Implementation notes: amd64, h5nano, crypto_aead/iscream14v1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream14v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
228240	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
228260	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
228265	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
228295	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
228300	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
281370	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
281375	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
281430	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
281505	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
281775	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
286640	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
286645	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
286680	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
286685	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
286685	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
689000	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
689025	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
701370	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
701370	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
710185	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140808	20140622
710200	`ref`	`gcc -O3 -fomit-frame-pointer`	20140808	20140622
711755	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
711815	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
712955	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
712990	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
715135	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
725650	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
725660	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
725675	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
725690	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140808	20140622
725705	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140808	20140622
726820	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
726845	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
728420	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
735355	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
735355	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
735380	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
735420	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
808645	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140808	20140622
808650	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140808	20140622
808700	`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
808710	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141017	20141014
813535	`ref`	`clang -O3 -fomit-frame-pointer`	20140808	20140622
1173010	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1173370	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1189345	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1189365	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140808	20140622
1189395	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1189430	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1189865	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1221375	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1221530	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1265380	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1265405	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1278370	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1278380	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1278385	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1278390	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1289650	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1289705	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140808	20140622
1289730	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140808	20140622
1323125	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
1323125	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
1323125	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
1324390	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1324480	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1324645	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1324660	`ref`	`gcc -O2 -fomit-frame-pointer`	20140808	20140622
1324770	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1324785	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1325035	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1325270	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
1326000	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1326015	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1337960	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
1494700	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1496965	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1584940	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1589920	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1698760	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1724910	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1795250	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1795285	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1795290	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1795300	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1798670	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140808	20140622
1798670	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
1798690	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
1798710	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1798735	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
1800780	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
1800875	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
1808030	`ref`	`gcc -O -fomit-frame-pointer`	20140808	20140622
1820690	`ref`	`gcc -Os -fomit-frame-pointer`	20140808	20140622
1820715	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1820760	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1855935	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1857805	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1859535	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1859620	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140808	20140622
1878135	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140808	20140622
1878190	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140808	20140622
1879635	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140808	20140622
1896615	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1896625	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1897355	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1897375	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140808	20140622
1897375	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140808	20140622
1899045	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1904300	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140808	20140622
1904570	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140808	20140622
1910180	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
4490355	`ref`	`gcc`	20140808	20140622
4490405	`ref`	`cc`	20140808	20140622
4490470	`ref`	`gcc -funroll-loops`	20140808	20140622

Test failure

Implementation: crypto_aead/iscream14v1/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/iscream14v1/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/iscream14v1/sse
Compiler: clang -O3 -fomit-frame-pointer

iscream.c: iscream.c:48:16: 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:114:16: 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