Implementation notes: amd64, temp, crypto_hash/bmw256

Computer: temp
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20191017
Operation: crypto_hash
Primitive: bmw256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6169	5211 0 0	13909 760 744	`core_2_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6293	5237 0 0	14749 784 776	`core_i7_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6324	6117 0 0	15893 784 776	`opt31ssse3_asm64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6386	6112 0 0	15717 784 776	`opt31ssse3_asm64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6572	5961 0 0	18477 784 808	`optc31ssse3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6665	5937 0 0	15509 784 776	`optc31ssse3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6820	5787 0 0	14485 760 744	`core_2_65nm/x86-64/ssse3_v1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6913	5744 0 0	15365 784 776	`amd_k10/x86-64/sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6944	5638 0 0	14397 760 744	`amd_k10/x86-64/sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6975	5759 0 0	15541 784 776	`amd_k10/x86-64/sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
6975	5935 0 0	15717 784 776	`opt29_v5_ssse3_asm64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
7595	11555 0 0	21053 784 776	`optbbe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
7843	37164 0 0	45829 760 744	`optc01`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
7967	14779 0 0	24189 784 776	`optbgbe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
7967	12924 0 0	22494 792 776	`optc04`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8060	6973 0 0	16501 784 776	`amd_k8/x86-64/noSSE`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8122	6988 0 0	19445 784 808	`amd_k8/x86-64/noSSE`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8122	18780 0 0	28366 792 776	`optc02`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8184	12792 0 0	22453 784 776	`optbbe`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8184	41079 0 0	50846 792 776	`optc01`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8215	12622 0 0	22293 784 776	`optabe`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8277	5317 0 0	14909 784 776	`core_2_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8308	11741 0 0	20389 760 744	`optabe`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8339	11812 0 0	20469 760 744	`optbbe`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8339	6377 0 0	15005 760 744	`optbgbe`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8370	5332 0 0	17805 784 808	`core_2_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8370	15054 0 0	24830 792 776	`sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8494	5131 0 0	13813 760 744	`core_i7_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8525	5252 0 0	17693 784 808	`core_i7_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8618	6004 0 0	14741 760 744	`opt31ssse3_asm64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8618	13183 0 0	22934 792 776	`optc03`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8804	13781 0 0	26197 784 808	`optbbe`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8866	13311 0 0	23062 792 776	`optc04`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
8990	20172 0 0	32686 792 808	`optc02`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9145	5332 0 0	15053 784 776	`core_2_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9207	5893 0 0	15485 784 776	`core_2_65nm/x86-64/ssse3_v1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9207	5934 0 0	15701 784 776	`optc31ssse3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9269	13724 0 0	26149 784 808	`optabe`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9393	5759 0 0	18293 784 808	`amd_k10/x86-64/sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9424	5252 0 0	14941 784 776	`core_i7_45nm/x86-64/sse4_v1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9486	5920 0 0	15525 784 776	`opt29_v5_ssse3_asm64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9486	5814 0 0	14557 760 744	`opt29_v5_ssse3_asm64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
9827	12868 0 0	22638 792 776	`sphlib-small`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10013	15263 0 0	23973 760 744	`optc02`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10168	16479 0 0	29190 792 808	`sphlib-small`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10354	5908 0 0	18381 784 808	`core_2_65nm/x86-64/ssse3_v1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10385	5908 0 0	15629 784 776	`core_2_65nm/x86-64/ssse3_v1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10447	16196 0 0	28005 784 808	`optbgbe`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10447	11235 0 0	19933 760 744	`optc03`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10788	6133 0 0	18669 784 808	`opt31ssse3_asm64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
10819	12837 0 0	22398 792 776	`optc03`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11005	6988 0 0	16693 784 776	`amd_k8/x86-64/noSSE`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11036	39914 0 0	49502 792 776	`optc01`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11067	6486 0 0	15253 760 744	`optc31ssse3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11284	42009 0 0	54534 792 808	`optc01`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11470	11397 0 0	20893 784 776	`optabe`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11718	15368 0 0	24949 784 776	`optbgbe`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
11718	15702 0 0	25670 792 776	`sphlib`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
12090	5935 0 0	18469 784 808	`opt29_v5_ssse3_asm64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
12152	6867 0 0	15565 760 744	`amd_k8/x86-64/noSSE`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
12493	18255 0 0	30966 792 808	`sphlib`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
13237	13455 0 0	25958 792 808	`optc04`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
13671	14251 0 0	23149 760 744	`sphlib`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
13702	19972 0 0	29742 792 776	`optc02`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
14880	10874 0 0	20534 792 776	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
15066	13311 0 0	25814 792 808	`optc03`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
15221	10775 0 0	20630 792 776	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
15283	11789 0 0	20685 760 744	`sphlib-small`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
15624	11384 0 0	20077 760 744	`optc04`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
16213	13878 0 0	23846 792 776	`sphlib-small`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
20460	12068 0 0	24662 792 808	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017
23188	9697 0 0	18429 760 744	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191219	20191017

Compiler output

Implementation: opt31ssse3_asm64
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

wrapper.c: wrapper.c:37:0: warning: "crypto_hash_BYTES" redefined [enabled by default]
wrapper.c: #define crypto_hash_BYTES 32
wrapper.c: ^
wrapper.c: In file included from wrapper.c:20:0:
wrapper.c: crypto_hash.h:7:0: note: this is the location of the previous definition
wrapper.c: #define crypto_hash_BYTES crypto_hash_bmw256_BYTES
wrapper.c: ^
wrapper.c: wrapper.c: In function 'crypto_hash_bmw256_opt31ssse3_asm64':
wrapper.c: wrapper.c:238:2: warning: passing argument 3 of 'Compress256' from incompatible pointer type [enabled by default]
wrapper.c: Compress256(data32, data32 +16, CONST32final-4); // TODO: This is a HACK...
wrapper.c: ^
wrapper.c: wrapper.c:39:8: note: expected 'struct hashState *' but argument is of type 'u_int32_t *'
wrapper.c: extern Compress256(u_int32_t *data32, u_int32_t *data32_end, hashState *state);
wrapper.c: ^

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	opt31ssse3_asm64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	opt31ssse3_asm64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	opt31ssse3_asm64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	opt31ssse3_asm64

Compiler output

Implementation: optc31ssse3
Security model: unknown
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:374:2: warning: passing argument 1 of '_mm_store_si128' from incompatible pointer type [enabled by default]
Compress256_sse_31.c: _mm_store_si128(&p256[00], copyTemp);
Compress256_sse_31.c: ^
Compress256_sse_31.c: In file included from /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/pmmintrin.h:35:0,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/tmmintrin.h:35,
Compress256_sse_31.c: from Compress256_sse_31.c:12:
Compress256_sse_31.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/emmintrin.h:694:1: note: expected '__vector(2) long long int *' but argument is of type 'u_int32_t *'
Compress256_sse_31.c: _mm_store_si128 (__m128i *__P, __m128i __B)
Compress256_sse_31.c: ^
Compress256_sse_31.c: ...
Compress256_sse_31.c: ^
Compress256_sse_31.c: Compress256_sse_31.c:1568:2: warning: passing argument 1 of '_mm_store_si128' from incompatible pointer type [enabled by default]
Compress256_sse_31.c: _mm_store_si128(&hashState256(state)->DoublePipe[12], copyTemp);
Compress256_sse_31.c: ^
Compress256_sse_31.c: In file included from /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/pmmintrin.h:35:0,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/tmmintrin.h:35,
Compress256_sse_31.c: from Compress256_sse_31.c:12:
Compress256_sse_31.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/emmintrin.h:694:1: note: expected '__vector(2) long long int *' but argument is of type 'u_int32_t *'
Compress256_sse_31.c: _mm_store_si128 (__m128i *__P, __m128i __B)
Compress256_sse_31.c: ^
wrapper.c: wrapper.c:26:0: warning: "crypto_hash_BYTES" redefined [enabled by default]
wrapper.c: #define crypto_hash_BYTES 32
wrapper.c: ^
wrapper.c: In file included from wrapper.c:20:0:
wrapper.c: crypto_hash.h:7:0: note: this is the location of the previous definition
wrapper.c: #define crypto_hash_BYTES crypto_hash_bmw256_BYTES
wrapper.c: ^
wrapper.c: wrapper.c: In function 'crypto_hash_bmw256_optc31ssse3':
wrapper.c: wrapper.c:226:2: warning: passing argument 3 of 'Compress256' from incompatible pointer type [enabled by default]
wrapper.c: Compress256(data32, data32 +16, CONST32final-4); // TODO: This is a HACK...
wrapper.c: ^
wrapper.c: wrapper.c:27:8: note: expected 'struct hashState *' but argument is of type 'u_int32_t *'
wrapper.c: extern Compress256(u_int32_t *data32, u_int32_t *data32_end, hashState *state);
wrapper.c: ^

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

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