Implementation notes: x86, latour, crypto_stream/cryptmtv3

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

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
7911	`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
8136	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170908	20170904
8172	`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
8181	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170908	20170904
8298	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20170908	20170904
8316	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20170908	20170904
8451	`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
8532	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20170908	20170904
8541	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20170908	20170904
8568	`e/v3`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20170908	20170904
8676	`e/v3`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20170908	20170904
8676	`e/v3`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20170908	20170904
8694	`e/v3`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20170908	20170904
8730	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170908	20170904
8757	`e/v3`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20170908	20170904
8766	`e/v3`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20170908	20170904
8766	`e/v3`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170908	20170904
8802	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170908	20170904
8811	`e/v3`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20170908	20170904
8820	`e/v3`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20170908	20170904
8820	`e/v3`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20170908	20170904
8829	`e/v3`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20170908	20170904
8856	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20170908	20170904
8856	`e/v3`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170908	20170904
8865	`e/v3`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20170908	20170904
8865	`e/v3`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20170908	20170904
8883	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20170908	20170904
8892	`e/v3`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20170908	20170904
8892	`e/v3`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20170908	20170904
8901	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20170908	20170904
8910	`e/v3`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20170908	20170904
8946	`e/v3`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20170908	20170904
9018	`e/v3`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20170908	20170904
9036	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20170908	20170904
9036	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170908	20170904
9036	`e/v3`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20170908	20170904
9036	`e/v3`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20170908	20170904
9054	`e/v3`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170908	20170904
9063	`e/v3`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20170908	20170904
9072	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20170908	20170904
9081	`e/v3`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20170908	20170904
9099	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20170908	20170904
9117	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20170908	20170904
9180	`e/v3`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20170908	20170904
9234	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170908	20170904
9252	`e/v3`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20170908	20170904
9252	`e/v3`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20170908	20170904
9270	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20170908	20170904
9270	`e/v3`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20170908	20170904
9279	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20170908	20170904
9360	`e/v3`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20170908	20170904
9486	`e/v3`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20170908	20170904
9495	`e/v3`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20170908	20170904
9504	`e/v3`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170908	20170904
9513	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170908	20170904
9513	`e/v3`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20170908	20170904
9531	`e/v3`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20170908	20170904
9531	`e/v3`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170908	20170904
9540	`e/v3`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20170908	20170904
9648	`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
12069	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20170908	20170904
12195	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170908	20170904
12249	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20170908	20170904
12285	`e/v3`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20170908	20170904
12285	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170908	20170904
12339	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20170908	20170904
12402	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20170908	20170904
12411	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20170908	20170904
12645	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20170908	20170904
12672	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20170908	20170904
12699	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20170908	20170904
13716	`e/v3`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20170908	20170904
13860	`e/v3`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20170908	20170904
13959	`e/v3`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20170908	20170904
13977	`e/v3`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20170908	20170904
14643	`e/v3`	`gcc -m32 -O -fomit-frame-pointer`	20170908	20170904
14688	`e/v3`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20170908	20170904
14724	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170908	20170904
14751	`e/v3`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170908	20170904
14760	`e/v3`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20170908	20170904
14769	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20170908	20170904
14769	`e/v3`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170908	20170904
14778	`e/v3`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20170908	20170904
14778	`e/v3`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170908	20170904
14787	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20170908	20170904
14814	`e/v3`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20170908	20170904
14814	`e/v3`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20170908	20170904
14823	`e/v3`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20170908	20170904
14832	`e/v3`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20170908	20170904
14904	`e/v3`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20170908	20170904
14913	`e/v3`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20170908	20170904
14922	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20170908	20170904
14922	`e/v3`	`gcc -m32 -O2 -fomit-frame-pointer`	20170908	20170904
14922	`e/v3`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20170908	20170904
14931	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20170908	20170904
14940	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20170908	20170904
14940	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20170908	20170904
14949	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20170908	20170904
14949	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170908	20170904
14949	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20170908	20170904
14958	`e/v3`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20170908	20170904
14985	`e/v3`	`gcc -m32 -Os -fomit-frame-pointer`	20170908	20170904
14994	`e/v3`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20170908	20170904
15066	`e/v3`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20170908	20170904
15093	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170908	20170904
15093	`e/v3`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170908	20170904
15102	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20170908	20170904
15129	`e/v3`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20170908	20170904
15201	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20170908	20170904
15201	`e/v3`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170908	20170904
15219	`e/v3`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20170908	20170904
15246	`e/v3`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170908	20170904
15318	`e/v3`	`gcc -m32 -O3 -fomit-frame-pointer`	20170908	20170904
15345	`e/v3`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170908	20170904
15363	`e/v3`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20170908	20170904
15471	`e/v3`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170908	20170904
15489	`e/v3`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20170908	20170904
15561	`e/v3`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20170908	20170904
15561	`e/v3`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20170908	20170904
15579	`e/v3`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170908	20170904
15615	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20170908	20170904
15615	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20170908	20170904
15651	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20170908	20170904
15759	`e/v3`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20170908	20170904
15768	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20170908	20170904
15768	`e/v3`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20170908	20170904
15813	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170908	20170904
15822	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170908	20170904
15894	`e/v3`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20170908	20170904
15921	`e/v3`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20170908	20170904
15984	`e/v3`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20170908	20170904
15993	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20170908	20170904
16002	`e/v3`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170908	20170904
16011	`e/v3`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20170908	20170904
16101	`e/v3`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20170908	20170904
16119	`e/v3`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20170908	20170904
16191	`e/v3`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20170908	20170904
16425	`e/v3`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20170908	20170904
16713	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20170908	20170904
16785	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20170908	20170904
16785	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20170908	20170904
16848	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20170908	20170904
16866	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20170908	20170904
16884	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20170908	20170904
16920	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20170908	20170904
16965	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20170908	20170904
16992	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20170908	20170904
17226	`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