Implementation notes: amd64, hydra1, crypto_aead/minalpherv11

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: minalpherv11

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
5044309	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
5046397	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
5056434	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
5109899	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
5113619	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
5171876	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
5191391	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
5544696	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
5562856	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
5562968	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
5564221	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
5580552	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
5632221	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
5650923	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
6795178	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
6807288	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
6817675	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
6831271	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
6910664	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
6913333	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
6915168	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
7024090	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
7050709	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
7087523	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
7101196	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
7101219	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
7131230	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
7148120	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
7148353	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
7148797	`ref`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
7148814	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
7174464	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
7200228	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
7216593	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
7221380	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
7232236	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
7246253	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
7246496	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
8399733	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
8523392	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
8552780	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
8665605	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
8668336	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
8684275	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
8826691	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
8891092	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
8967986	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
8980888	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
9014220	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
9021298	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
9043893	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
9045648	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
9075647	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
9080331	`ref`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
9187192	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
9391535	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
9393056	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161020	20161009
9398896	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161020	20161009
9408355	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
9415355	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
9420685	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161020	20161009
9436976	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
9449003	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161020	20161009
9461151	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
9506874	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
9542624	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
9607774	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
9621193	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
9892448	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
9981118	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
10067314	`ref`	`gcc -O -fomit-frame-pointer`	20161020	20161009
10083667	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
10085333	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
10199750	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
10205208	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
10233576	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161020	20161009
10237336	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
10253312	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
10253612	`ref`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
10257024	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
10274420	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
10294741	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
10330206	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
10350622	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
10389374	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
10404986	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161020	20161009
10410618	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161020	20161009
10412184	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
10412399	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
10423450	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
10425608	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
10469037	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161020	20161009
10627437	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
10643906	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161020	20161009
10662503	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161020	20161009
10713686	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161020	20161009
10761885	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161020	20161009
11257168	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
45065018	`ref`	`cc`	20161020	20161009
45081443	`ref`	`gcc -funroll-loops`	20161020	20161009
45107166	`ref`	`gcc`	20161020	20161009

Test failure

Implementation: crypto_aead/minalpherv11/ref
Compiler: gcc -m64 -march=core2 -O3 -fomit-frame-pointer

error 111

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

Compiler	Implementations
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/minalpherv11/avx2
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_setzero_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/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
MinalpherCore.cpp: (__v4di)_mm256_setzero_si256(), \
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:92:10: error: always_inline function '_mm256_and_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: tmp0 = _mm256_and_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:93:10: error: always_inline function '_mm256_andnot_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: tmp1 = _mm256_andnot_si256(ymmMask, tmp);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:96:10: error: always_inline function '_mm256_srli_epi16' 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: tmp1 = _mm256_srli_epi16(tmp1, 4);
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:99:18: error: always_inline function '_mm256_unpacklo_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: __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 'sse4.2', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'sse4.2'
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: crypto_aead/minalpherv11/avx2
Compiler: clang++ -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

MinalpherCore.cpp: MinalpherCore.cpp:85:27: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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_setzero_si256' requires target feature 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
MinalpherCore.cpp: __m256i tmp = _mm256_permute4x64_epi64(DATA, 0xD8);
MinalpherCore.cpp: ^
MinalpherCore.cpp: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
MinalpherCore.cpp: (__v4di)_mm256_setzero_si256(), \
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:92:10: error: always_inline function '_mm256_and_si256' requires target feature 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'minalpher_core_single_block' that is compiled without support for 'xsave'
MinalpherCore.cpp: ...

Number of similar (compiler,implementation) pairs: 2, namely:

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

Compiler output

Implementation: crypto_aead/minalpherv11/avx2
Compiler: g++

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

Compiler	Implementations
g++	avx2

Compiler output

Implementation: crypto_aead/minalpherv11/avx2
Compiler: g++ -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 57, 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 -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 -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 -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=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++ -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=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
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: crypto_aead/minalpherv11/avx2
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/5/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h: In function 'void __static_initialization_and_destruction_0(int, int)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1252:1: 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: error: 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/5/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1252:1: 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: error: 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/5/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h: In function 'void __static_initialization_and_destruction_0(int, int)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1252:1: 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: error: 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/5/include/immintrin.h:41:0,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1252:1: 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: error: 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