Implementation notes: amd64, h4e350, crypto_aead/scream12v2

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream12v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
400017	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
402672	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
402738	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
402744	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
402768	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
414930	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
415011	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
415119	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
415143	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
418161	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
447924	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
455481	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
646914	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
647088	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
647145	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
648252	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140629	20140525
648315	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140629	20140525
648330	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
654576	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140629	20140525
654900	`ref`	`gcc -O3 -fomit-frame-pointer`	20140629	20140525
654951	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
661476	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
661515	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
661833	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
661938	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
663246	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
663399	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
665346	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140629	20140525
665361	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
665457	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140629	20140525
667374	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
667602	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
668847	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
669030	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
669681	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
669798	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
669819	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
673524	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
673974	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
703812	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
703881	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
718770	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
718863	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
719010	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
719085	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140629	20140525
726417	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140629	20140525
726468	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
728121	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140629	20140525
815937	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
815970	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140629	20140525
844989	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140805	20140622
845016	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141018	20141014
845070	`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`	20141018	20141014
845586	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140805	20140622
847269	`ref`	`clang -O3 -fomit-frame-pointer`	20140805	20140622
1080867	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
1082064	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
1082184	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
1085424	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
1088178	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
1088553	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
1088973	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
1089198	`ref`	`gcc -O2 -fomit-frame-pointer`	20140629	20140525
1090428	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140629	20140525
1093872	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
1097157	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
1098384	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
1102266	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
1102281	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
1148526	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1148895	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1168098	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140629	20140525
1168110	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1168140	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1168188	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1168533	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1168593	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140629	20140525
1169823	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1188021	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1189668	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1199946	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
1199949	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
1199973	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
1200411	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140629	20140525
1201068	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
1201236	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
1201548	`ref`	`gcc -O -fomit-frame-pointer`	20140629	20140525
1253427	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1253658	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1289214	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140629	20140525
1289220	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140629	20140525
1290435	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140629	20140525
1290825	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140629	20140525
1300761	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
1300935	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1301316	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1324941	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1325325	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1343232	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140629	20140525
1343247	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1343271	`ref`	`gcc -Os -fomit-frame-pointer`	20140629	20140525
1343652	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1343820	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1344480	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1344555	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140629	20140525
1344786	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
4539477	`ref`	`cc`	20140629	20140525
4541733	`ref`	`gcc -funroll-loops`	20140629	20140525
4548417	`ref`	`gcc`	20140629	20140525

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