Implementation notes: amd64, h5nano, crypto_aead/scream12v1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
208775	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140819	20140622
208885	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140819	20140622
208905	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140819	20140622
208920	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140819	20140622
209195	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140819	20140622
232630	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140819	20140622
232675	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140819	20140622
232710	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140819	20140622
232740	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140819	20140622
233075	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140819	20140622
250445	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140819	20140622
250500	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140819	20140622
250555	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140819	20140622
250570	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140819	20140622
250915	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140819	20140622
661505	`ref`	`gcc -O3 -fomit-frame-pointer`	20140819	20140622
661520	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140819	20140622
662130	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
662190	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
662375	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
662415	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
662835	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
662865	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
665625	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140819	20140622
665655	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140819	20140622
665670	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140819	20140622
665690	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140819	20140622
665690	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140819	20140622
668910	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140819	20140622
672330	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
672340	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140819	20140622
672685	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140819	20140622
672700	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140819	20140622
672715	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140819	20140622
676290	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
676555	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
677005	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
677010	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140819	20140622
681955	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
681985	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140819	20140622
686650	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140819	20140622
686655	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140819	20140622
686680	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140819	20140622
690785	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
690850	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
691650	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
691650	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
704100	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140819	20140622
704215	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140819	20140622
704250	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140819	20140622
712885	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140819	20140622
713000	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
713000	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
713030	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140819	20140622
808830	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140819	20140622
808830	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140819	20140622
883500	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141019	20141014
889220	`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`	20141019	20141014
889235	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140819	20140622
889275	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140819	20140622
895590	`ref`	`clang -O3 -fomit-frame-pointer`	20140819	20140622
1021400	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
1021405	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140819	20140622
1061670	`ref`	`gcc -O2 -fomit-frame-pointer`	20140819	20140622
1061675	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140819	20140622
1061675	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140819	20140622
1092635	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140819	20140622
1092635	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140819	20140622
1092635	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140819	20140622
1092650	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140819	20140622
1092675	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140819	20140622
1190375	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
1190380	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140819	20140622
1190400	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140819	20140622
1190735	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140819	20140622
1198300	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
1198300	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140819	20140622
1238380	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
1238415	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140819	20140622
1258925	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140819	20140622
1262720	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140819	20140622
1415015	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140819	20140622
1415040	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140819	20140622
1415065	`ref`	`gcc -O -fomit-frame-pointer`	20140819	20140622
1415070	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140819	20140622
1415075	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140819	20140622
1415090	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140819	20140622
1417320	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140819	20140622
1418360	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140819	20140622
1475265	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140819	20140622
1475295	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1482350	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140819	20140622
1484520	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1484840	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140819	20140622
1622700	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1625080	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1631925	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140819	20140622
1631925	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140819	20140622
1631950	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140819	20140622
1631960	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140819	20140622
1631975	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140819	20140622
1637340	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1637375	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140819	20140622
1642875	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1647480	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1665790	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1665835	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140819	20140622
1665890	`ref`	`gcc -Os -fomit-frame-pointer`	20140819	20140622
1665910	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140819	20140622
1665910	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140819	20140622
1665910	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
1667995	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140819	20140622
3348625	`ref`	`cc`	20140819	20140622
3348890	`ref`	`gcc -funroll-loops`	20140819	20140622
3348985	`ref`	`gcc`	20140819	20140622

Test failure

Implementation: crypto_aead/scream12v1/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/scream12v1/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/scream12v1/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