Implementation notes: amd64, gpu, crypto_aead/minalpherv11

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: minalpherv11

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
5610888	12538 0 0	31317 760 872	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190827	20190816
5659108	13575 0 0	30637 760 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190827	20190816
5863692	15807 0 0	34168 784 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190827	20190816
5873108	15695 0 0	33896 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190827	20190816
6085604	13635 0 0	31485 760 1160	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190827	20190816
6092600	13575 0 0	30637 760 1160	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190827	20190816
6332856	15695 0 0	33896 784 928	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190827	20190816
6334148	15474 0 0	32760 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190827	20190816
6340572	13850 0 0	33957 760 872	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190827	20190816
6342044	15935 0 0	33552 784 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190827	20190816
6432204	13635 0 0	31485 760 1160	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190827	20190816
6433000	15807 0 0	34168 784 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190827	20190816
6466000	15474 0 0	32760 784 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190827	20190816
6647604	10287 0 0	25832 784 928	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190827	20190816
6657520	15935 0 0	33552 784 928	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190827	20190816
6686356	9871 0 0	25008 784 928	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190827	20190816
6699120	10535 0 0	26296 784 928	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190827	20190816
6782336	10012 0 0	24984 784 928	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190827	20190816
6839028	13850 0 0	33957 760 872	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190827	20190816
6850956	13850 0 0	33957 760 872	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190827	20190816
6880748	10012 0 0	24984 784 928	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190827	20190816
6882144	21070 0 0	26296 784 928	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190827	20190816
6907580	10431 0 0	25720 784 928	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190827	20190816
6917976	15935 0 0	33552 784 928	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190827	20190816
6986840	10191 0 0	25544 784 928	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190827	20190816
7024412	10207 0 0	25464 784 928	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190827	20190816
7115096	10191 0 0	25544 784 928	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190827	20190816
7134220	10287 0 0	25832 784 928	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190827	20190816
7136516	10191 0 0	25544 784 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190827	20190816
7168184	10431 0 0	25720 784 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190827	20190816
7201364	9855 0 0	25152 784 928	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190827	20190816
7210060	9855 0 0	25152 784 928	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190827	20190816
7217988	9855 0 0	25152 784 928	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190827	20190816
7405908	10431 0 0	25656 784 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190827	20190816
7582744	14511 0 0	30533 768 928	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190827	20190816
7748972	14855 0 0	30989 768 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190827	20190816
8110076	14855 0 0	30989 768 928	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190827	20190816
8129888	16075 0 0	32397 768 928	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190827	20190816
8199352	14855 0 0	30989 768 928	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190827	20190816
8222800	14919 0 0	31133 768 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190827	20190816
8309532	15943 0 0	32125 768 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190827	20190816
8311560	14514 0 0	30237 768 928	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190827	20190816
8361216	14919 0 0	31133 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190827	20190816
8375568	15943 0 0	32125 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190827	20190816
8501480	15814 0 0	32101 768 928	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190827	20190816
8534376	14511 0 0	30533 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190827	20190816
8609372	14514 0 0	30237 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190827	20190816
8626272	15986 0 0	32093 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190827	20190816
8714480	16075 0 0	32397 768 928	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190827	20190816
8722616	16075 0 0	32397 768 928	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190827	20190816
8821568	15814 0 0	32101 768 928	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190827	20190816
8981408	15986 0 0	32093 768 928	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190827	20190816
9614856	7016 0 0	19861 768 928	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190827	20190816
9999064	7016 0 0	19869 768 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190827	20190816
10096680	7016 0 0	19861 768 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190827	20190816
10168716	6623 0 0	19461 768 928	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190827	20190816
10332148	7016 0 0	19861 768 928	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190827	20190816
10403048	14542 0 0	20429 768 928	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190827	20190816
10478116	6623 0 0	19461 768 928	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190827	20190816
10490228	7016 0 0	19861 768 928	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190827	20190816
10523380	7016 0 0	19869 768 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190827	20190816
10554904	6386 0 0	18909 768 928	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190827	20190816
10569608	7016 0 0	19861 768 928	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190827	20190816
10658400	7271 0 0	20429 768 928	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190827	20190816
10734756	7016 0 0	19861 768 928	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190827	20190816
10759372	7016 0 0	19861 768 928	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190827	20190816
10769356	7016 0 0	19861 768 928	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190827	20190816
10835820	5806 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190827	20190816
10908676	6386 0 0	18909 768 928	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190827	20190816
10915424	7016 0 0	19869 768 928	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190827	20190816
11213028	5806 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190827	20190816
11278592	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190827	20190816
11288680	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190827	20190816
11573736	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190827	20190816
11623640	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190827	20190816
11656824	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190827	20190816
11777204	6522 0 0	19405 768 928	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190827	20190816
11846900	6758 0 0	19621 768 928	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190827	20190816
11945876	13516 0 0	19621 768 928	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190827	20190816
11962860	6842 0 0	19717 768 928	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190827	20190816
11977140	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190827	20190816
12007212	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190827	20190816
12030592	6663 0 0	19509 768 928	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190827	20190816
12043328	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190827	20190816
12067028	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190827	20190816
12069120	6522 0 0	19405 768 928	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190827	20190816
12072000	5689 0 0	17561 752 896	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190827	20190816
12145116	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190827	20190816
12148752	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190827	20190816
12171812	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190827	20190816
12225748	6842 0 0	19717 768 928	`ref`	`gcc_-O_-fomit-frame-pointer`	20190827	20190816
12243692	6842 0 0	19717 768 928	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190827	20190816
12266532	5689 0 0	17561 752 896	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190827	20190816
12329296	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190827	20190816
12345324	6839 0 0	19717 768 928	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190827	20190816
12351100	5678 0 0	17545 752 896	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190827	20190816
12374268	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190827	20190816
12380004	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190827	20190816
12470544	5817 0 0	17713 752 896	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190827	20190816
12474056	6839 0 0	19717 768 928	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190827	20190816
12763520	6663 0 0	19509 768 928	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190827	20190816
12781148	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190827	20190816
12824464	5689 0 0	17561 752 896	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190827	20190816
12831364	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190827	20190816
12881260	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190827	20190816
12895232	11378 0 0	17561 752 896	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190827	20190816
12928956	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190827	20190816
13048128	5689 0 0	17561 752 896	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190827	20190816
13153904	5689 0 0	17561 752 896	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190827	20190816
13163740	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190827	20190816
13311384	5689 0 0	17561 752 896	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190827	20190816
13354776	5678 0 0	17545 752 896	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190827	20190816
41667072	9834 0 0	24414 760 888	`ref`	`gcc_-funroll-loops`	20190827	20190816
43782652	9834 0 0	24414 760 888	`ref`	`cc`	20190827	20190816
44744548	9834 0 0	24414 760 888	`ref`	`gcc`	20190827	20190816

Test failure

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

error 111

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

Compiler	Implementations
g++ -m64 -march=core-avx2 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=core-avx2 -O -fomit-frame-pointer	avx2
g++ -m64 -march=core-avx2 -Os -fomit-frame-pointer	avx2
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: avx2
Security model: unknown
Compiler: clang++ -O3 -fomit-frame-pointer -Qunused-arguments

MinalpherCore.cpp: MinalpherCore.cpp:85:27: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'sse4.2'
MinalpherCore.cpp: const __m256i ymmMask = _mm256_set_epi32(0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:88:17: error: always_inline function '_mm256_undefined_si256' requires target feature 'sse4.2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'sse4.2'
MinalpherCore.cpp: __m256i tmp = _mm256_permute4x64_epi64(DATA, 0xD8);
MinalpherCore.cpp: ^
MinalpherCore.cpp: /usr/include/clang/6.0.0/include/avx2intrin.h:968:44: note: expanded from macro '_mm256_permute4x64_epi64'
MinalpherCore.cpp: (__v4di)_mm256_undefined_si256(), \
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:92:10: error: always_inline function '_mm256_and_si256' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp0 = _mm256_and_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:93:10: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp1 = _mm256_andnot_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:96:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp1 = _mm256_srli_epi16(tmp1, 4);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:99:18: error: always_inline function '_mm256_unpacklo_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: __m256i ymm0 = _mm256_unpacklo_epi8(tmp0, tmp1);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:100:18: error: always_inline function '_mm256_unpackhi_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: __m256i ymm1 = _mm256_unpackhi_epi8(tmp0, tmp1);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:106:27: error: always_inline function '_mm256_set_epi8' requires target feature 'sse4.2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'sse4.2'
MinalpherCore.cpp: ...

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

Compiler	Implementations
clang++ -O3 -fomit-frame-pointer -Qunused-arguments	avx2
clang++ -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang++ -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2
clang++ -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

MinalpherCore.cpp: MinalpherCore.cpp:92:10: error: always_inline function '_mm256_and_si256' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp0 = _mm256_and_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:93:10: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp1 = _mm256_andnot_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:96:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: tmp1 = _mm256_srli_epi16(tmp1, 4);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:99:18: error: always_inline function '_mm256_unpacklo_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: __m256i ymm0 = _mm256_unpacklo_epi8(tmp0, tmp1);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:100:18: error: always_inline function '_mm256_unpackhi_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: __m256i ymm1 = _mm256_unpackhi_epi8(tmp0, tmp1);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:128:3: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: singleRoundFunctionH( 0, ymm0, ymm1);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:112:12: note: expanded from macro 'singleRoundFunctionH'
MinalpherCore.cpp: ymm0 = _mm256_shuffle_epi8( ymmSbox, ymm0 );\
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:128:3: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'avx2'
MinalpherCore.cpp: MinalpherCore.cpp:113:12: note: expanded from macro 'singleRoundFunctionH'
MinalpherCore.cpp: ymm1 = _mm256_shuffle_epi8( ymmSbox, ymm1 );\
MinalpherCore.cpp: ^
MinalpherCore.cpp: ...

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

Compiler	Implementations
clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	avx2
clang++ -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx2
clang++ -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx2
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: g++

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
g++	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: g++ -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 52, namely:

Compiler	Implementations
g++ -O2 -fomit-frame-pointer	avx2
g++ -O3 -fomit-frame-pointer	avx2
g++ -O -fomit-frame-pointer	avx2
g++ -Os -fomit-frame-pointer	avx2
g++ -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
g++ -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
g++ -fno-schedule-insns -O -fomit-frame-pointer	avx2
g++ -fno-schedule-insns -Os -fomit-frame-pointer	avx2
g++ -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
g++ -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
g++ -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx2
g++ -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx2
g++ -m64 -O2 -fomit-frame-pointer	avx2
g++ -m64 -O3 -fomit-frame-pointer	avx2
g++ -m64 -O -fomit-frame-pointer	avx2
g++ -m64 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -O -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4 -O -fomit-frame-pointer	avx2
g++ -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=corei7 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=corei7 -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=corei7 -O -fomit-frame-pointer	avx2
g++ -m64 -march=corei7 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=k8 -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=k8 -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=k8 -O -fomit-frame-pointer	avx2
g++ -m64 -march=k8 -Os -fomit-frame-pointer	avx2
g++ -m64 -march=nocona -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=nocona -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=nocona -O -fomit-frame-pointer	avx2
g++ -m64 -march=nocona -Os -fomit-frame-pointer	avx2
g++ -march=barcelona -O2 -fomit-frame-pointer	avx2
g++ -march=barcelona -O3 -fomit-frame-pointer	avx2
g++ -march=barcelona -O -fomit-frame-pointer	avx2
g++ -march=barcelona -Os -fomit-frame-pointer	avx2
g++ -march=k8 -O2 -fomit-frame-pointer	avx2
g++ -march=k8 -O3 -fomit-frame-pointer	avx2
g++ -march=k8 -O -fomit-frame-pointer	avx2
g++ -march=k8 -Os -fomit-frame-pointer	avx2
g++ -march=nocona -O2 -fomit-frame-pointer	avx2
g++ -march=nocona -O3 -fomit-frame-pointer	avx2
g++ -march=nocona -O -fomit-frame-pointer	avx2
g++ -march=nocona -Os -fomit-frame-pointer	avx2

Compiler output

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

MinalpherCore.cpp: MinalpherCore.cpp: In function 'void minalpher_core_single_block(const __m256i&, __m256i&, __m256i&)':
MinalpherCore.cpp: MinalpherCore.cpp:85:138: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
MinalpherCore.cpp: const __m256i ymmMask = _mm256_set_epi32(0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F);
MinalpherCore.cpp: ^
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h: In function 'void __static_initialization_and_destruction_0(int, int)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1277:1: error: inlining failed in call to always_inline '__m256i _mm256_set_epi8(char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char)': target specific option mismatch
MinalpherCore.cpp: _mm256_set_epi8 (char __q31, char __q30, char __q29, char __q28,
MinalpherCore.cpp: ^~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:705:55: note: called from here
MinalpherCore.cpp: const __m256i ShuffleQuadrupleBlock3 = _mm256_set_epi8(0xc, 0xd, 0x9, 0x8, 0xf, 0xe, 0xb, 0xa, 0x4, 0x5, 0x1, 0x0, 0x7, 0x6, 0x3, 0x2, 0xc, 0xd, 0x9, 0x8, 0xf, 0xe, 0xb, 0xa, 0x4, 0x5, 0x1, 0x0, 0x7, 0x6, 0x3, 0x2);
MinalpherCore.cpp: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1277:1: error: inlining failed in call to always_inline '__m256i _mm256_set_epi8(char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char)': target specific option mismatch
MinalpherCore.cpp: _mm256_set_epi8 (char __q31, char __q30, char __q29, char __q28,
MinalpherCore.cpp: ^~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:704:55: note: called from here
MinalpherCore.cpp: const __m256i ShuffleQuadrupleBlock2 = _mm256_set_epi8(0x9, 0x8, 0xf, 0xe, 0xd, 0xc, 0xa, 0xb, 0x1, 0x0, 0x7, 0x6, 0x5, 0x4, 0x2, 0x3, 0x9, 0x8, 0xf, 0xe, 0xd, 0xc, 0xa, 0xb, 0x1, 0x0, 0x7, 0x6, 0x5, 0x4, 0x2, 0x3);
MinalpherCore.cpp: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: ...
MinalpherCore.cpp: MinalpherCore.cpp: In function 'void minalpher_core_single_block(const __m256i&, __m256i&, __m256i&)':
MinalpherCore.cpp: MinalpherCore.cpp:85:138: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
MinalpherCore.cpp: const __m256i ymmMask = _mm256_set_epi32(0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F);
MinalpherCore.cpp: ^
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h: In function 'void __static_initialization_and_destruction_0(int, int)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1277:1: error: inlining failed in call to always_inline '__m256i _mm256_set_epi8(char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char)': target specific option mismatch
MinalpherCore.cpp: _mm256_set_epi8 (char __q31, char __q30, char __q29, char __q28,
MinalpherCore.cpp: ^~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:705:55: note: called from here
MinalpherCore.cpp: const __m256i ShuffleQuadrupleBlock3 = _mm256_set_epi8(0xc, 0xd, 0x9, 0x8, 0xf, 0xe, 0xb, 0xa, 0x4, 0x5, 0x1, 0x0, 0x7, 0x6, 0x3, 0x2, 0xc, 0xd, 0x9, 0x8, 0xf, 0xe, 0xb, 0xa, 0x4, 0x5, 0x1, 0x0, 0x7, 0x6, 0x3, 0x2);
MinalpherCore.cpp: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1277:1: error: inlining failed in call to always_inline '__m256i _mm256_set_epi8(char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char, char)': target specific option mismatch
MinalpherCore.cpp: _mm256_set_epi8 (char __q31, char __q30, char __q29, char __q28,
MinalpherCore.cpp: ^~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:704:55: note: called from here
MinalpherCore.cpp: const __m256i ShuffleQuadrupleBlock2 = _mm256_set_epi8(0x9, 0x8, 0xf, 0xe, 0xd, 0xc, 0xa, 0xb, 0x1, 0x0, 0x7, 0x6, 0x5, 0x4, 0x2, 0x3, 0x9, 0x8, 0xf, 0xe, 0xd, 0xc, 0xa, 0xb, 0x1, 0x0, 0x7, 0x6, 0x5, 0x4, 0x2, 0x3);
MinalpherCore.cpp: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: ...

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

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

Compiler output

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

MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h: In function 'void minalpher_core_single_block(const __m256i&, __m256i&, __m256i&)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:588:1: error: inlining failed in call to always_inline '__m256i _mm256_shuffle_epi8(__m256i, __m256i)': target specific option mismatch
MinalpherCore.cpp: _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
MinalpherCore.cpp: ^~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:150:30: note: called from here
MinalpherCore.cpp: ymm1_ = _mm256_shuffle_epi8(ymm1, ShuffleSingleBlock1);
MinalpherCore.cpp: ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:588:1: error: inlining failed in call to always_inline '__m256i _mm256_shuffle_epi8(__m256i, __m256i)': target specific option mismatch
MinalpherCore.cpp: _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
MinalpherCore.cpp: ^~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: MinalpherCore.cpp:149:9: note: called from here
MinalpherCore.cpp: ymm1 = _mm256_shuffle_epi8(ymmSbox, ymm1);
MinalpherCore.cpp: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
MinalpherCore.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: ...

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

Compiler	Implementations
g++ -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=core-avx-i -O -fomit-frame-pointer	avx2
g++ -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx2
g++ -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=corei7-avx -O -fomit-frame-pointer	avx2
g++ -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx2
g++ -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	avx2
g++ -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	avx2
g++ -m64 -march=native -mtune=native -O -fomit-frame-pointer	avx2
g++ -m64 -march=native -mtune=native -Os -fomit-frame-pointer	avx2
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx2
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx2
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx2
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx2