Implementation notes: x86, margaux, crypto_stream/cryptmtv3

Computer: margaux
Architecture: x86
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20171218
Operation: crypto_stream
Primitive: cryptmtv3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
8028	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20170908	20170904
8055	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170908	20170904
8118	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170908	20170904
8127	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20170908	20170904
8181	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20170908	20170904
8280	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170908	20170904
8289	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20170908	20170904
8316	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20170908	20170904
8343	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20170908	20170904
8469	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20170908	20170904
8487	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20170908	20170904
8532	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20170908	20170904
8613	`e/v3`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20170908	20170904
8685	`e/v3`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170908	20170904
8748	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170908	20170904
8748	`e/v3`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20170908	20170904
8757	`e/v3`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20170908	20170904
8757	`e/v3`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170908	20170904
8766	`e/v3`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170908	20170904
8775	`e/v3`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20170908	20170904
8793	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20170908	20170904
8802	`e/v3`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20170908	20170904
8802	`e/v3`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20170908	20170904
8811	`e/v3`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20170908	20170904
8820	`e/v3`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20170908	20170904
8829	`e/v3`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20170908	20170904
8838	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170908	20170904
8847	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20170908	20170904
8847	`e/v3`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170908	20170904
8865	`e/v3`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20170908	20170904
8874	`e/v3`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20170908	20170904
8928	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170908	20170904
8937	`e/v3`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170908	20170904
8982	`e/v3`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20170908	20170904
9027	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170908	20170904
9036	`e/v3`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20170908	20170904
9054	`e/v3`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170908	20170904
9054	`e/v3`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20170908	20170904
9063	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170908	20170904
9090	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20170908	20170904
9117	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20170908	20170904
9135	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170908	20170904
9162	`e/v3`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20170908	20170904
9207	`e/v3`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20170908	20170904
9234	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20170908	20170904
9252	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170908	20170904
9252	`e/v3`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170908	20170904
9261	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20170908	20170904
9261	`e/v3`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20170908	20170904
9288	`e/v3`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20170908	20170904
9351	`e/v3`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170908	20170904
9504	`e/v3`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20170908	20170904
9504	`e/v3`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20170908	20170904
9504	`e/v3`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20170908	20170904
9522	`e/v3`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20170908	20170904
9531	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170908	20170904
9531	`e/v3`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170908	20170904
9567	`e/v3`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20170908	20170904
9576	`e/v3`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170908	20170904
9594	`e/v3`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170908	20170904
9810	`e/v3`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170908	20170904
12114	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20170908	20170904
12204	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20170908	20170904
12294	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170908	20170904
12303	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20170908	20170904
12312	`e/v3`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20170908	20170904
12357	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20170908	20170904
12420	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170908	20170904
12456	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20170908	20170904
12582	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20170908	20170904
12582	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20170908	20170904
12663	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20170908	20170904
13680	`e/v3`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20170908	20170904
13842	`e/v3`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20170908	20170904
13905	`e/v3`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170908	20170904
13932	`e/v3`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20170908	20170904
14544	`e/v3`	`gcc -m32 -O -fomit-frame-pointer`	20170908	20170904
14679	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170908	20170904
14679	`e/v3`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170908	20170904
14733	`e/v3`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170908	20170904
14769	`e/v3`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170908	20170904
14778	`e/v3`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170908	20170904
14787	`e/v3`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20170908	20170904
14796	`e/v3`	`gcc -m32 -O3 -fomit-frame-pointer`	20170908	20170904
14796	`e/v3`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20170908	20170904
14814	`e/v3`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20170908	20170904
14823	`e/v3`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20170908	20170904
14823	`e/v3`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20170908	20170904
14850	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20170908	20170904
14850	`e/v3`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170908	20170904
14859	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170908	20170904
14868	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20170908	20170904
14877	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20170908	20170904
14886	`e/v3`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20170908	20170904
14886	`e/v3`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20170908	20170904
14913	`e/v3`	`gcc -m32 -O2 -fomit-frame-pointer`	20170908	20170904
14922	`e/v3`	`gcc -m32 -Os -fomit-frame-pointer`	20170908	20170904
14922	`e/v3`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20170908	20170904
14931	`e/v3`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20170908	20170904
14967	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20170908	20170904
14994	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170908	20170904
15003	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170908	20170904
15003	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170908	20170904
15057	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20170908	20170904
15075	`e/v3`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170908	20170904
15138	`e/v3`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20170908	20170904
15138	`e/v3`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20170908	20170904
15201	`e/v3`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20170908	20170904
15201	`e/v3`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170908	20170904
15228	`e/v3`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170908	20170904
15336	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20170908	20170904
15390	`e/v3`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20170908	20170904
15462	`e/v3`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170908	20170904
15471	`e/v3`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170908	20170904
15480	`e/v3`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170908	20170904
15507	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20170908	20170904
15543	`e/v3`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20170908	20170904
15606	`e/v3`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170908	20170904
15660	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170908	20170904
15660	`e/v3`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170908	20170904
15678	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20170908	20170904
15687	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170908	20170904
15687	`e/v3`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20170908	20170904
15696	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170908	20170904
15696	`e/v3`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20170908	20170904
15795	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20170908	20170904
15795	`e/v3`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20170908	20170904
15840	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170908	20170904
15849	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20170908	20170904
15867	`e/v3`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20170908	20170904
15867	`e/v3`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170908	20170904
15867	`e/v3`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170908	20170904
15885	`e/v3`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170908	20170904
15894	`e/v3`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20170908	20170904
15966	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170908	20170904
16029	`e/v3`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20170908	20170904
16146	`e/v3`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20170908	20170904
16236	`e/v3`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20170908	20170904
16398	`e/v3`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20170908	20170904
16749	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170908	20170904
16803	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20170908	20170904
16830	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20170908	20170904
16830	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170908	20170904
16839	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170908	20170904
16866	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170908	20170904
16893	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170908	20170904
17073	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20170908	20170904
17091	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20170908	20170904
17181	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20170908	20170904

Test failure

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 9, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	e/v3
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	e/v3
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	e/v3
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	e/v3
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	e/v3
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	e/v3
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	e/v3
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	e/v3
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	e/v3

Compiler output

Implementation: crypto_stream/cryptmtv3/e/v3
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

cryptmt-v3.c: In file included from e/sse2.c:5:0,
cryptmt-v3.c: from e/cryptmt-v3.c:66,
cryptmt-v3.c: from cryptmt-v3.c:2:
cryptmt-v3.c: /usr/lib/gcc/x86_64-linux-gnu/4.8/include/emmintrin.h:31:3: error: #error "SSE2 instruction set not enabled"
cryptmt-v3.c: # error "SSE2 instruction set not enabled"
cryptmt-v3.c: ^
cryptmt-v3.c: In file included from e/cryptmt-v3.c:66:0,
cryptmt-v3.c: from cryptmt-v3.c:2:
cryptmt-v3.c: e/sse2.c:15:1: error: unknown type name '__m128i'
cryptmt-v3.c: static INLINE __m128i _mm_recursion(const __m128i *x, const __m128i *y,
cryptmt-v3.c: ^
cryptmt-v3.c: e/sse2.c:15:1: error: unknown type name '__m128i'
cryptmt-v3.c: e/sse2.c:15:1: error: unknown type name '__m128i'
cryptmt-v3.c: e/sse2.c:16:9: error: unknown type name '__m128i'
cryptmt-v3.c: __m128i z, const __m128i mask);
cryptmt-v3.c: ^
cryptmt-v3.c: e/sse2.c:16:9: error: unknown type name '__m128i'
cryptmt-v3.c: e/sse2.c:18:39: error: unknown type name '__m128i'
cryptmt-v3.c: static INLINE void _mm_filter_16bytes(__m128i *sfmt, __m128i *p_accum,
cryptmt-v3.c: ^
cryptmt-v3.c: e/sse2.c:18:54: error: unknown type name '__m128i'
cryptmt-v3.c: static INLINE void _mm_filter_16bytes(__m128i *sfmt, __m128i *p_accum,
cryptmt-v3.c: ^
cryptmt-v3.c: e/sse2.c:21:34: error: unknown type name '__m128i'
cryptmt-v3.c: static INLINE void _mm_booter_am(__m128i *acc, __m128i *pos1, __m128i *pos2,
cryptmt-v3.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	e/v3
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	e/v3
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	e/v3
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	e/v3
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	e/v3
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	e/v3
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	e/v3
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	e/v3