Implementation notes: amd64, h5nano, crypto_aead/scream12v2

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream12v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
208370	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140819	20140622
208370	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140819	20140622
208380	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140819	20140622
208400	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140819	20140622
208495	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140819	20140622
231375	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140819	20140622
231380	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140819	20140622
231385	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140819	20140622
231395	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140819	20140622
231425	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140819	20140622
249170	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140819	20140622
249175	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140819	20140622
249185	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140819	20140622
249185	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140819	20140622
249185	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140819	20140622
655900	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
655900	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
662490	`ref`	`gcc -O3 -fomit-frame-pointer`	20140819	20140622
662490	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140819	20140622
662510	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140819	20140622
663665	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
663685	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
664245	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
664245	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
665375	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140819	20140622
665380	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140819	20140622
665380	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140819	20140622
665415	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140819	20140622
666080	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140819	20140622
668035	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
668290	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
674135	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140819	20140622
674140	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140819	20140622
674140	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140819	20140622
677815	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
677860	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
681450	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
681475	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
686690	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140819	20140622
686700	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140819	20140622
686890	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140819	20140622
688500	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
688520	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
690985	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
691475	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
692080	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
692630	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
703765	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140819	20140622
703780	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140819	20140622
704345	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140819	20140622
713080	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140819	20140622
713110	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
713190	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140819	20140622
713225	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
807120	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140819	20140622
809220	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140819	20140622
890750	`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
890750	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140819	20140622
890800	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140819	20140622
890830	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141019	20141014
892960	`ref`	`clang -O3 -fomit-frame-pointer`	20140819	20140622
1022205	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
1024815	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
1062625	`ref`	`gcc -O2 -fomit-frame-pointer`	20140819	20140622
1062635	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140819	20140622
1064755	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140819	20140622
1093710	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140819	20140622
1093885	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140819	20140622
1096015	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140819	20140622
1096535	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140819	20140622
1189445	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140819	20140622
1189445	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140819	20140622
1189465	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
1189485	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
1195955	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
1195960	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
1239380	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
1239380	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
1262960	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140819	20140622
1387200	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140819	20140622
1387215	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140819	20140622
1414940	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140819	20140622
1414945	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140819	20140622
1414970	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140819	20140622
1414970	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140819	20140622
1414980	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140819	20140622
1415000	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140819	20140622
1417155	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140819	20140622
1417200	`ref`	`gcc -O -fomit-frame-pointer`	20140819	20140622
1472340	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1472365	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1472405	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140819	20140622
1472415	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140819	20140622
1473730	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140819	20140622
1620605	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1620640	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1638470	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140819	20140622
1638470	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140819	20140622
1638470	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140819	20140622
1638490	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140819	20140622
1638490	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140819	20140622
1640530	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1641525	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1646065	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1646095	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1670055	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1670065	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1670065	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1670070	`ref`	`gcc -Os -fomit-frame-pointer`	20140819	20140622
1670070	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140819	20140622
1670075	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140819	20140622
1670085	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
3352995	`ref`	`gcc -funroll-loops`	20140819	20140622
3355045	`ref`	`cc`	20140819	20140622
3356610	`ref`	`gcc`	20140819	20140622

Test failure

Implementation: crypto_aead/scream12v2/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/scream12v2/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/scream12v2/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