Implementation notes: amd64, h5nano, crypto_aead/iscream12v1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
196205	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
196225	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
196240	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
196270	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
196275	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
243295	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
243325	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
243360	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
243380	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
243440	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
248185	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
248200	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
248220	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
248220	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
248665	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
605490	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
605495	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
610955	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
610970	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
622395	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
622565	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140807	20140622
623545	`ref`	`gcc -O3 -fomit-frame-pointer`	20140808	20140622
625240	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140807	20140622
625240	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
627910	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140807	20140622
627915	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
635045	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
635045	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
635475	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
635490	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
637245	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140808	20140622
637245	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
637245	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140808	20140622
638335	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140807	20140622
638335	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140807	20140622
638335	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140807	20140622
638335	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140807	20140622
638390	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140807	20140622
703785	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140808	20140622
703800	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140808	20140622
703825	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141017	20141014
703865	`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
707670	`ref`	`clang -O3 -fomit-frame-pointer`	20140808	20140622
1015280	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1015280	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1029260	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1029275	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1029305	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140808	20140622
1029330	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1029600	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1056150	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1056165	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1096590	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1098870	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1111930	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1112065	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1112090	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1112130	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1113940	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140808	20140622
1113940	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140808	20140622
1113995	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1147495	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140807	20140622
1147495	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140807	20140622
1147515	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140807	20140622
1147525	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140807	20140622
1148065	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140807	20140622
1148730	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1148765	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1148785	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140807	20140622
1148850	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1149035	`ref`	`gcc -O2 -fomit-frame-pointer`	20140808	20140622
1149035	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140807	20140622
1149425	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1150460	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1150465	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1296275	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1296350	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1372280	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1372420	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1469855	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1493155	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1555610	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140807	20140622
1555670	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1555675	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1557795	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1562715	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1562735	`ref`	`gcc -O -fomit-frame-pointer`	20140808	20140622
1562735	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140807	20140622
1562735	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140807	20140622
1562755	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140807	20140622
1562755	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140807	20140622
1562755	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140807	20140622
1564815	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140807	20140622
1575530	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1576240	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140807	20140622
1576665	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1577475	`ref`	`gcc -Os -fomit-frame-pointer`	20140808	20140622
1579665	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1606140	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140807	20140622
1606145	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140807	20140622
1627780	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140807	20140622
1627785	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140807	20140622
1629590	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140807	20140622
1640640	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1641400	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140808	20140622
1641400	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140808	20140622
1641400	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1641400	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1641410	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1642870	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1646980	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140807	20140622
1649270	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140807	20140622
3895010	`ref`	`cc`	20140808	20140622
3895035	`ref`	`gcc`	20140808	20140622
3895040	`ref`	`gcc -funroll-loops`	20140808	20140622

Test failure

Implementation: crypto_aead/iscream12v1/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/iscream12v1/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/iscream12v1/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