Implementation notes: amd64, h3neo, crypto_aead/minalpherv11

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240107
Operation: crypto_aead
Primitive: minalpherv11

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
5096420	9921 0 0	24827 844 1024	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231219	20231212
5107249	10969 0 0	26779 844 1024	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231219	20231212
5142804	12607 0 0	29011 844 1024	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231219	20231212
5900549	12479 0 0	29631 812 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231212
6883922	5015 0 0	18399 844 1024	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231219	20231212
7723156	8823 0 0	24631 812 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231212
7756966	5642 0 0	19595 844 1024	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231219	20231212
9368649	5669 0 0	19346 788 1056	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231212
11071691	6789 0 0	21620 796 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231212

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

MinalpherCore.cpp: MinalpherCore.cpp:42:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: { _mm256_set_epi32(0x0000000, 0x03020100, 0x00000000, 0x0000000, 0x0000000, 0x02030001, 0x0000000, 0x0000000),
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:43:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: _mm256_set_epi32(0x0000000, 0x01000302, 0x00000000, 0x0000000, 0x0000000, 0x00010203, 0x0000000, 0x0000000)},
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:44:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: { _mm256_set_epi32(0x0000000, 0x02030001, 0x00000000, 0x0000000, 0x0000000, 0x03020100, 0x0000000, 0x0000000),
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:45:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: _mm256_set_epi32(0x0000000, 0x00010203, 0x00000000, 0x0000000, 0x0000000, 0x01000302, 0x0000000, 0x0000000)},
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:46:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: { _mm256_set_epi32(0x0000000, 0x01000302, 0x00000000, 0x0000000, 0x0000000, 0x00010203, 0x0000000, 0x0000000),
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:47:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: _mm256_set_epi32(0x0000000, 0x03020100, 0x00000000, 0x0000000, 0x0000000, 0x02030001, 0x0000000, 0x0000000)},
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:48:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: { _mm256_set_epi32(0x0000000, 0x00010203, 0x00000000, 0x0000000, 0x0000000, 0x01000302, 0x0000000, 0x0000000),
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:49:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: _mm256_set_epi32(0x0000000, 0x02030001, 0x00000000, 0x0000000, 0x0000000, 0x03020100, 0x0000000, 0x0000000)},
MinalpherCore.cpp: ^
MinalpherCore.cpp: MinalpherCore.cpp:50:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
MinalpherCore.cpp: ...

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

Compiler	Implementations
clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang++ -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang++ -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

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: 85 | 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/11/include/immintrin.h:43,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h: In function 'void __static_initialization_and_destruction_0(int, int)':
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1285:1: 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: 1285 | _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: 705 | 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/11/include/immintrin.h:43,
MinalpherCore.cpp: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
MinalpherCore.cpp: from define.h:47,
MinalpherCore.cpp: from MinalpherCore.cpp:33:
MinalpherCore.cpp: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1285:1: 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: 1285 | _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: 704 | 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++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2