Implementation notes: x86, h2atom, crypto_stream/cryptmtv3

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_stream
Primitive: cryptmtv3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
13620	`e/v3`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161027	20161009
13740	`e/v3`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161027	20161009
14020	`e/v3`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161027	20161009
14040	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161027	20161009
14040	`e/v3`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161027	20161009
14040	`e/v3`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20161027	20161009
14040	`e/v3`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161027	20161009
14050	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161027	20161009
14070	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161027	20161009
14160	`e/v3`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161027	20161009
14300	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161027	20161009
14440	`e/v3`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161027	20161009
14710	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161027	20161009
14790	`e/v3`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161027	20161009
14790	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161027	20161009
14790	`e/v3`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161027	20161009
14820	`e/v3`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161027	20161009
14880	`e/v3`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161027	20161009
14890	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161027	20161009
14890	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161027	20161009
14950	`e/v3`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161027	20161009
15050	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161027	20161009
15070	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161027	20161009
15080	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161027	20161009
15120	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161027	20161009
15150	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161027	20161009
15150	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161027	20161009
15170	`e/v3`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161027	20161009
15230	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161027	20161009
15230	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161027	20161009
15270	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161027	20161009
15270	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161027	20161009
15360	`e/v3`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161027	20161009
15480	`e/v3`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161027	20161009
15500	`e/v3`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161027	20161009
15530	`e/v3`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161027	20161009
15540	`e/v3`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161027	20161009
15650	`e/v3`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161027	20161009
15650	`e/v3`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161027	20161009
15650	`e/v3`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161027	20161009
15680	`e/v3`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161027	20161009
15690	`e/v3`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161027	20161009
15690	`e/v3`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161027	20161009
15710	`e/v3`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161027	20161009
15710	`e/v3`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161027	20161009
15720	`e/v3`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161027	20161009
15740	`e/v3`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161027	20161009
15740	`e/v3`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161027	20161009
15770	`e/v3`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161027	20161009
15780	`e/v3`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161027	20161009
15780	`e/v3`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161027	20161009
15810	`e/v3`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161027	20161009
15830	`e/v3`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161027	20161009
15900	`e/v3`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161027	20161009
15910	`e/v3`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161027	20161009
15920	`e/v3`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161027	20161009
15920	`e/v3`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161027	20161009
15920	`e/v3`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161027	20161009
16010	`e/v3`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161027	20161009
16090	`e/v3`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161027	20161009
16540	`e/v3`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161027	20161009
17100	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161027	20161009
19230	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161027	20161009
20350	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161027	20161009
20360	`e/v3`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161027	20161009
29910	`e/v3`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161027	20161009
29940	`e/v3`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161027	20161009
29950	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161027	20161009
29950	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161027	20161009
29950	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161027	20161009
29950	`e/v3`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161027	20161009
30040	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161027	20161009
30050	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161027	20161009
30190	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161027	20161009
30190	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161027	20161009
30190	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161027	20161009
30280	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161027	20161009
30280	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161027	20161009
30420	`e/v3`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161027	20161009
30600	`e/v3`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161027	20161009
30600	`e/v3`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161027	20161009
30830	`e/v3`	`gcc -m32 -O3 -fomit-frame-pointer`	20161027	20161009
30840	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161027	20161009
30840	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161027	20161009
30920	`e/v3`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161027	20161009
30960	`e/v3`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161027	20161009
30960	`e/v3`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161027	20161009
31040	`e/v3`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161027	20161009
31040	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161027	20161009
31040	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161027	20161009
31060	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161027	20161009
31360	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161027	20161009
32110	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161027	20161009
32150	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161027	20161009
32160	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161027	20161009
32160	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161027	20161009
32160	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161027	20161009
32210	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161027	20161009
32220	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161027	20161009
32220	`e/v3`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161027	20161009
32280	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161027	20161009
32290	`e/v3`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161027	20161009
32500	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161027	20161009
32500	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161027	20161009
32500	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161027	20161009
32500	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161027	20161009
32520	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161027	20161009
32830	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161027	20161009
37030	`e/v3`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161027	20161009
37030	`e/v3`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161027	20161009
37040	`e/v3`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161027	20161009
37390	`e/v3`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161027	20161009
37390	`e/v3`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161027	20161009
37440	`e/v3`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161027	20161009
37670	`e/v3`	`gcc -m32 -O2 -fomit-frame-pointer`	20161027	20161009
37890	`e/v3`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161027	20161009
37890	`e/v3`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161027	20161009
37940	`e/v3`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161027	20161009
37940	`e/v3`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161027	20161009
37940	`e/v3`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161027	20161009
38010	`e/v3`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161027	20161009
38020	`e/v3`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161027	20161009
38150	`e/v3`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161027	20161009
38150	`e/v3`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161027	20161009
38380	`e/v3`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161027	20161009
38460	`e/v3`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161027	20161009
39220	`e/v3`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161027	20161009
39230	`e/v3`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161027	20161009
39230	`e/v3`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161027	20161009
39300	`e/v3`	`gcc -m32 -Os -fomit-frame-pointer`	20161027	20161009
39300	`e/v3`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161027	20161009
39350	`e/v3`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161027	20161009
39370	`e/v3`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161027	20161009
39410	`e/v3`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161027	20161009
39410	`e/v3`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161027	20161009
40430	`e/v3`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161027	20161009
40520	`e/v3`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161027	20161009
40540	`e/v3`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161027	20161009
40560	`e/v3`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161027	20161009
40620	`e/v3`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161027	20161009
40620	`e/v3`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161027	20161009
40880	`e/v3`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161027	20161009
40880	`e/v3`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161027	20161009
40890	`e/v3`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161027	20161009
40910	`e/v3`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161027	20161009
40910	`e/v3`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161027	20161009
41290	`e/v3`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161027	20161009
41410	`e/v3`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161027	20161009
41410	`e/v3`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161027	20161009
41510	`e/v3`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161027	20161009
41530	`e/v3`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161027	20161009
42480	`e/v3`	`gcc -m32 -O -fomit-frame-pointer`	20161027	20161009
47330	`e/v3`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161027	20161009

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 /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
cryptmt-v3.c: from /home/djb/supercop-20161009/supercop-data/h2atom/x86/include/ecrypt-config.h:296,
cryptmt-v3.c: from e/cryptmt-v3.c:9,
cryptmt-v3.c: from cryptmt-v3.c:1:
cryptmt-v3.c: e/sse2.c: In function '_mm_recursion':
cryptmt-v3.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
cryptmt-v3.c: _mm_xor_si128 (__m128i __A, __m128i __B)
cryptmt-v3.c: ^
cryptmt-v3.c: In file included from e/cryptmt-v3.c:66:0,
cryptmt-v3.c: from cryptmt-v3.c:1:
cryptmt-v3.c: e/sse2.c:39:7: error: called from here
cryptmt-v3.c: c = _mm_xor_si128(c, a);
cryptmt-v3.c: ^
cryptmt-v3.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
cryptmt-v3.c: from /home/djb/supercop-20161009/supercop-data/h2atom/x86/include/ecrypt-config.h:296,
cryptmt-v3.c: from e/cryptmt-v3.c:9,
cryptmt-v3.c: from cryptmt-v3.c:1:
cryptmt-v3.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
cryptmt-v3.c: _mm_xor_si128 (__m128i __A, __m128i __B)
cryptmt-v3.c: ^
cryptmt-v3.c: In file included from e/cryptmt-v3.c:66:0,
cryptmt-v3.c: from cryptmt-v3.c:1:
cryptmt-v3.c: e/sse2.c:38:7: error: called from here
cryptmt-v3.c: c = _mm_xor_si128(c, b);
cryptmt-v3.c: ^
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