Implementation notes: amd64, h4e350, crypto_aead/scream10v1

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream10v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
339591	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
340254	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
340323	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
340353	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
340392	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
350784	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
350982	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
351003	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
351009	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
351042	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
377724	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
382116	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
546534	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140629	20140525
547176	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
547731	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140629	20140525
552468	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
552477	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
554106	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
560010	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
560079	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
560172	`ref`	`gcc -O3 -fomit-frame-pointer`	20140629	20140525
560301	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140629	20140525
560640	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
563850	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
563880	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
564375	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
564390	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140629	20140525
564399	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140629	20140525
564474	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
564528	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
567924	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
568167	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
571107	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
571161	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
571506	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
571950	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
571989	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
575409	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
575442	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
600279	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
600327	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
603990	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140629	20140525
604053	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
604071	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140629	20140525
609873	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
610398	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
610707	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
610731	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140629	20140525
685494	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
687537	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140629	20140525
716055	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141018	20141014
716076	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140805	20140622
716358	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140805	20140622
716361	`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
718425	`ref`	`clang -O3 -fomit-frame-pointer`	20140805	20140622
915522	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
918864	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
928905	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
928923	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
928986	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
939834	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
939855	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
940710	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
940788	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
941532	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140629	20140525
942492	`ref`	`gcc -O2 -fomit-frame-pointer`	20140629	20140525
943044	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
944721	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
944832	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
961998	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
967518	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
985209	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
986427	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
989892	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
989892	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140629	20140525
990969	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
990972	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
991011	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140629	20140525
991047	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
991176	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140629	20140525
1017831	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
1017843	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
1018134	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
1018227	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140629	20140525
1018998	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
1019121	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
1019202	`ref`	`gcc -O -fomit-frame-pointer`	20140629	20140525
1052382	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1055025	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1091466	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140629	20140525
1092129	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140629	20140525
1092951	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140629	20140525
1093353	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140629	20140525
1126107	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1126497	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1126605	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140629	20140525
1127064	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1127070	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1127499	`ref`	`gcc -Os -fomit-frame-pointer`	20140629	20140525
1128252	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140629	20140525
1128444	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1274295	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1277508	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1292445	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
1292472	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1293321	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
3869706	`ref`	`gcc`	20140629	20140525
3869946	`ref`	`cc`	20140629	20140525
3870666	`ref`	`gcc -funroll-loops`	20140629	20140525

Test failure

Implementation: crypto_aead/scream10v1/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/scream10v1/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/scream10v1/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