Implementation notes: amd64, gpu, crypto_aead/hs1sivlov2

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: hs1sivlov2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
10275	12177 0 0	31646 792 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
10916	17336 0 0	37645 776 1160	`faster`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
10996	12177 0 0	31582 792 928	`faster`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
11184	12177 0 0	31646 792 928	`faster`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
11469	11353 0 0	30790 792 928	`faster`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
11778	11456 0 0	32021 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
12248	12128 0 0	33461 776 1160	`dolbeau/amd64-sse`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
12256	8308 0 0	25413 784 928	`faster`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
12268	12128 0 0	33461 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
12276	17336 0 0	37645 776 1160	`faster`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
12344	12177 0 0	31646 792 928	`faster`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
12380	11456 0 0	32021 776 1160	`dolbeau/amd64-sse`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
12504	21542 0 0	40822 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
12549	12217 0 0	31670 792 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
12616	12217 0 0	31606 792 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
12681	18712 0 0	35565 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
12735	17027 0 0	38798 792 928	`faster`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190826	20190816
12796	21542 0 0	40822 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
12888	8308 0 0	25413 784 928	`faster`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
12897	18487 0 0	35101 784 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
12972	16705 0 0	37926 792 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
12992	8308 0 0	25413 784 928	`faster`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
13068	15157 0 0	38541 776 872	`faster`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
13089	10957 0 0	31373 784 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
13167	18487 0 0	35101 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
13216	10477 0 0	30597 784 928	`faster`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
13233	18712 0 0	35565 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
13254	10797 0 0	31181 784 928	`faster`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190826	20190816
13311	17027 0 0	38798 792 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
13324	11610 0 0	31054 792 928	`faster`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
13468	18712 0 0	35565 784 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
13496	12185 0 0	31422 792 928	`faster`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
13500	15157 0 0	38541 776 872	`faster`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
13500	11302 0 0	30238 792 928	`faster`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
13520	15157 0 0	37197 776 872	`faster`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
13536	10797 0 0	31181 784 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
13551	10477 0 0	30597 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
13593	10086 0 0	30229 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
13665	17956 0 0	40158 792 928	`faster`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
13708	11302 0 0	30238 792 928	`faster`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
13728	8745 0 0	24161 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
13748	17027 0 0	38798 792 928	`faster`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
13755	8132 0 0	25205 784 928	`faster`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
13812	21542 0 0	40822 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
13816	10102 0 0	30157 784 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
13848	10102 0 0	30157 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
13857	11610 0 0	31054 792 928	`faster`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
13936	10349 0 0	30117 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
14048	25204 0 0	32470 792 928	`faster`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
14064	10486 0 0	30541 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
14067	20216 0 0	37093 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
14094	7772 0 0	24605 784 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
14096	15157 0 0	38541 776 872	`faster`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
14100	18820 0 0	41302 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
14108	16705 0 0	37926 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
14128	7430 0 0	22945 768 896	`faster`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
14142	20360 0 0	37213 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
14148	8132 0 0	25261 784 928	`faster`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
14168	10472 0 0	30797 784 928	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
14178	8745 0 0	24161 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
14228	10086 0 0	30229 784 928	`faster`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
14228	7430 0 0	22945 768 896	`faster`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
14284	8018 0 0	24837 784 928	`faster`	`gcc_-m64_-O_-fomit-frame-pointer`	20190826	20190816
14304	10486 0 0	30541 784 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
14322	10349 0 0	30117 784 928	`faster`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
14412	7977 0 0	24813 784 928	`faster`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
14436	18712 0 0	35565 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
14445	20191 0 0	37077 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
14460	21542 0 0	40726 792 928	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
14588	18487 0 0	35101 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
14596	18487 0 0	35101 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
14604	12602 0 0	32470 792 928	`faster`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
14612	24038 0 0	43094 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
14660	11954 0 0	31518 792 928	`faster`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
14676	10957 0 0	31373 784 928	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
14727	19624 0 0	36237 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
14739	18820 0 0	41302 792 928	`faster`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
14766	16810 0 0	25805 784 928	`faster`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
14768	11610 0 0	31054 792 928	`faster`	`gcc_-O3_-fomit-frame-pointer`	20190826	20190816
14780	10472 0 0	30797 784 928	`faster`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190826	20190816
14796	8745 0 0	24161 768 896	`dolbeau/amd64-sse`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
14880	7754 0 0	24293 784 928	`faster`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
14913	7570 0 0	23177 768 896	`faster`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
14944	10797 0 0	31181 784 928	`faster`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
14946	23891 0 0	43054 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
14968	7595 0 0	23129 768 896	`faster`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
14988	19624 0 0	36237 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
15024	7977 0 0	24813 784 928	`faster`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
15028	7159 0 0	22673 768 896	`faster`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
15028	7977 0 0	24813 784 928	`faster`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
15090	7595 0 0	23193 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
15100	8132 0 0	25261 784 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
15120	8308 0 0	25413 784 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
15186	7620 0 0	24317 784 928	`faster`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
15192	7595 0 0	23129 768 896	`faster`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
15192	7430 0 0	22945 768 896	`faster`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
15212	8745 0 0	24161 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
15252	8180 0 0	25277 784 928	`faster`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
15255	14858 0 0	22969 768 896	`faster`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
15270	7901 0 0	24877 784 928	`faster`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
15363	7429 0 0	22961 768 896	`faster`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
15368	10472 0 0	30797 784 928	`faster`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190826	20190816
15648	17956 0 0	40158 792 928	`faster`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
15723	7429 0 0	22961 768 896	`faster`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
15948	8309 0 0	25429 784 928	`faster`	`gcc_-O2_-fomit-frame-pointer`	20190826	20190816
15996	23891 0 0	43118 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
16012	7685 0 0	24437 784 928	`faster`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
16044	11954 0 0	31518 792 928	`faster`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
16076	8405 0 0	25805 784 928	`faster`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
16120	19653 0 0	36269 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
16124	7754 0 0	24293 784 928	`faster`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
16128	7430 0 0	22945 768 896	`faster`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
16140	20109 0 0	36733 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
16184	7429 0 0	22969 768 896	`faster`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
16188	9040 0 0	24449 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
16200	7977 0 0	24813 784 928	`faster`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
16292	16074 0 0	24837 784 928	`faster`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
16376	24027 0 0	43262 792 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
16410	7406 0 0	22945 768 896	`faster`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
16449	7620 0 0	24317 784 928	`faster`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
16552	7406 0 0	22945 768 896	`faster`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
16566	8991 0 0	24417 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
16572	7570 0 0	23177 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
16572	7159 0 0	22673 768 896	`faster`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
16608	8309 0 0	25429 784 928	`faster`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
16616	7595 0 0	23201 768 896	`faster`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
16616	7429 0 0	22961 768 896	`faster`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
16828	7685 0 0	24437 784 928	`faster`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
16836	20216 0 0	37093 784 928	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
16848	7595 0 0	23201 768 896	`faster`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
16872	7277 0 0	22809 768 896	`faster`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
17040	7159 0 0	22673 768 896	`faster`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
17072	7595 0 0	23129 768 896	`faster`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190826	20190816
17120	8309 0 0	25429 784 928	`faster`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
17124	8037 0 0	24837 784 928	`faster`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
17180	7751 0 0	24605 784 928	`faster`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
17476	7772 0 0	24605 784 928	`faster`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
17504	8988 0 0	24417 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
17644	7883 0 0	24741 784 928	`faster`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
17660	7429 0 0	22961 768 896	`faster`	`gcc_-Os_-fomit-frame-pointer`	20190826	20190816
17692	7901 0 0	24877 784 928	`faster`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
17836	8018 0 0	24837 784 928	`faster`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
17960	8988 0 0	24417 768 896	`dolbeau/amd64-sse`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
18048	7595 0 0	23193 768 896	`faster`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
18112	8018 0 0	24837 784 928	`faster`	`gcc_-O_-fomit-frame-pointer`	20190826	20190816
18228	7429 0 0	22961 768 896	`faster`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
27648	7218 0 0	28629 776 1160	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
31581	6880 0 0	30541 776 872	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
31668	7218 0 0	28629 776 1160	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
32716	6880 0 0	30541 776 872	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
34024	6714 0 0	27333 776 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
34056	6714 0 0	27333 776 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
36108	6880 0 0	29213 776 872	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190826	20190816
38548	6880 0 0	30541 776 872	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190826	20190816
39261	5927 0 0	25350 792 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190826	20190816
44756	5927 0 0	25254 792 928	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190826	20190816
44892	7641 0 0	28774 792 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
45234	7551 0 0	29966 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
45260	4397 0 0	19849 768 896	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190826	20190816
45315	5927 0 0	25350 792 928	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190826	20190816
45420	7493 0 0	29654 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
45956	5959 0 0	25334 792 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190826	20190816
46332	7295 0 0	27629 784 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
46497	7493 0 0	29654 792 928	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
46584	7823 0 0	29510 792 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
46820	5927 0 0	25350 792 928	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190826	20190816
47264	5911 0 0	25118 792 928	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190826	20190816
47324	7295 0 0	27629 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
47380	7823 0 0	29510 792 928	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
47536	7247 0 0	27517 784 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
47540	7551 0 0	29966 792 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
47592	7823 0 0	29510 792 928	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190826	20190816
47648	6007 0 0	25382 792 928	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190826	20190816
48964	7253 0 0	27301 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
49608	7247 0 0	27517 784 928	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190826	20190816
49772	7095 0 0	26765 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
50512	6197 0 0	25718 792 928	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
51020	5947 0 0	24806 792 928	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
51624	6239 0 0	26062 792 928	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
52156	6197 0 0	25718 792 928	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190826	20190816
52200	7253 0 0	27301 784 928	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
52888	7641 0 0	28774 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
53252	6175 0 0	25542 792 928	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190826	20190816
53552	6175 0 0	25542 792 928	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190826	20190816
53748	7247 0 0	27517 784 928	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
53828	7095 0 0	26765 784 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
55056	6175 0 0	25542 792 928	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190826	20190816
55240	5959 0 0	25270 792 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190826	20190816
55608	12478 0 0	26062 792 928	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190826	20190816
55842	13606 0 0	32294 776 888	`faster`	`cc`	20190826	20190816
56560	5947 0 0	24806 792 928	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190826	20190816
58288	13606 0 0	32294 776 888	`faster`	`gcc_-funroll-loops`	20190826	20190816
58756	13606 0 0	32294 776 888	`faster`	`gcc`	20190826	20190816
60117	5511 0 0	22501 784 928	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190826	20190816
61908	5511 0 0	22525 784 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190826	20190816
61916	5511 0 0	22525 784 928	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190826	20190816
62595	7896 0 0	27942 792 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
63630	5551 0 0	22541 784 928	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190826	20190816
63942	11326 0 0	22949 784 928	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
64016	7908 0 0	27974 792 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
65022	7970 0 0	28086 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
65300	5551 0 0	22541 784 928	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190826	20190816
65484	7912 0 0	28198 792 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
65876	5370 0 0	21829 784 928	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
67328	5573 0 0	22461 784 928	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
68388	5511 0 0	22525 784 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190826	20190816
68584	7908 0 0	27974 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
68949	4399 0 0	19865 768 896	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190826	20190816
69327	5879 0 0	22718 792 928	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190826	20190816
69360	5573 0 0	22461 784 928	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190826	20190816
69568	7912 0 0	28198 792 928	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190826	20190816
69822	4467 0 0	19945 768 896	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
69825	5370 0 0	21829 784 928	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190826	20190816
70084	5663 0 0	22949 784 928	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190826	20190816
70536	7896 0 0	27942 792 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
70842	5879 0 0	22718 792 928	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190826	20190816
71116	5511 0 0	22501 784 928	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190826	20190816
71256	5511 0 0	22501 784 928	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190826	20190816
72177	4476 0 0	19985 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
72852	5551 0 0	22541 784 928	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190826	20190816
74000	7912 0 0	28198 792 928	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190826	20190816
74109	5868 0 0	22574 792 928	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
74132	5511 0 0	22501 784 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190826	20190816
74476	7970 0 0	28086 792 928	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
74709	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190826	20190816
75327	4399 0 0	19865 768 896	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
75568	4397 0 0	19857 768 896	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
75612	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190826	20190816
75680	4399 0 0	19865 768 896	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190826	20190816
75816	4391 0 0	19833 768 896	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190826	20190816
75868	4476 0 0	19977 768 896	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
75920	4467 0 0	19945 768 896	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
76224	11732 0 0	22686 792 928	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
76368	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190826	20190816
76532	4397 0 0	19849 768 896	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190826	20190816
76716	5511 0 0	22501 784 928	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190826	20190816
77052	4474 0 0	19977 768 896	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
77319	4391 0 0	19825 768 896	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190826	20190816
77952	5928 0 0	22654 792 928	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
77972	4476 0 0	19977 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
78284	4391 0 0	19825 768 896	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190826	20190816
78296	5868 0 0	22574 792 928	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190826	20190816
78840	4399 0 0	19857 768 896	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
79044	8798 0 0	19865 768 896	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
79236	4474 0 0	19977 768 896	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
79668	5928 0 0	22654 792 928	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190826	20190816
79816	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190826	20190816
79860	4391 0 0	19825 768 896	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190826	20190816
80036	5879 0 0	22718 792 928	`ref`	`gcc_-O_-fomit-frame-pointer`	20190826	20190816
80052	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190826	20190816
80948	4476 0 0	19985 768 896	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190826	20190816
80980	4467 0 0	19945 768 896	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190826	20190816
81172	4399 0 0	19865 768 896	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190826	20190816
81884	4397 0 0	19849 768 896	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190826	20190816
82328	5866 0 0	22686 792 928	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190826	20190816
82784	4397 0 0	19857 768 896	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190826	20190816
83068	4397 0 0	19849 768 896	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190826	20190816
83636	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190826	20190816
84940	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190826	20190816
86676	4399 0 0	19857 768 896	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190826	20190816
86828	5879 0 0	22718 792 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190826	20190816
379444	8668 0 0	27359 784 888	`ref`	`cc`	20190826	20190816
386676	8668 0 0	27359 784 888	`ref`	`gcc_-funroll-loops`	20190826	20190816
430424	8668 0 0	27359 784 888	`ref`	`gcc`	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: 14, 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 -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: encrypt.c: In function 'prf_hash2_1':
encrypt.c: encrypt.c:403:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(nhkey+ 0)); // 1
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: encrypt.c: In function 'prf_hash2_1':
encrypt.c: encrypt.c:403:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(nhkey+ 0)); // 1
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:317:20: 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:330:21: 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:317:20: 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:317:20: 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: encrypt.c: In function 'prf_hash2_1':
encrypt.c: encrypt.c:461:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:477:19: 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:317:20: 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:317:20: 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: encrypt.c: In function 'prf_hash2_1':
encrypt.c: encrypt.c:461:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:477:19: 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:190:
encrypt.c: ./c128.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c128.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: ./c128.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: ./c128.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: ./c128.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: ./c128.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: ./c128.h:100:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c128.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: ./c128.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: c128.h: In function 'chacha_noxor128':
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:190:0:
encrypt.c: c128.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: c128.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: c128.h:106:7: 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:190:0:
encrypt.c: c128.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: c128.h: In function 'chacha_noxor128':
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:190:0:
encrypt.c: c128.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: c128.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: c128.h:106:7: 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:190:0:
encrypt.c: c128.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