Implementation notes: amd64, h4e350, crypto_aead/scream10v2

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream10v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
339111	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
339165	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
339561	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
339843	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
343836	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
349581	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
349707	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
349812	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
351354	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
353061	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
376611	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
382497	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
545397	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140629	20140525
546309	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140629	20140525
546837	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
548880	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
548964	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
554304	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
559998	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
560253	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
560481	`ref`	`gcc -O3 -fomit-frame-pointer`	20140629	20140525
560487	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140629	20140525
560595	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
563814	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
563838	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
564051	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
564126	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
564606	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140629	20140525
564618	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140629	20140525
564651	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
567288	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
567456	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
570918	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
571164	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
571245	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
571638	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
571638	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
574662	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
574722	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
600183	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
600327	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
605355	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140629	20140525
605367	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140629	20140525
605388	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
608847	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140629	20140525
608970	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
609720	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
609750	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
686736	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140629	20140525
686946	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
717867	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141018	20141014
717915	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140805	20140622
718038	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140805	20140622
718161	`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
719109	`ref`	`clang -O3 -fomit-frame-pointer`	20140805	20140622
920871	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
920988	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
924576	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
924861	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
924894	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
924903	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
925872	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
931464	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
931512	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
932544	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
933057	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
934947	`ref`	`gcc -O2 -fomit-frame-pointer`	20140629	20140525
936381	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140629	20140525
940836	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
982977	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
983232	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
997437	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
999327	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
999330	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140629	20140525
999345	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
999348	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
999669	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1000644	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140629	20140525
1006143	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1006464	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1024248	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
1024251	`ref`	`gcc -O -fomit-frame-pointer`	20140629	20140525
1024257	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
1024257	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
1024266	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
1024803	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
1025655	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140629	20140525
1062663	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1066737	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1092870	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140629	20140525
1097658	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140629	20140525
1098555	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140629	20140525
1099011	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140629	20140525
1099611	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
1099614	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1100451	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1119153	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1119534	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1137039	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1137138	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140629	20140525
1137507	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1138107	`ref`	`gcc -Os -fomit-frame-pointer`	20140629	20140525
1142028	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1142754	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140629	20140525
1142808	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1143729	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
3843360	`ref`	`cc`	20140629	20140525
3844395	`ref`	`gcc -funroll-loops`	20140629	20140525
3845973	`ref`	`gcc`	20140629	20140525

Test failure

Implementation: crypto_aead/scream10v2/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/scream10v2/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/scream10v2/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