Implementation notes: amd64, h5nano, crypto_aead/iscream14v2

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream14v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
227130	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
227130	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
227145	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
227310	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
227345	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
279460	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
279490	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
279490	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
279585	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
279610	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
285115	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
285115	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
285115	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
285130	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
285185	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
692545	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
692555	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
703475	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
703480	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
709820	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
709835	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
710375	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140808	20140622
710385	`ref`	`gcc -O3 -fomit-frame-pointer`	20140808	20140622
710395	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
711605	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
711605	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
718890	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
718890	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
724500	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
724550	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140808	20140622
724570	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140808	20140622
724870	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
725025	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
734955	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
735085	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
735105	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
735120	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
735280	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
807040	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141017	20141014
807055	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140808	20140622
807130	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140808	20140622
807260	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141017	20141014
814720	`ref`	`clang -O3 -fomit-frame-pointer`	20140808	20140622
1172880	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1172900	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1188895	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1188895	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1189325	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1189335	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140808	20140622
1189335	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1221545	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1221570	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1265565	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1265580	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1277840	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1277845	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1277865	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1277885	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1289975	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1289985	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140808	20140622
1289995	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140808	20140622
1323170	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
1323200	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
1323810	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
1323810	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
1324305	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1324325	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1324445	`ref`	`gcc -O2 -fomit-frame-pointer`	20140808	20140622
1324485	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1324485	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1325055	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1325075	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1330980	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1330985	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1332620	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
1490915	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1527660	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1599445	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1599465	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1695585	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1695585	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1819140	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1819175	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1820575	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1820595	`ref`	`gcc -Os -fomit-frame-pointer`	20140808	20140622
1820595	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1820605	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140808	20140622
1820770	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1824360	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1824430	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1825470	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
1825490	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
1825490	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
1825520	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1825525	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140808	20140622
1825555	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
1825570	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
1850435	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1850435	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1853820	`ref`	`gcc -O -fomit-frame-pointer`	20140808	20140622
1864610	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140808	20140622
1864620	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140808	20140622
1864725	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140808	20140622
1864985	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140808	20140622
1873070	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140808	20140622
1895030	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140808	20140622
1895030	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1895265	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1897335	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1901945	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1903575	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1904365	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140808	20140622
4545985	`ref`	`gcc`	20140808	20140622
4554125	`ref`	`cc`	20140808	20140622
4556820	`ref`	`gcc -funroll-loops`	20140808	20140622

Test failure

Implementation: crypto_aead/iscream14v2/sse
Compiler: gcc -m64 -march=core2 -Os -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
gcc -m64 -march=core2 -Os -fomit-frame-pointer	sse
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	sse
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	sse
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	sse
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/iscream14v2/sse
Compiler: cc

Number of similar (compiler,implementation) pairs: 71, namely:

Compiler	Implementations
cc	sse
gcc	sse
gcc -O2 -fomit-frame-pointer	sse
gcc -O3 -fomit-frame-pointer	sse
gcc -O -fomit-frame-pointer	sse
gcc -Os -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	sse
gcc -funroll-loops	sse
gcc -funroll-loops -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -O -fomit-frame-pointer	sse
gcc -funroll-loops -Os -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	sse
gcc -m64 -O2 -fomit-frame-pointer	sse
gcc -m64 -O3 -fomit-frame-pointer	sse
gcc -m64 -O -fomit-frame-pointer	sse
gcc -m64 -Os -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	sse
gcc -march=barcelona -O2 -fomit-frame-pointer	sse
gcc -march=barcelona -O3 -fomit-frame-pointer	sse
gcc -march=barcelona -O -fomit-frame-pointer	sse
gcc -march=barcelona -Os -fomit-frame-pointer	sse
gcc -march=k8 -O2 -fomit-frame-pointer	sse
gcc -march=k8 -O3 -fomit-frame-pointer	sse
gcc -march=k8 -O -fomit-frame-pointer	sse
gcc -march=k8 -Os -fomit-frame-pointer	sse
gcc -march=nocona -O2 -fomit-frame-pointer	sse
gcc -march=nocona -O3 -fomit-frame-pointer	sse
gcc -march=nocona -O -fomit-frame-pointer	sse
gcc -march=nocona -Os -fomit-frame-pointer	sse

Compiler output

Implementation: crypto_aead/iscream14v2/sse
Compiler: clang -O3 -fomit-frame-pointer

iscream.c: iscream.c:38:16: warning: unknown attribute 'flatten' ignored [-Wattributes]
iscream.c: __attribute__((flatten)) void encrypt_tweakey (v16qi *restrict X, v16qi *restrict TK) {
iscream.c: ^
iscream.c: iscream.c:95:16: warning: unknown attribute 'flatten' ignored [-Wattributes]
iscream.c: __attribute__((flatten)) void decrypt_tweakey (v16qi *restrict X, v16qi *restrict TK) {
iscream.c: ^
iscream.c: fatal error: error in backend: Cannot select: intrinsic %llvm.x86.ssse3.pshuf.b.128