Implementation notes: amd64, h4e350, crypto_aead/iscream14v1

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream14v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
459342	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
470607	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
470682	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
470694	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
470820	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
475074	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
475089	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
475437	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
476613	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
478032	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
510723	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
529116	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
691866	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
691881	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
694218	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
694377	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
694665	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
694680	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140621	20140525
694743	`ref`	`gcc -O3 -fomit-frame-pointer`	20140621	20140525
695694	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
695709	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
700614	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
700668	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140621	20140525
700683	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140621	20140525
701505	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
701508	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
701955	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
702036	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
702075	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
702150	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
702396	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
707904	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
798978	`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
799011	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
799020	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140804	20140622
799176	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140804	20140622
801645	`ref`	`clang -O3 -fomit-frame-pointer`	20140804	20140622
1164387	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1164567	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1173909	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1174047	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1180653	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1180812	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140621	20140525
1185036	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1192266	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1193853	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1247148	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1247157	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1256172	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1259160	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1287612	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1290474	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1311849	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140621	20140525
1311999	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140621	20140525
1313250	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1430082	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1430169	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1438503	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1438509	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140621	20140525
1438560	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140621	20140525
1439493	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1441410	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1456530	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1457034	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1482285	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1482357	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1494675	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
1517376	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
1517424	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
1517436	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
1517448	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
1517634	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1517661	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1520226	`ref`	`gcc -O2 -fomit-frame-pointer`	20140621	20140525
1523733	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1524843	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1557276	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1557300	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1575150	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140621	20140525
1575183	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140621	20140525
1575240	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140621	20140525
1577937	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140621	20140525
1624632	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1625907	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1643733	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1643865	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1665285	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1665351	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
1665375	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1666668	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1668537	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140621	20140525
1668585	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140621	20140525
1668603	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1668639	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1668894	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1670352	`ref`	`gcc -Os -fomit-frame-pointer`	20140621	20140525
1670550	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1694127	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1696353	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1697871	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
1697895	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1697907	`ref`	`gcc -O -fomit-frame-pointer`	20140621	20140525
1697970	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
1698297	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
1699899	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140621	20140525
1699908	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
5234967	`ref`	`cc`	20140621	20140525
5235111	`ref`	`gcc`	20140621	20140525
5235567	`ref`	`gcc -funroll-loops`	20140621	20140525

Test failure

Implementation: crypto_aead/iscream14v1/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/iscream14v1/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/iscream14v1/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