Implementation notes: amd64, h4e350, crypto_aead/iscream12v2

Computer: h4e350
Architecture: amd64
CPU ID: AuthenticAMD-00500f10-178bfbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: iscream12v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
395508	`sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
405252	`sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
405282	`sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
405318	`sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
405420	`sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
409530	`sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
409602	`sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
409620	`sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
410199	`sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
412989	`sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
437088	`sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
452169	`sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
593967	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
594051	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
597042	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
597066	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140621	20140525
597153	`ref`	`gcc -O3 -fomit-frame-pointer`	20140621	20140525
597399	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
597402	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140621	20140525
600543	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
600711	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
604071	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
604146	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
606918	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140621	20140525
611265	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140621	20140525
611355	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140621	20140525
611388	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140621	20140525
612375	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140621	20140525
613464	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
613617	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140621	20140525
617409	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
617502	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140621	20140525
688908	`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`	20141016	20141014
688971	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140804	20140622
689826	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140804	20140622
690789	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
694395	`ref`	`clang -O3 -fomit-frame-pointer`	20140804	20140622
1009365	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1009395	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1020648	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1020777	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1020858	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140621	20140525
1020864	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1023015	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1026399	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1026414	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1079631	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1079727	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1081659	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1081749	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1086624	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140621	20140525
1086669	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1089039	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140621	20140525
1118658	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1118922	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1255521	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1255773	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1258482	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140621	20140525
1258509	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140621	20140525
1260288	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1260387	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1260420	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1280724	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1280745	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1287405	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1287645	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140621	20140525
1292142	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140621	20140525
1304634	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1304694	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140621	20140525
1306626	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140621	20140525
1306629	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140621	20140525
1306668	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140621	20140525
1306698	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140621	20140525
1309407	`ref`	`gcc -O2 -fomit-frame-pointer`	20140621	20140525
1309773	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140621	20140525
1312077	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140621	20140525
1349079	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1349118	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140621	20140525
1352238	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140621	20140525
1352352	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140621	20140525
1352355	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140621	20140525
1352415	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140621	20140525
1394115	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1394337	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140621	20140525
1420812	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140621	20140525
1420920	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140621	20140525
1420944	`ref`	`gcc -Os -fomit-frame-pointer`	20140621	20140525
1421031	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1422945	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140621	20140525
1423143	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140621	20140525
1432629	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1432647	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140621	20140525
1439190	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1441176	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140621	20140525
1443354	`ref`	`gcc -O -fomit-frame-pointer`	20140621	20140525
1443375	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140621	20140525
1443390	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140621	20140525
1443444	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140621	20140525
1443447	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140621	20140525
1443480	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140621	20140525
1445622	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140621	20140525
1511181	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1511307	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140621	20140525
1516848	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140621	20140525
1516878	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
1518507	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140621	20140525
4402377	`ref`	`cc`	20140621	20140525
4406970	`ref`	`gcc`	20140621	20140525
4448751	`ref`	`gcc -funroll-loops`	20140621	20140525

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