Implementation notes: amd64, h4e350, crypto_aead/iscream14v2

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream14v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
458085	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
469293	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
469374	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
469542	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
470154	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
473703	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
473751	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
473757	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
474456	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
477741	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
507423	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
524085	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
683547	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
683595	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
688002	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
688023	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
694245	`ref`	`gcc -O3 -fomit-frame-pointer`	20140621	20140525
694248	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140621	20140525
694272	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
696576	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
696705	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
699105	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
699123	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140621	20140525
699180	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140621	20140525
701646	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
701661	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
702276	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
703413	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
703428	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
705093	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
705132	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
708090	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
797226	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
799278	`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
800472	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140804	20140622
802428	`ref`	`clang -O3 -fomit-frame-pointer`	20140804	20140622
805884	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140804	20140622
1166103	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1166532	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1178451	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1178460	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1179399	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140621	20140525
1179429	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1183095	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1187283	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1187793	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1241310	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140621	20140525
1244253	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1244415	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140621	20140525
1249350	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1250964	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1275996	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1276191	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1276272	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1278222	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1443924	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1443939	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1449873	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140621	20140525
1449933	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1450032	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140621	20140525
1452333	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1452549	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1476504	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1478844	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1483086	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1483140	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1494966	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
1507440	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1507542	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1509690	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
1509756	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
1509762	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
1512624	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1512660	`ref`	`gcc -O2 -fomit-frame-pointer`	20140621	20140525
1512678	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1513161	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
1559100	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1560645	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140621	20140525
1560756	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140621	20140525
1560780	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140621	20140525
1561908	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1563441	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140621	20140525
1609356	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1611660	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1639392	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1639542	`ref`	`gcc -Os -fomit-frame-pointer`	20140621	20140525
1639560	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140621	20140525
1639581	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1639608	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1641882	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140621	20140525
1653123	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1653222	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1659354	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
1664421	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
1664433	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
1664517	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
1664532	`ref`	`gcc -O -fomit-frame-pointer`	20140621	20140525
1664571	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1664913	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140621	20140525
1694532	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1694640	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1699068	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1699188	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1719387	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1719399	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
1721409	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
5075715	`ref`	`gcc -funroll-loops`	20140621	20140525
5077185	`ref`	`gcc`	20140621	20140525
5097327	`ref`	`cc`	20140621	20140525

Test failure

Implementation: crypto_aead/iscream14v2/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/iscream14v2/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/iscream14v2/sse
Compiler: clang -O3 -fomit-frame-pointer

iscream.c: iscream.c:38:16: 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:95:16: 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