Implementation notes: amd64, h4e350, crypto_aead/iscream12v1

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
397008	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
406566	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
406635	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
406635	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
406716	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
410928	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
411192	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
411246	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
411636	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
412242	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
440472	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
457143	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
597156	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140621	20140525
597177	`ref`	`gcc -O3 -fomit-frame-pointer`	20140621	20140525
597177	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
598776	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
599028	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
599982	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
600096	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
604032	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
604077	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
606819	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
606840	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
606855	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
612987	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140621	20140525
612993	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
613056	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140621	20140525
614007	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
614061	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
614433	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
615006	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
615006	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
692361	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
692427	`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`	20141016	20141014
692454	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140804	20140622
693450	`ref`	`clang -O3 -fomit-frame-pointer`	20140804	20140622
693888	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140804	20140622
1006569	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1009956	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1016100	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1016160	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1020465	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1022703	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140621	20140525
1024086	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1030485	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1030590	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1076397	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140621	20140525
1078641	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140621	20140525
1078875	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1079610	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1081833	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1097130	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1097160	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1102917	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1103394	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1240161	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1240185	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1247268	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1247286	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1247511	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140621	20140525
1247592	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140621	20140525
1249668	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1260222	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1260366	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1283766	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1283817	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1291158	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
1313499	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
1313535	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
1313880	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1313928	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1315401	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
1316010	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
1316208	`ref`	`gcc -O2 -fomit-frame-pointer`	20140621	20140525
1323084	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1325091	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1345422	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1345530	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1363377	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140621	20140525
1363383	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140621	20140525
1363392	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140621	20140525
1366323	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140621	20140525
1405923	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1407132	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1431609	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1431627	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1439829	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1439955	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1439964	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
1443039	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1443048	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1444500	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1444539	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140621	20140525
1444584	`ref`	`gcc -Os -fomit-frame-pointer`	20140621	20140525
1444638	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1444671	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1446300	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140621	20140525
1467972	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1468086	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1474365	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
1474404	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
1474440	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140621	20140525
1474473	`ref`	`gcc -O -fomit-frame-pointer`	20140621	20140525
1474494	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
1475820	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1476621	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
4534227	`ref`	`cc`	20140621	20140525
4536717	`ref`	`gcc`	20140621	20140525
4540737	`ref`	`gcc -funroll-loops`	20140621	20140525

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