Implementation notes: amd64, h3neo, crypto_hash/bblake256

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240107
Operation: crypto_hash
Primitive: bblake256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
27137	10618 0 0	20896 780 928	`T:bswap`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
27255	10763 0 0	21056 780 928	`T:regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
27506	11204 0 0	24083 844 896	`T:bswap`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
27523	11550 0 0	25101 804 960	`T:bswap`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
27578	11412 0 0	24275 844 896	`T:regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
27627	11710 0 0	25261 804 960	`T:regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
27865	11522 0 0	23725 804 960	`T:bswap`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
27949	11059 0 0	23467 844 896	`T:bswap`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
27949	11682 0 0	23885 804 960	`T:regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
28084	11267 0 0	23691 844 896	`T:regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
28490	10131 0 0	21619 844 896	`T:bswap`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
28539	10115 0 0	20667 844 896	`T:bswap`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
28637	10339 0 0	21843 844 896	`T:regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
28656	10307 0 0	20859 844 896	`T:regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
29203	10432 0 0	20365 836 896	`T:bswap`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
29261	10637 0 0	20557 836 896	`T:regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
29475	10693 0 0	22004 796 960	`T:bswap`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
30961	11354 0 0	22676 796 960	`T:regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
31739	21730 0 0	33851 844 896	`T:sse2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35078	23411 0 0	35059 844 896	`T:sse2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35103	22877 0 0	33635 844 896	`T:sse2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35163	22738 0 0	31933 836 896	`T:sse2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
35192	24709 0 0	38277 804 960	`T:sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
35385	25581 0 0	37805 804 960	`T:sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
35894	24307 0 0	34147 844 896	`T:sse2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
38497	24945 0 0	36276 796 960	`T:sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
41353	22549 0 0	32856 780 928	`T:sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
54998	11405 0 0	21696 780 928	`T:sandy`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
56352	11476 0 0	24339 844 896	`T:sandy`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
56419	12318 0 0	25869 804 960	`T:sandy`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
56682	12290 0 0	24493 804 960	`T:sandy`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
57580	11907 0 0	24331 844 896	`T:sandy`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
58134	10979 0 0	22483 844 896	`T:sandy`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
58137	10963 0 0	21531 844 896	`T:sandy`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
58503	11088 0 0	21005 836 896	`T:sandy`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
65566	11157 0 0	22484 796 960	`T:sandy`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

hash.c: hash.c:184:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: m.u128[0] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 00)), u8to32);
hash.c: ^
hash.c: hash.c:185:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: m.u128[1] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 16)), u8to32);
hash.c: ^
hash.c: hash.c:186:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: m.u128[2] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 32)), u8to32);
hash.c: ^
hash.c: hash.c:187:15: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: m.u128[3] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 48)), u8to32);
hash.c: ^
hash.c: hash.c:201:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: round( 0,m,row1,row2,row3,row4,buf1,buf2);
hash.c: ^
hash.c: hash.c:164:3: note: expanded from macro 'round'
hash.c: down1(r,m,row1,row2,row3,row4,buf1,buf2) \
hash.c: ^
hash.c: hash.c:95:9: note: expanded from macro 'down1'
hash.c: row4 = _mm_shuffle_epi8(row4, r16); \
hash.c: ^
hash.c: hash.c:201:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'blake256_compress' that is compiled without support for 'ssse3'
hash.c: hash.c:165:3: note: expanded from macro 'round'
hash.c: down2(r,m,row1,row2,row3,row4,buf1,buf2) \
hash.c: ^
hash.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ssse3
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ssse3
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ssse3
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ssse3
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ssse3

Compiler output

Implementation: T:ssse3
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from hash.c:3:
hash.c: hash.c: In function 'blake256_compress':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:187:15: note: called from here
hash.c: 187 | m.u128[3] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 48)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:3:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:186:15: note: called from here
hash.c: 186 | m.u128[2] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 32)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:3:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: | ^~~~~~~~~~~~~~~~
hash.c: hash.c:185:15: note: called from here
hash.c: 185 | m.u128[1] = _mm_shuffle_epi8(_mm_loadu_si128((__m128i*)(datablock + 16)), u8to32);
hash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:3:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
hash.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ssse3