Implementation notes: amd64, h5nano, crypto_aead/iscream12v2

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream12v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
195040	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
195040	`sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
195040	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
195045	`sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
195095	`sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
241530	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
241545	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
241600	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
241620	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
241640	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
246630	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
246645	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
246670	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
246710	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
246775	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
605555	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
605695	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
619070	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
619105	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140808	20140622
622820	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
622830	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
625160	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
625180	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
626565	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
626640	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140808	20140622
626680	`ref`	`gcc -O3 -fomit-frame-pointer`	20140808	20140622
632540	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140808	20140622
633645	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
633660	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140808	20140622
633740	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
633740	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140808	20140622
636035	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140808	20140622
636065	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140808	20140622
636660	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140808	20140622
637655	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140808	20140622
638080	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140808	20140622
638080	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140808	20140622
638110	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140808	20140622
702995	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141017	20141014
703020	`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`	20141017	20141014
703025	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140808	20140622
703035	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140808	20140622
709475	`ref`	`clang -O3 -fomit-frame-pointer`	20140808	20140622
1015155	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1015415	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1028800	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1028820	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1029160	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140808	20140622
1029180	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1029195	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1056345	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1065720	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1096805	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1096835	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1112345	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1112920	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1112935	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1113080	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1114450	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140808	20140622
1114535	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140808	20140622
1114540	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1147545	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140808	20140622
1148180	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140808	20140622
1148855	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1148870	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1149470	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140808	20140622
1149660	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140808	20140622
1150295	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140808	20140622
1151290	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140808	20140622
1151555	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140808	20140622
1152530	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140808	20140622
1154285	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1154295	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140808	20140622
1155150	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140808	20140622
1197595	`ref`	`gcc -O2 -fomit-frame-pointer`	20140808	20140622
1292490	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1292535	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1372475	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1374045	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140808	20140622
1468530	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1468545	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140808	20140622
1557195	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1557220	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1557235	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140808	20140622
1557240	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140808	20140622
1558595	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140808	20140622
1558595	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140808	20140622
1558605	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140808	20140622
1558610	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140808	20140622
1558645	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140808	20140622
1558650	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140808	20140622
1558665	`ref`	`gcc -O -fomit-frame-pointer`	20140808	20140622
1560825	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140808	20140622
1574260	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1575495	`ref`	`gcc -Os -fomit-frame-pointer`	20140808	20140622
1575510	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1575520	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140808	20140622
1575575	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
1575595	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1576455	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1614365	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140808	20140622
1614525	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140808	20140622
1614580	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140808	20140622
1614900	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140808	20140622
1614920	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140808	20140622
1639120	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140808	20140622
1639145	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140808	20140622
1639145	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1639145	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140808	20140622
1640005	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1640010	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140808	20140622
1641930	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140808	20140622
3949275	`ref`	`gcc -funroll-loops`	20140808	20140622
3950135	`ref`	`cc`	20140808	20140622
3959935	`ref`	`gcc`	20140808	20140622

Test failure

Implementation: crypto_aead/iscream12v2/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/iscream12v2/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/iscream12v2/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