Implementation notes: x86, floodyberry, crypto_stream/salsa208

Computer: floodyberry
Architecture: x86
CPU ID: GenuineIntel-00010676-bfebfbff
SUPERCOP version: 20140505
Operation: crypto_stream
Primitive: salsa208

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
3187	`x86_xmm5`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
3200	`x86_xmm5`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
3200	`x86_xmm5`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
3225	`x86_xmm5`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
3225	`x86_xmm5`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
3237	`e/x86-xmm5`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
3250	`x86_xmm5`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
3262	`e/x86-xmm5`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
3263	`e/x86-xmm5`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
3263	`x86_xmm5`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
3275	`e/x86-xmm5`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
3275	`e/x86-xmm5`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
3312	`e/x86-xmm5`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
3662	`e/x86-xmm4`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
3675	`e/x86-xmm4`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
3712	`e/x86-xmm4`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
3725	`e/x86-xmm4`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
3725	`e/x86-xmm4`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
3750	`e/x86-xmm4`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
4537	`e/x86-xmm2`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
4537	`e/x86-xmm2`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
4537	`e/x86-xmm2`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
4538	`e/x86-xmm2`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
4538	`e/x86-xmm2`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
4550	`e/x86-xmm2`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
4888	`e/x86-xmm`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
4912	`e/x86-xmm`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
4950	`e/x86-xmm`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
4950	`e/x86-xmm`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
4963	`e/x86-xmm`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
4988	`e/x86-xmm`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7000	`e/x86-mmx`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7025	`e/x86-mmx`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7025	`e/x86-mmx`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
7025	`e/x86-mmx`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7025	`e/x86-mmx`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7037	`e/x86-mmx`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7087	`e/x86-mmx`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7088	`e/x86-3`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7112	`e/x86-athlon`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7113	`e/x86-3`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7125	`e/x86-pm`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7150	`e/x86-pm`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7150	`e/x86-athlon`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7150	`e/x86-athlon`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7162	`e/x86-2`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7162	`e/x86-3`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7162	`e/x86-3`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7175	`e/x86-3`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7175	`e/x86-2`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
7175	`e/x86-3`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
7175	`e/x86-2`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7188	`e/x86-pm`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7200	`e/x86-2`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7200	`e/x86-pm`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7212	`e/x86-pm`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
7212	`e/x86-pm`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7213	`e/x86-2`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7213	`e/x86-2`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7225	`e/x86-1`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
7225	`e/x86-athlon`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7237	`e/x86-1`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
7237	`e/x86-1`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
7250	`e/x86-1`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7250	`e/x86-1`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
7262	`e/x86-1`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
7263	`e/x86-2`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7263	`e/x86-pm`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7275	`e/x86-3`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7275	`e/x86-athlon`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
7325	`e/x86-1`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7425	`e/x86-athlon`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7437	`e/merged`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
7487	`e/x86-athlon`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
8750	`e/ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
8813	`e/regs`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
9013	`e/merged`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
9050	`e/merged`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
9087	`e/merged`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
9150	`e/regs`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
9387	`e/merged`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
9925	`e/ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
10687	`e/merged`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
11087	`e/regs`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
11238	`e/regs`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
11813	`e/regs`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
12175	`e/regs`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
12337	`e/ref`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
12863	`e/merged`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
12988	`e/ref`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
13150	`e/ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
13337	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140508	20140505
13512	`ref`	`icc -m32 -O3 -static -xHost -fomit-frame-pointer`	20140508	20140505
13825	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20140508	20140505
14175	`e/ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
16525	`e/regs`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
17363	`ref`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505
17388	`ref`	`clang -O1 -march=native -m32 -fomit-frame-pointer`	20140508	20140505
17625	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140508	20140505
17650	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20140508	20140505
18150	`e/ref`	`icc -m32 -O1 -static -xHost -fomit-frame-pointer`	20140508	20140505

Test failure

Implementation: crypto_stream/salsa208/e/x86-xmm
Compiler: clang -O1 -march=native -m32 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 19, namely:

Compiler	Implementations
clang -O1 -march=native -m32 -fomit-frame-pointer	e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5
clang -O3 -march=native -m32 -fomit-frame-pointer	e/merged e/ref e/regs e/x86-1 e/x86-2 e/x86-3 e/x86-athlon e/x86-mmx e/x86-pm e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5 ref x86_xmm5

Compiler output

Implementation: crypto_stream/salsa208/e/x86-1
Compiler: clang -O1 -march=native -m32 -fomit-frame-pointer

salsa20.s: clang: warning: argument unused during compilation: '-fomit-frame-pointer'
salsa20.s: clang: warning: argument unused during compilation: '-D SUPERCOP'
salsa20.s: clang: warning: argument unused during compilation: '-I .'
salsa20.s: clang: warning: argument unused during compilation: '-I /home/bloom/supercop-20140505/supercop-data/floodyberry/x86/include'

Number of similar (compiler,implementation) pairs: 20, namely:

Compiler	Implementations
clang -O1 -march=native -m32 -fomit-frame-pointer	e/x86-1 e/x86-2 e/x86-3 e/x86-athlon e/x86-mmx e/x86-pm e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5
clang -O3 -march=native -m32 -fomit-frame-pointer	e/x86-1 e/x86-2 e/x86-3 e/x86-athlon e/x86-mmx e/x86-pm e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5

Compiler output

Implementation: crypto_stream/salsa208/x86_xmm5
Compiler: clang -O1 -march=native -m32 -fomit-frame-pointer

stream.s: clang: warning: argument unused during compilation: '-fomit-frame-pointer'
stream.s: clang: warning: argument unused during compilation: '-D SUPERCOP'
stream.s: clang: warning: argument unused during compilation: '-I .'
stream.s: clang: warning: argument unused during compilation: '-I /home/bloom/supercop-20140505/supercop-data/floodyberry/x86/include'

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O1 -march=native -m32 -fomit-frame-pointer	x86_xmm5
clang -O3 -march=native -m32 -fomit-frame-pointer	x86_xmm5

Compiler output

Implementation: crypto_stream/salsa208/e/merged
Compiler: icc -m32 -O1 -static -xHost -fomit-frame-pointer

try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc
try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/ipp/../compiler/lib/intel64/libirc.a while searching for irc
try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc
try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc
try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/ipp/../compiler/lib/intel64/libirc.a while searching for irc
try.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc
measure.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc
measure.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/ipp/../compiler/lib/intel64/libirc.a while searching for irc
measure.c: ld: warning: skipping incompatible /opt/intel/composer_xe_2013_sp1.0.080/compiler/lib/intel64/libirc.a while searching for irc

Number of similar (compiler,implementation) pairs: 30, namely:

Compiler	Implementations
icc -m32 -O1 -static -xHost -fomit-frame-pointer	e/merged e/ref e/regs e/x86-1 e/x86-2 e/x86-3 e/x86-athlon e/x86-mmx e/x86-pm e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5 ref x86_xmm5
icc -m32 -O3 -static -xHost -fomit-frame-pointer	e/merged e/ref e/regs e/x86-1 e/x86-2 e/x86-3 e/x86-athlon e/x86-mmx e/x86-pm e/x86-xmm e/x86-xmm2 e/x86-xmm4 e/x86-xmm5 ref x86_xmm5