Implementation notes: amd64, gpu, crypto_aead/hs1sivhiv2

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: hs1sivhiv2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
23031	14042 0 0	36389 776 872	`faster`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
29055	14839 0 0	34342 792 928	`faster`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
29778	14839 0 0	34406 792 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
30264	9684 0 0	26845 784 928	`faster`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
30528	14839 0 0	34406 792 928	`faster`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
30540	28409 0 0	45077 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
31148	14839 0 0	34406 792 928	`faster`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
32022	14872 0 0	35405 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
32832	28014 0 0	44917 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
33054	30886 0 0	50222 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
33116	8332 0 0	23881 768 896	`faster`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
33292	9684 0 0	26845 784 928	`faster`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
33600	15336 0 0	36717 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
33608	28014 0 0	44917 784 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
33696	28014 0 0	44917 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
33824	28409 0 0	45077 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
34008	11847 0 0	27313 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
34065	15548 0 0	35062 792 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
34083	28014 0 0	44917 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
34172	14872 0 0	35405 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
34287	15548 0 0	34998 792 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
34515	11847 0 0	27313 768 896	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
34820	14042 0 0	37733 776 872	`faster`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
34860	11847 0 0	27313 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
35044	30886 0 0	50222 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
35212	9684 0 0	26845 784 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
35484	21338 0 0	42622 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
35512	30886 0 0	50222 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
35552	15336 0 0	36717 776 1160	`dolbeau/amd64-sse`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
35649	21357 0 0	43174 792 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
35668	15404 0 0	34750 792 928	`faster`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
35859	21357 0 0	43174 792 928	`faster`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190826	20190816
35904	35370 0 0	37662 792 928	`faster`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
35958	16054 0 0	35070 792 928	`faster`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
36116	9684 0 0	26845 784 928	`faster`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
36204	11877 0 0	32229 784 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
36204	9812 0 0	27013 784 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
36267	9924 0 0	27125 784 928	`faster`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
36276	8332 0 0	23881 768 896	`faster`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
36572	8112 0 0	23673 768 896	`faster`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
36588	8332 0 0	23881 768 896	`faster`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
36621	11466 0 0	31701 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
36675	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
36678	13149 0 0	33541 784 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
36708	13277 0 0	33797 784 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
36712	28409 0 0	45077 784 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
36832	8332 0 0	23881 768 896	`faster`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
36908	9477 0 0	26085 784 928	`faster`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
36980	11847 0 0	27313 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
37024	8112 0 0	23673 768 896	`faster`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
37146	12765 0 0	33005 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
37172	9812 0 0	27013 784 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
37305	9780 0 0	26893 784 928	`faster`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
37413	11877 0 0	32229 784 928	`faster`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190826	20190816
37576	21357 0 0	43174 792 928	`faster`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
37626	8413 0 0	23921 768 896	`faster`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
37632	13149 0 0	33541 784 928	`faster`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190826	20190816
37665	9161 0 0	26077 784 928	`faster`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
37824	16117 0 0	35622 792 928	`faster`	`gcc_-O3_-fomit-frame-pointer`	20190826	20190816
37880	9104 0 0	25989 784 928	`faster`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
37884	11815 0 0	31973 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
37892	8421 0 0	23929 768 896	`faster`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
37908	11551 0 0	31661 784 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
37988	17205 0 0	36902 792 928	`faster`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
38238	8400 0 0	23913 768 896	`faster`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
38292	22989 0 0	45286 792 928	`faster`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
38300	28409 0 0	45077 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
38440	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
38502	10189 0 0	27661 784 928	`faster`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
38508	9477 0 0	26085 784 928	`faster`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
38544	9104 0 0	25989 784 928	`faster`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
38560	14042 0 0	37733 776 872	`faster`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
38670	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
38727	17685 0 0	37662 792 928	`faster`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
38733	8894 0 0	25781 784 928	`faster`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
38788	32336 0 0	49277 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
38816	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
38836	23661 0 0	46238 792 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
38856	8807 0 0	25565 784 928	`faster`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
39144	8271 0 0	23777 768 896	`faster`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
39156	15988 0 0	35486 792 928	`faster`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
39268	10029 0 0	27157 784 928	`faster`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
39316	8413 0 0	23985 768 896	`faster`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
39327	31959 0 0	48629 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
39330	36460 0 0	55686 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
39376	11877 0 0	32229 784 928	`faster`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190826	20190816
39432	36675 0 0	55958 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
39568	8421 0 0	23929 768 896	`faster`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
39588	8807 0 0	25565 784 928	`faster`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
39596	32086 0 0	48965 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
39678	31817 0 0	48485 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
39680	12765 0 0	33005 784 928	`faster`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
39720	22989 0 0	45286 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
39740	8112 0 0	23673 768 896	`faster`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
39872	12357 0 0	27777 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
39884	11815 0 0	31973 784 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
39990	9653 0 0	26733 784 928	`faster`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
40038	12370 0 0	27793 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
40120	32336 0 0	49277 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
40160	11466 0 0	31701 784 928	`faster`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
40212	30886 0 0	50126 792 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
40220	12743 0 0	32605 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
40340	10029 0 0	27157 784 928	`faster`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
40416	14042 0 0	37733 776 872	`faster`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
40468	8532 0 0	24113 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
40536	9653 0 0	26733 784 928	`faster`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
40560	9026 0 0	25917 784 928	`faster`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
40644	21338 0 0	42622 792 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
40728	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
40964	8808 0 0	25589 784 928	`faster`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
41012	9154 0 0	26077 784 928	`faster`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
41028	36282 0 0	55374 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
41084	16117 0 0	35622 792 928	`faster`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
41193	32408 0 0	49077 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
41424	9104 0 0	25989 784 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
41512	23661 0 0	46238 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
41744	16054 0 0	35070 792 928	`faster`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
41820	12357 0 0	27777 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
41852	36460 0 0	55750 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
41920	8915 0 0	25845 784 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
42464	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
42476	31817 0 0	48485 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
42512	32422 0 0	49357 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
42748	9104 0 0	25989 784 928	`faster`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
42792	20378 0 0	27661 784 928	`faster`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
42796	16117 0 0	35622 792 928	`faster`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
42920	12743 0 0	32605 784 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
43008	12417 0 0	27857 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
43008	13149 0 0	33541 784 928	`faster`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
43100	17205 0 0	36902 792 928	`faster`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
43196	8400 0 0	23913 768 896	`faster`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
43308	8413 0 0	23985 768 896	`faster`	`gcc_-Os_-fomit-frame-pointer`	20190826	20190816
43672	10029 0 0	27157 784 928	`faster`	`gcc_-O2_-fomit-frame-pointer`	20190826	20190816
43908	8915 0 0	25845 784 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
44656	9161 0 0	26077 784 928	`faster`	`gcc_-m64_-O_-fomit-frame-pointer`	20190826	20190816
45044	8546 0 0	24121 768 896	`faster`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190826	20190816
45168	18308 0 0	26077 784 928	`faster`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
45444	16826 0 0	23921 768 896	`faster`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
46020	13277 0 0	33797 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
46364	11551 0 0	31661 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
46840	8532 0 0	24113 768 896	`faster`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
46940	8808 0 0	25589 784 928	`faster`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
46948	8413 0 0	23985 768 896	`faster`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
48892	9161 0 0	26077 784 928	`faster`	`gcc_-O_-fomit-frame-pointer`	20190826	20190816
66369	8062 0 0	29581 776 1160	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
69492	8062 0 0	29581 776 1160	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
71853	7606 0 0	31381 776 872	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
79065	7606 0 0	31381 776 872	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
79122	7486 0 0	28189 776 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
80619	7606 0 0	30053 776 872	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
84300	7606 0 0	31381 776 872	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
86862	8189 0 0	29398 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
89442	8359 0 0	30078 792 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
90999	7647 0 0	28077 784 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
91617	6655 0 0	26094 792 928	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
92427	7621 0 0	27733 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
92840	7486 0 0	28189 776 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
93132	8359 0 0	30078 792 928	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
94200	6583 0 0	26054 792 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
94336	8359 0 0	30078 792 928	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190826	20190816
95232	7647 0 0	28077 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
95307	7631 0 0	27933 784 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
95397	6623 0 0	26062 792 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
96284	7621 0 0	27733 784 928	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
96774	8183 0 0	30694 792 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
96846	7631 0 0	27933 784 928	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
97264	7501 0 0	27229 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
97468	6583 0 0	26054 792 928	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
97568	6583 0 0	26054 792 928	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
98676	6823 0 0	26222 792 928	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
99552	8183 0 0	30694 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
100884	8189 0 0	29398 792 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
101944	8157 0 0	30382 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
102112	8157 0 0	30382 792 928	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
102628	6583 0 0	25958 792 928	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
102880	7501 0 0	27229 784 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
103088	6595 0 0	25510 792 928	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
103368	6893 0 0	26478 792 928	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
104388	7631 0 0	27933 784 928	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190826	20190816
105784	6623 0 0	25998 792 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
105852	6823 0 0	26222 792 928	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190826	20190816
106480	6893 0 0	26478 792 928	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
106812	6559 0 0	25798 792 928	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
110492	6823 0 0	26222 792 928	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
111068	13870 0 0	26854 792 928	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
111880	6595 0 0	25510 792 928	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
112308	5863 0 0	22941 784 928	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
112616	6935 0 0	26854 792 928	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
113823	5863 0 0	22901 784 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
113871	5863 0 0	22901 784 928	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
114426	5863 0 0	22941 784 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
114612	5919 0 0	22941 784 928	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
114940	5863 0 0	22901 784 928	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
116264	5909 0 0	22861 784 928	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
117372	11838 0 0	23301 784 928	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
117420	5863 0 0	22901 784 928	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
118396	5863 0 0	22885 784 928	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
118660	5863 0 0	22941 784 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
120396	5919 0 0	23301 784 928	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
121048	4745 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
124524	5909 0 0	22861 784 928	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
126828	4755 0 0	20281 768 896	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
127014	8321 0 0	28510 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
127059	4755 0 0	20281 768 896	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
127530	4747 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
127540	4755 0 0	20281 768 896	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190826	20190816
127665	8256 0 0	28406 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
128568	4747 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
129184	4693 0 0	20169 768 896	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
129268	4747 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
129468	5696 0 0	22213 784 928	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
130148	4693 0 0	20177 768 896	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
130362	8256 0 0	28406 792 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
130424	4747 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
131238	4707 0 0	20209 768 896	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
131600	4679 0 0	20137 768 896	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
132440	4693 0 0	20169 768 896	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
132544	5696 0 0	22213 784 928	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
132639	8285 0 0	28630 792 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
133731	4677 0 0	20137 768 896	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
134236	5919 0 0	22941 784 928	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
134696	4679 0 0	20145 768 896	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
135012	4679 0 0	20145 768 896	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
135096	4707 0 0	20209 768 896	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
135204	4679 0 0	20145 768 896	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
135228	4707 0 0	20209 768 896	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
136122	8285 0 0	28630 792 928	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190826	20190816
136216	4693 0 0	20169 768 896	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190826	20190816
136868	9358 0 0	20137 768 896	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
137800	4679 0 0	20137 768 896	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
138156	8285 0 0	28630 792 928	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190826	20190816
138264	8271 0 0	28390 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
138504	4707 0 0	20209 768 896	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
139404	4745 0 0	20249 768 896	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
142044	4677 0 0	20137 768 896	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
142888	4679 0 0	20137 768 896	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
143766	16921 0 0	35598 776 888	`faster`	`cc`	20190826	20190816
144208	5919 0 0	22941 784 928	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190826	20190816
144480	8271 0 0	28390 792 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
145124	8321 0 0	28510 792 928	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
145728	16921 0 0	35598 776 888	`faster`	`gcc`	20190826	20190816
150576	6219 0 0	23006 792 928	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
150692	6157 0 0	22918 792 928	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
152392	6164 0 0	23062 792 928	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190826	20190816
153828	6168 0 0	23062 792 928	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
154020	6168 0 0	23062 792 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
154564	6219 0 0	23006 792 928	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
156144	6157 0 0	22918 792 928	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
156460	16921 0 0	35598 776 888	`faster`	`gcc_-funroll-loops`	20190826	20190816
159784	6153 0 0	23030 792 928	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
159964	6164 0 0	23062 792 928	`ref`	`gcc_-O_-fomit-frame-pointer`	20190826	20190816
160016	6164 0 0	23062 792 928	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
162036	6168 0 0	23062 792 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
162212	6164 0 0	23062 792 928	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
162648	6164 0 0	23062 792 928	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
162832	6164 0 0	23062 792 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
162964	6164 0 0	23062 792 928	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
163064	6164 0 0	23062 792 928	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
163116	12306 0 0	23030 792 928	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
865080	9141 0 0	27847 784 888	`ref`	`gcc_-funroll-loops`	20190826	20190816
876591	9141 0 0	27847 784 888	`ref`	`gcc`	20190826	20190816
923190	9141 0 0	27847 784 888	`ref`	`cc`	20190826	20190816

Test failure

Implementation: dolbeau/amd64-avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer

error 111

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

Compiler	Implementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	dolbeau/amd64-sse
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
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
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: dolbeau/amd64-avx2
Security model: unknown
Compiler: cc

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

Compiler	Implementations
cc	dolbeau/amd64-avx2
gcc	dolbeau/amd64-avx2
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops	dolbeau/amd64-avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/amd64-avx2
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:90:2: error: "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/amd64-avx2
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/amd64-avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~

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

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/amd64-avx512
Security model: unknown
Compiler: cc

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

Compiler	Implementations
cc	dolbeau/amd64-avx512
gcc	dolbeau/amd64-avx512
gcc -funroll-loops	dolbeau/amd64-avx512

Compiler output

Implementation: dolbeau/amd64-avx512
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:90:2: error: "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c:330:20: error: conflicting types for '_mm512_reduce_add_epi64'
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^
encrypt.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/avx512fintrin.h:9747:48: note: previous definition is here
encrypt.c: static __inline__ long long __DEFAULT_FN_ATTRS _mm512_reduce_add_epi64(__m512i __W) {
encrypt.c: ^
encrypt.c: encrypt.c:343:21: error: invalid input size for constraint 'Yz'
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: 3 errors generated.

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512

Compiler output

Implementation: dolbeau/amd64-avx512
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer

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

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: dolbeau/amd64-avx512
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c:330:20: error: conflicting types for '_mm512_reduce_add_epi64'
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:45:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx512fintrin.h:13531:1: note: previous definition of '_mm512_reduce_add_epi64' was here
encrypt.c: _mm512_reduce_add_epi64 (__m512i __A)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:330:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:111:11: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i x_0 = _mm512_set1_epi32(x[0]);
encrypt.c: ^~~
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:528:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 1);
encrypt.c: ^~~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c:330:20: error: conflicting types for '_mm512_reduce_add_epi64'
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:45:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx512fintrin.h:13531:1: note: previous definition of '_mm512_reduce_add_epi64' was here
encrypt.c: _mm512_reduce_add_epi64 (__m512i __A)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:330:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:111:11: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i x_0 = _mm512_set1_epi32(x[0]);
encrypt.c: ^~~
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:528:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 1);
encrypt.c: ^~~~

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: dolbeau/amd64-avx512
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 19, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512

Compiler output

Implementation: dolbeau/amd64-sse
Security model: unknown
Compiler: cc

Number of similar (compiler,implementation) pairs: 71, namely:

Compiler	Implementations
cc	dolbeau/amd64-sse
gcc	dolbeau/amd64-sse
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops	dolbeau/amd64-sse
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: dolbeau/amd64-sse
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:192:
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:14:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: ./c256.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse

Compiler output

Implementation: dolbeau/amd64-sse
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse