Implementation notes: amd64, h5nano, crypto_aead/scream10v1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream10v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
176460	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140818	20140622
176470	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140818	20140622
176475	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140818	20140622
176480	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140818	20140622
176695	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140818	20140622
196530	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140818	20140622
196605	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140818	20140622
196610	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140818	20140622
196615	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140818	20140622
196625	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140818	20140622
211815	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140818	20140622
211845	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140818	20140622
211855	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140818	20140622
211910	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140818	20140622
211955	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140818	20140622
563440	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140818	20140622
563460	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140818	20140622
564280	`ref`	`gcc -O3 -fomit-frame-pointer`	20140818	20140622
564285	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140818	20140622
564295	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140818	20140622
565230	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140818	20140622
565240	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140818	20140622
565700	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140818	20140622
566335	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140818	20140622
566370	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140818	20140622
566370	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140818	20140622
566425	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140818	20140622
567155	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140818	20140622
567330	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140818	20140622
568950	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140818	20140622
573995	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140818	20140622
574010	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140818	20140622
575960	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140818	20140622
578395	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140818	20140622
578990	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140818	20140622
579120	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140818	20140622
579175	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140818	20140622
583005	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140818	20140622
583020	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140818	20140622
583375	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140818	20140622
583375	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140818	20140622
583395	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140818	20140622
584595	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140818	20140622
584620	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140818	20140622
585575	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140818	20140622
585575	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140818	20140622
585590	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140818	20140622
596110	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140818	20140622
596140	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140818	20140622
596140	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140818	20140622
601815	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140818	20140622
601855	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140818	20140622
601860	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140818	20140622
601860	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140818	20140622
677770	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140818	20140622
678065	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140818	20140622
755125	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140818	20140622
755140	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141019	20141014
755195	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140818	20140622
755250	`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`	20141019	20141014
756930	`ref`	`clang -O3 -fomit-frame-pointer`	20140818	20140622
867070	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140818	20140622
869175	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140818	20140622
901770	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140818	20140622
901790	`ref`	`gcc -O2 -fomit-frame-pointer`	20140818	20140622
902305	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140818	20140622
926095	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140818	20140622
926345	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140818	20140622
927170	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140818	20140622
927935	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140818	20140622
927955	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140818	20140622
1008425	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140818	20140622
1008425	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140818	20140622
1016145	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140818	20140622
1016415	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140818	20140622
1016430	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140818	20140622
1038625	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140818	20140622
1049050	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140818	20140622
1049055	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140818	20140622
1065690	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140818	20140622
1065690	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140818	20140622
1195570	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140818	20140622
1195575	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140818	20140622
1195595	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140818	20140622
1195610	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140818	20140622
1195650	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140818	20140622
1197705	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140818	20140622
1197750	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140818	20140622
1197805	`ref`	`gcc -O -fomit-frame-pointer`	20140818	20140622
1246920	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140818	20140622
1256785	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140818	20140622
1256795	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140818	20140622
1257210	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140818	20140622
1266040	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140818	20140622
1370510	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140818	20140622
1377190	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140818	20140622
1377190	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140818	20140622
1377190	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140818	20140622
1377240	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140818	20140622
1377300	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140818	20140622
1381225	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140818	20140622
1383460	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140818	20140622
1386530	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140818	20140622
1388200	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140818	20140622
1405460	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140818	20140622
1405495	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140818	20140622
1405555	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140818	20140622
1405580	`ref`	`gcc -Os -fomit-frame-pointer`	20140818	20140622
1405585	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140818	20140622
1405590	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140818	20140622
1405660	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140818	20140622
1407710	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140818	20140622
2832905	`ref`	`gcc -funroll-loops`	20140818	20140622
2834275	`ref`	`cc`	20140818	20140622
2834735	`ref`	`gcc`	20140818	20140622

Test failure

Implementation: crypto_aead/scream10v1/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/scream10v1/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/scream10v1/sse
Compiler: clang -O3 -fomit-frame-pointer

scream.c: scream.c:39:16: warning: unknown attribute 'flatten' ignored [-Wattributes]
scream.c: __attribute__((flatten)) void encrypt_tweakey (v16qi *restrict X, v16qi *restrict T3) {
scream.c: ^
scream.c: scream.c:96:16: warning: unknown attribute 'flatten' ignored [-Wattributes]
scream.c: __attribute__((flatten)) void decrypt_tweakey (v16qi *restrict X, v16qi *restrict T3) {
scream.c: ^
scream.c: fatal error: error in backend: Cannot select: intrinsic %llvm.x86.ssse3.pshuf.b.128