Implementation notes: amd64, h4e350, crypto_aead/scream12v1

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: scream12v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
400902	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
403812	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
403881	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
403881	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
403941	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
415512	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
416202	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
416247	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
416289	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
416478	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
448257	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
454365	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
646677	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140629	20140525
648672	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140629	20140525
648729	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140629	20140525
649149	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
651348	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
651564	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
654234	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140629	20140525
654534	`ref`	`gcc -O3 -fomit-frame-pointer`	20140629	20140525
654993	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140629	20140525
661371	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
661386	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
662175	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
662217	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
663294	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
663453	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
665160	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140629	20140525
665214	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
665238	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140629	20140525
667986	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
668253	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
669261	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
669648	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140629	20140525
669705	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
670065	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140629	20140525
670545	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140629	20140525
674106	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
674595	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
704937	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
705207	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140629	20140525
719223	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
719283	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
719325	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140629	20140525
719394	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
727368	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140629	20140525
727371	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140629	20140525
727473	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
813549	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
813621	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140629	20140525
842946	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141018	20141014
843027	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140805	20140622
843060	`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
843549	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140805	20140622
846450	`ref`	`clang -O3 -fomit-frame-pointer`	20140805	20140622
1081236	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
1082106	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140629	20140525
1084896	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
1085016	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140629	20140525
1089546	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140629	20140525
1098903	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140629	20140525
1098954	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140629	20140525
1099608	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140629	20140525
1099644	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140629	20140525
1099812	`ref`	`gcc -O2 -fomit-frame-pointer`	20140629	20140525
1101144	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140629	20140525
1101465	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140629	20140525
1111332	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
1111338	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140629	20140525
1132026	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1133355	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1156878	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140629	20140525
1158723	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1159503	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1159713	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140629	20140525
1159914	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1159935	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1160010	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1166088	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1167264	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140629	20140525
1203657	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140629	20140525
1203699	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140629	20140525
1203738	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140629	20140525
1204002	`ref`	`gcc -O -fomit-frame-pointer`	20140629	20140525
1204071	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140629	20140525
1204914	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140629	20140525
1205187	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140629	20140525
1234182	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1236726	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140629	20140525
1280574	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140629	20140525
1280586	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140629	20140525
1281858	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140629	20140525
1282500	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140629	20140525
1321953	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140629	20140525
1322085	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140629	20140525
1322841	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140629	20140525
1322889	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1323222	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1323318	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140629	20140525
1324419	`ref`	`gcc -Os -fomit-frame-pointer`	20140629	20140525
1324563	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140629	20140525
1510179	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1510224	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140629	20140525
1524111	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1524129	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140629	20140525
1524153	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140629	20140525
4585530	`ref`	`gcc`	20140629	20140525
4587024	`ref`	`cc`	20140629	20140525
4587711	`ref`	`gcc -funroll-loops`	20140629	20140525

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