816
75292459	1436 0 0	12213 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
75462224	4568 0 0	18733 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190821	20190816
75493275	4499 0 0	18677 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
75849512	1436 0 0	12213 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190821	20190816
76082464	1436 0 0	12165 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190821	20190816
76259912	1436 0 0	12173 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190821	20190816
76272884	1280 0 0	11813 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
76551456	1436 0 0	12213 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
76593724	1280 0 0	11813 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
76667078	1436 0 0	12173 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190821	20190816
76867536	1436 0 0	12165 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190821	20190816
77431944	1428 0 0	12149 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190821	20190816
77500962	1436 0 0	12173 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190821	20190816
77609231	1484 0 0	12541 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
77804572	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190821	20190816
78130854	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190821	20190816
78436708	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190821	20190816
79187736	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190821	20190816
79499844	1356 0 0	12069 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190821	20190816
80291860	1302 0 0	12125 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
81046350	1356 0 0	12069 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190821	20190816
81099330	2704 0 0	12053 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
81368656	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190821	20190816
81538924	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190821	20190816
81574736	1356 0 0	12069 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
81908352	1356 0 0	12021 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190821	20190816
82311044	1360 0 0	12037 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190821	20190816
82550588	1302 0 0	12125 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
82582782	1271 0 0	12037 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
82695042	1271 0 0	12037 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
83356140	1352 0 0	12053 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
88491305	1248 0 0	11025 752 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
88900540	2496 0 0	11025 752 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
89239896	1242 0 0	11009 752 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
89417124	1248 0 0	11025 752 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
89680923	1242 0 0	11009 752 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
89751704	1248 0 0	11025 752 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190821	20190816
90194288	1248 0 0	11025 752 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
90427890	1248 0 0	11025 752 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
90890577	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190821	20190816
90950946	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190821	20190816
90962397	1248 0 0	11025 752 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
91239222	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
91801278	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190821	20190816
91872919	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190821	20190816
92258913	1314 0 0	11113 752 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
92562558	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
92759796	1257 0 0	11041 752 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190821	20190816
93504552	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190821	20190816
93848357	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190821	20190816
94059990	1250 0 0	11025 752 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190821	20190816
94296044	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
94512067	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
94719046	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190821	20190816
95559674	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
95570316	1314 0 0	11113 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
97875836	1320 0 0	11129 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
146749095	1566 0 0	13646 760 792	`simpler`	`gcc_-funroll-loops`	20190821	20190816
150783028	1566 0 0	13646 760 792	`simpler`	`cc`	20190821	20190816
154125928	1566 0 0	13646 760 792	`simpler`	`gcc`	20190821	20190816
234734732	2532 0 0	14622 760 792	`ref`	`gcc`	20190821	20190816
238210660	2532 0 0	14622 760 792	`ref`	`gcc_-funroll-loops`	20190821	20190816
238502212	2532 0 0	14622 760 792	`ref`	`cc`	20190821	20190816

Test failure

Implementation: avx2
Security model: unknown
Compiler: cc

error 111

Number of similar (compiler,implementation) pairs: 131, namely:

Compiler	Implementations
cc	avx2
clang -O3 -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
gcc	avx2
gcc -O2 -fomit-frame-pointer	avx2
gcc -O3 -fomit-frame-pointer	avx2
gcc -O -fomit-frame-pointer	avx2
gcc -Os -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -funroll-loops	avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -O -fomit-frame-pointer	avx2
gcc -funroll-loops -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	avx2
gcc -m64 -O2 -fomit-frame-pointer	avx2
gcc -m64 -O3 -fomit-frame-pointer	avx2
gcc -m64 -O -fomit-frame-pointer	avx2
gcc -m64 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -march=barcelona -O -fomit-frame-pointer	avx2
gcc -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -march=k8 -O -fomit-frame-pointer	avx2
gcc -march=k8 -Os -fomit-frame-pointer	avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx2
gcc -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -march=nocona -O -fomit-frame-pointer	avx2
gcc -march=nocona -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	faster
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	faster
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	faster
clang -O3 -fomit-frame-pointer -Qunused-arguments	faster821
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	faster821
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	faster821
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	faster821
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster821
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster821
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster821
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster821
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
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	simpler
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	simpler
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	simpler

Test failure

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

error 111
error 111

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	avx2

Test failure

Implementation: faster821
Security model: unknown
Compiler: cc

error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation

Number of similar (compiler,implementation) pairs: 106, namely:

Compiler	Implementations
cc	faster821
gcc	faster821
gcc -O2 -fomit-frame-pointer	faster821
gcc -O3 -fomit-frame-pointer	faster821
gcc -O -fomit-frame-pointer	faster821
gcc -Os -fomit-frame-pointer	faster821
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	faster821
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	faster821
gcc -fno-schedule-insns -O -fomit-frame-pointer	faster821
gcc -fno-schedule-insns -Os -fomit-frame-pointer	faster821
gcc -funroll-loops	faster821
gcc -funroll-loops -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -O -fomit-frame-pointer	faster821
gcc -funroll-loops -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	faster821
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -O -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	faster821
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	faster821
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	faster821
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	faster821
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	faster821
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	faster821
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	faster821
gcc -m64 -O2 -fomit-frame-pointer	faster821
gcc -m64 -O3 -fomit-frame-pointer	faster821
gcc -m64 -O -fomit-frame-pointer	faster821
gcc -m64 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	faster821
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -O -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	faster821
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	faster821
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	faster821
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=corei7 -O -fomit-frame-pointer	faster821
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=k8 -O -fomit-frame-pointer	faster821
gcc -m64 -march=k8 -Os -fomit-frame-pointer	faster821
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	faster821
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	faster821
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=nocona -O -fomit-frame-pointer	faster821
gcc -m64 -march=nocona -Os -fomit-frame-pointer	faster821
gcc -march=barcelona -O2 -fomit-frame-pointer	faster821
gcc -march=barcelona -O3 -fomit-frame-pointer	faster821
gcc -march=barcelona -O -fomit-frame-pointer	faster821
gcc -march=barcelona -Os -fomit-frame-pointer	faster821
gcc -march=k8 -O2 -fomit-frame-pointer	faster821
gcc -march=k8 -O3 -fomit-frame-pointer	faster821
gcc -march=k8 -O -fomit-frame-pointer	faster821
gcc -march=k8 -Os -fomit-frame-pointer	faster821
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	faster821
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	faster821
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	faster821
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	faster821
gcc -march=nocona -O2 -fomit-frame-pointer	faster821
gcc -march=nocona -O3 -fomit-frame-pointer	faster821
gcc -march=nocona -O -fomit-frame-pointer	faster821
gcc -march=nocona -Os -fomit-frame-pointer	faster821

Test failure

Implementation: faster821
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation
error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	faster821
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	faster821
gcc -m64 -march=barcelona -O -fomit-frame-pointer	faster821
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	faster821

Compiler output

Implementation: faster
Security model: unknown
Compiler: cc

core.c: core.c: In function 'vec256_frombits':
core.c: core.c:17:12: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
core.c: vec256 b0 = _mm256_loadu_si256((vec256 *) b); b += 32; /* 0,1,...,31 */
core.c: ^~
core.c: core.c: In function 'vec256_swap':
core.c: core.c:171:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
core.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
core.c: ^~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
core.c: from core.c:4:
core.c: core.c: In function 'vec256_bit0mask':
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1459:1: error: inlining failed in call to always_inline '_mm256_castsi256_si128': target specific option mismatch
core.c: _mm256_castsi256_si128 (__m256i __A)
core.c: ^~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:223:12: note: called from here
core.c: return -(_mm_cvtsi128_si32(_mm256_castsi256_si128(f[0])) & 1);
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	faster
gcc	faster
gcc -funroll-loops	faster

Compiler output

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

core.c: core.c:353:19: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: F0[0] = F0[1] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
core.c: ^
core.c: core.c:354:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: F0[2] = _mm256_set_epi32(32767,-1,32767,-1,32767,-1,65535,-1);
core.c: ^
core.c: core.c:355:27: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: F1[0] = F1[1] = F1[2] = _mm256_set1_epi32(0);
core.c: ^
core.c: core.c:357:27: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: V0[2] = V0[1] = V0[0] = _mm256_set1_epi32(0);
core.c: ^
core.c: core.c:358:27: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: V1[2] = V1[1] = V1[0] = _mm256_set1_epi32(0);
core.c: ^
core.c: core.c:360:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: R0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
core.c: ^
core.c: core.c:361:19: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: R0[2] = R0[1] = _mm256_set1_epi32(0);
core.c: ^
core.c: core.c:362:27: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: R1[2] = R1[1] = R1[0] = _mm256_set1_epi32(0);
core.c: ^
core.c: core.c:376:15: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'r3_recip' that is compiled without support for 'sse4.2'
core.c: ...

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

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

Compiler output

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

core.c: core.c:26:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c0 = _mm256_unpacklo_epi32(b0,b1); /* 0 1 2 3 32 33 34 35 4 5 6 7 36 37 38 39 ... 55 */
core.c: ^
core.c: core.c:27:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c1 = _mm256_unpackhi_epi32(b0,b1); /* 8 9 10 11 40 41 42 43 ... 63 */
core.c: ^
core.c: core.c:28:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c2 = _mm256_unpacklo_epi32(b2,b3);
core.c: ^
core.c: core.c:29:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c3 = _mm256_unpackhi_epi32(b2,b3);
core.c: ^
core.c: core.c:30:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c4 = _mm256_unpacklo_epi32(b4,b5);
core.c: ^
core.c: core.c:31:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c5 = _mm256_unpackhi_epi32(b4,b5);
core.c: ^
core.c: core.c:32:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c6 = _mm256_unpacklo_epi32(b6,b7);
core.c: ^
core.c: core.c:33:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: vec256 c7 = _mm256_unpackhi_epi32(b6,b7);
core.c: ^
core.c: core.c:35:22: error: always_inline function '_mm256_slli_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
core.c: ...

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

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

Compiler output

Implementation: faster
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 84, namely:

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

Compiler output

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

core.c: core.c: In function 'r3_recip':
core.c: core.c:353:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
core.c: F0[0] = F0[1] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
core.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c: In function 'vec256_swap':
core.c: core.c:171:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
core.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
core.c: ^~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: core.c: In function 'vec256_frombits':
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
core.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
core.c: ^~~~~~~~~~~~~~~~~~~~
core.c: core.c:56:7: note: called from here
core.c: h = _mm256_shuffle_epi32(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
core.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:55:7: note: called from here
core.c: h = _mm256_permute4x64_epi64(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: ...
core.c: core.c: In function 'r3_recip':
core.c: core.c:353:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
core.c: F0[0] = F0[1] = _mm256_set_epi32(-1,-1,-1,-1,-1,-1,-1,-1);
core.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c: In function 'vec256_swap':
core.c: core.c:171:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
core.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
core.c: ^~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: core.c: In function 'vec256_frombits':
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
core.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
core.c: ^~~~~~~~~~~~~~~~~~~~
core.c: core.c:56:7: note: called from here
core.c: h = _mm256_shuffle_epi32(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
core.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:55:7: note: called from here
core.c: h = _mm256_permute4x64_epi64(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: ...

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

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

Compiler output

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

core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: core.c: In function 'vec256_frombits':
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
core.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
core.c: ^~~~~~~~~~~~~~~~~~~~
core.c: core.c:56:7: note: called from here
core.c: h = _mm256_shuffle_epi32(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
core.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:55:7: note: called from here
core.c: h = _mm256_permute4x64_epi64(h,0xd8);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
core.c: from core.c:4:
core.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
core.c: _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
core.c: ^~~~~~~~~~~~~~~~~~~
core.c: core.c:54:7: note: called from here
core.c: h = _mm256_shuffle_epi8(h,TRANSPOSE);
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: ...

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

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