Implementation notes: amd64, speed2supercop, crypto_hash/bmw256

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240425
Operation: crypto_hash
Primitive: bmw256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
11712	11490 0 0	20392 728 768	`T:optbbe`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
11736	38653 0 0	47552 728 768	`T:optc01`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12068	11485 0 0	20376 728 768	`T:optabe`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12104	12027 0 0	21964 744 800	`T:optabe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12216	12158 0 0	22092 744 800	`T:optbbe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12312	43825 0 0	54213 752 800	`T:optc01`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12336	43793 0 0	56061 752 800	`T:optc01`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12372	40943 0 0	50957 752 800	`T:optc01`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12640	18906 0 0	28917 752 800	`T:optc02`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12660	19881 0 0	30269 752 800	`T:optc02`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12660	12872 0 0	22861 752 800	`T:optc03`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12744	19881 0 0	32149 752 800	`T:optc02`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
12916	12767 0 0	22765 752 800	`T:optc04`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
13296	15590 0 0	25749 752 800	`T:sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
13876	6647 0 0	16492 744 800	`T:optbgbe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
13908	15150 0 0	24088 728 768	`T:optc02`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
14656	12559 0 0	22709 752 800	`T:sphlib-small`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
22756	14073 0 0	26389 752 800	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
23036	12793 0 0	23229 752 800	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
23148	11355 0 0	21421 752 800	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425
34692	10186 0 0	19144 728 768	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240426	20240425

Checksum failure

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

80b9b7112d1d2b8ae15902ed31e97e4fe46f40d2f2026b50abc6025b936713bc

Number of similar (compiler,implementation) pairs: 3, namely:

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

Checksum failure

Implementation: T:sphlib
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

c79502110cadeddc766ccd862f784ba8f7dc7c9ce54fe5f1db1b45e2a9a10c43

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib T:sphlib-small

Test failure

Implementation: T:amd_k8/x86-64/noSSE
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 111

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_65nm/x86-64/ssse3_v1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_65nm/x86-64/ssse3_v1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_65nm/x86-64/ssse3_v1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_2_65nm/x86-64/ssse3_v1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_i7_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_i7_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_i7_45nm/x86-64/sse4_v1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:core_i7_45nm/x86-64/sse4_v1

Test failure

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

error 111
crypto_hash is nondeterministic

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optabe
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optabe
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optbbe
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optbbe
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc03
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc03
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc03
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc04
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc04
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc04
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib-small
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib-small

Compiler output

Implementation: T:amd_k8/x86-64/noSSE
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

try.c: /usr/bin/ld: libcrypto_hash_bmw256.a(Compress256_icc.o): warning: relocation in read-only section `.eh_frame'
try.c: /usr/bin/ld: warning: creating DT_TEXTREL in a PIE

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:amd_k8/x86-64/noSSE

Compiler output

Implementation: T:optc31ssse3
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

Compress256_sse_31.c: Compress256_sse_31.c: In function 'Compress256':
Compress256_sse_31.c: Compress256_sse_31.c:374:26: warning: passing argument 1 of '_mm_storeu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
Compress256_sse_31.c: 374 | _mm_storeu_si128(&p256[00], copyTemp);
Compress256_sse_31.c: | ^~~~~~~~~
Compress256_sse_31.c: | |
Compress256_sse_31.c: | u_int32_t * {aka unsigned int *}
Compress256_sse_31.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/12/include/pmmintrin.h:31,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-linux-gnu/12/include/tmmintrin.h:31,
Compress256_sse_31.c: from Compress256_sse_31.c:12:
Compress256_sse_31.c: /usr/lib/gcc/x86_64-linux-gnu/12/include/emmintrin.h:737:30: note: expected '__m128i_u *' but argument is of type 'u_int32_t *' {aka 'unsigned int *'}
Compress256_sse_31.c: 737 | _mm_storeu_si128 (__m128i_u *__P, __m128i __B)
Compress256_sse_31.c: | ~~~~~~~~~~~^~~
Compress256_sse_31.c: Compress256_sse_31.c:377:36: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
Compress256_sse_31.c: 377 | copyTemp = _mm_loadu_si128(&hashState256(state)->DoublePipe[ 4]);
Compress256_sse_31.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Compress256_sse_31.c: | |
Compress256_sse_31.c: | u_int32_t * {aka unsigned int *}
Compress256_sse_31.c: /usr/lib/gcc/x86_64-linux-gnu/12/include/emmintrin.h:701:35: note: expected 'const __m128i_u *' but argument is of type 'u_int32_t *' {aka 'unsigned int *'}
Compress256_sse_31.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
Compress256_sse_31.c: | ~~~~~~~~~~~~~~~~~^~~
Compress256_sse_31.c: Compress256_sse_31.c:378:26: warning: passing argument 1 of '_mm_storeu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
Compress256_sse_31.c: 378 | _mm_storeu_si128(&p256[04], copyTemp);
Compress256_sse_31.c: | ^~~~~~~~~
Compress256_sse_31.c: | |
Compress256_sse_31.c: | u_int32_t * {aka unsigned int *}
Compress256_sse_31.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc31ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc31ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc31ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:optc31ssse3