Implementation notes: amd64, slide, crypto_hash/bmw256

Computer: slide
Architecture: amd64
CPU ID: GenuineIntel-00040651-bfebfbff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: bmw256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
7620	`amd_k10/x86-64/sse2`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
7884	`core_i7_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
7904	`core_2_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
7912	`core_i7_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
7928	`core_i7_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
7940	`core_2_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
7940	`core_2_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
7952	`core_2_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
8352	`core_2_65nm/x86-64/ssse3_v1`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
8392	`opt29_v5_ssse3_asm64`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
8392	`core_2_65nm/x86-64/ssse3_v1`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
8400	`core_2_65nm/x86-64/ssse3_v1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
8400	`core_2_65nm/x86-64/ssse3_v1`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
8420	`opt29_v5_ssse3_asm64`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
8420	`opt29_v5_ssse3_asm64`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
8428	`opt29_v5_ssse3_asm64`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
8544	`amd_k10/x86-64/sse2`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
8556	`amd_k10/x86-64/sse2`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
8568	`amd_k10/x86-64/sse2`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
8656	`opt31ssse3_asm64`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
8660	`opt31ssse3_asm64`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
8740	`opt31ssse3_asm64`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
8808	`core_i7_45nm/x86-64/sse4_v1`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
8860	`opt31ssse3_asm64`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
9330	`amd_k8/x86-64/noSSE`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
10516	`amd_k8/x86-64/noSSE`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
10516	`amd_k8/x86-64/noSSE`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
10736	`amd_k8/x86-64/noSSE`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
11193	`optabe`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
11684	`optabe`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
11748	`optbbe`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
11820	`optc01`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
11968	`optc01`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
11972	`optbbe`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
12064	`optc01`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12112	`optabe`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
12204	`optabe`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12240	`optc03`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12264	`optc03`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
12288	`optc02`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
12292	`optc04`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
12296	`optbbe`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
12308	`optc03`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
12412	`optc04`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
12424	`optc02`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12428	`optc04`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12452	`optbbe`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
12592	`optc02`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
13008	`sphlib`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
13036	`optbgbe`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
13068	`optbgbe`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
13096	`optc01`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
13100	`sphlib`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
13152	`optbgbe`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
13160	`sphlib`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
13209	`sphlib`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
13712	`optbgbe`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
14260	`optc03`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
14320	`optc04`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
14568	`sphlib-small`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
14720	`sphlib-small`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
14740	`optc02`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
14908	`sphlib-small`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
15292	`sphlib-small`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806
19088	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160906	20160806
19160	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160906	20160806
19188	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160906	20160806
32836	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160906	20160806

Compiler output

Implementation: crypto_hash/bmw256/optc31ssse3
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

Compress256_sse_31.c: Compress256_sse_31.c: In function 'Compress256':
Compress256_sse_31.c: Compress256_sse_31.c:374:18: warning: passing argument 1 of '_mm_store_si128' from incompatible pointer type
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-linux-gnu/4.9/include/pmmintrin.h:31:0,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-linux-gnu/4.9/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/4.9/include/emmintrin.h:704:1: 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:377:28: warning: passing argument 1 of '_mm_load_si128' from incompatible pointer type
Compress256_sse_31.c: copyTemp = _mm_load_si128(&hashState256(state)->gt;DoublePipe[ 4]);
Compress256_sse_31.c: ^
Compress256_sse_31.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.9/include/pmmintrin.h:31:0,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-linux-gnu/4.9/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/4.9/include/emmintrin.h:686:1: note: expected 'const __vector(2) long long int *' but argument is of type 'u_int32_t *'
Compress256_sse_31.c: _mm_load_si128 (__m128i const *__P)
Compress256_sse_31.c: ^
Compress256_sse_31.c: Compress256_sse_31.c:378:18: warning: passing argument 1 of '_mm_store_si128' from incompatible pointer type
Compress256_sse_31.c: _mm_store_si128(&p256[04], copyTemp);
Compress256_sse_31.c: ^
Compress256_sse_31.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/4.9/include/pmmintrin.h:31:0,
Compress256_sse_31.c: from /usr/lib/gcc/x86_64-linux-gnu/4.9/include/tmmintrin.h:31,
Compress256_sse_31.c: from Compress256_sse_31.c:12:
Compress256_sse_31.c: ...

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

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

Compiler output

Implementation: crypto_hash/bmw256/opt31ssse3_asm64
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

wrapper.c: wrapper.c:37:0: warning: "crypto_hash_BYTES" redefined
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:238:34: warning: passing argument 3 of 'Compress256' from incompatible pointer type
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	opt31ssse3_asm64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	opt31ssse3_asm64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	opt31ssse3_asm64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	opt31ssse3_asm64