Implementation notes: armeabi, h6dragon, crypto_aead/pi64cipher256v1

Computer: h6dragon
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: pi64cipher256v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
803430	`optimized_nonSSE`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20141025	20141014
803553	`optimized_nonSSE`	`gcc -Os -fomit-frame-pointer`	20141025	20141014
816587	`optimized_nonSSE`	`gcc -mcpu=cortex-a5 -Os -fomit-frame-pointer`	20141025	20141014
836959	`optimized_nonSSE`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20141025	20141014
837008	`optimized_nonSSE`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20141025	20141014
851914	`optimized_nonSSE`	`gcc -mcpu=cortex-a9 -Os -fomit-frame-pointer`	20141025	20141014
854486	`optimized_nonSSE`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20141025	20141014
859687	`optimized_nonSSE`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20141025	20141014
873632	`optimized_nonSSE`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20141025	20141014
873638	`optimized_nonSSE`	`gcc -funroll-loops -O -fomit-frame-pointer`	20141025	20141014
876802	`optimized_nonSSE`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20141025	20141014
940380	`optimized_nonSSE`	`gcc -mcpu=strongarm1100 -Os -fomit-frame-pointer`	20141025	20141014
940474	`optimized_nonSSE`	`gcc -mcpu=arm8 -Os -fomit-frame-pointer`	20141025	20141014
940521	`optimized_nonSSE`	`gcc -mcpu=arm810 -Os -fomit-frame-pointer`	20141025	20141014
940564	`optimized_nonSSE`	`gcc -mcpu=strongarm -Os -fomit-frame-pointer`	20141025	20141014
940622	`optimized_nonSSE`	`gcc -mcpu=strongarm110 -Os -fomit-frame-pointer`	20141025	20141014
959209	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20141025	20141014
986177	`optimized_nonSSE`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -O3 -fomit-frame-pointer`	20141025	20141014
1011812	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20141025	20141014
1179788	`ref`	`gcc -mcpu=arm810 -O3 -fomit-frame-pointer`	20141025	20141014
1179818	`ref`	`gcc -mcpu=strongarm1100 -O3 -fomit-frame-pointer`	20141025	20141014
1179821	`ref`	`gcc -mcpu=strongarm110 -O3 -fomit-frame-pointer`	20141025	20141014
1179830	`ref`	`gcc -mcpu=strongarm -O3 -fomit-frame-pointer`	20141025	20141014
1179831	`ref`	`gcc -mcpu=arm8 -O3 -fomit-frame-pointer`	20141025	20141014
1181419	`ref`	`gcc -mcpu=cortex-a9 -Os -fomit-frame-pointer`	20141025	20141014
1189391	`ref`	`gcc -mcpu=cortex-a5 -Os -fomit-frame-pointer`	20141025	20141014
1208691	`ref`	`gcc -Os -fomit-frame-pointer`	20141025	20141014
1209289	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20141025	20141014
1216806	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20141025	20141014
1216811	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20141025	20141014
1230034	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20141025	20141014
1230152	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20141025	20141014
1231230	`ref`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -O3 -fomit-frame-pointer`	20141025	20141014
1231875	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20141025	20141014
1251810	`ref`	`gcc -mcpu=cortex-a9 -O -fomit-frame-pointer`	20141025	20141014
1258441	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20141025	20141014
1261667	`ref`	`gcc -mcpu=cortex-a5 -O -fomit-frame-pointer`	20141025	20141014
1267200	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20141025	20141014
1267499	`ref`	`gcc -O -fomit-frame-pointer`	20141025	20141014
1297518	`optimized_nonSSE`	`gcc -O3 -fomit-frame-pointer`	20141025	20141014
1301548	`ref`	`gcc -mcpu=arm810 -O -fomit-frame-pointer`	20141025	20141014
1301580	`ref`	`gcc -mcpu=arm8 -O -fomit-frame-pointer`	20141025	20141014
1301929	`ref`	`gcc -mcpu=strongarm -O -fomit-frame-pointer`	20141025	20141014
1301949	`ref`	`gcc -mcpu=strongarm1100 -O -fomit-frame-pointer`	20141025	20141014
1301961	`ref`	`gcc -mcpu=strongarm110 -O -fomit-frame-pointer`	20141025	20141014
1324644	`ref`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -O3 -fomit-frame-pointer`	20141025	20141014
1345751	`ref`	`gcc -O3 -fomit-frame-pointer`	20141025	20141014
1347193	`optimized_nonSSE`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -Os -fomit-frame-pointer`	20141025	20141014
1347892	`ref`	`gcc -mcpu=cortex-a5 -O3 -fomit-frame-pointer`	20141025	20141014
1368570	`ref`	`gcc -mcpu=cortex-a9 -O3 -fomit-frame-pointer`	20141025	20141014
1370629	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20141025	20141014
1377040	`optimized_nonSSE`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -O3 -fomit-frame-pointer`	20141025	20141014
1377480	`ref`	`gcc -mcpu=strongarm110 -Os -fomit-frame-pointer`	20141025	20141014
1377495	`ref`	`gcc -mcpu=strongarm1100 -Os -fomit-frame-pointer`	20141025	20141014
1377559	`ref`	`gcc -mcpu=strongarm -Os -fomit-frame-pointer`	20141025	20141014
1377566	`ref`	`gcc -mcpu=arm810 -Os -fomit-frame-pointer`	20141025	20141014
1377594	`ref`	`gcc -mcpu=arm8 -Os -fomit-frame-pointer`	20141025	20141014
1387998	`optimized_nonSSE`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -Os -fomit-frame-pointer`	20141025	20141014
1449354	`ref`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -O2 -fomit-frame-pointer`	20141025	20141014
1456185	`ref`	`gcc -mcpu=arm8 -O2 -fomit-frame-pointer`	20141025	20141014
1456279	`ref`	`gcc -mcpu=arm810 -O2 -fomit-frame-pointer`	20141025	20141014
1456449	`ref`	`gcc -mcpu=strongarm -O2 -fomit-frame-pointer`	20141025	20141014
1456509	`ref`	`gcc -mcpu=strongarm1100 -O2 -fomit-frame-pointer`	20141025	20141014
1456517	`ref`	`gcc -mcpu=strongarm110 -O2 -fomit-frame-pointer`	20141025	20141014
1462952	`optimized_nonSSE`	`gcc -mcpu=cortex-a9 -O3 -fomit-frame-pointer`	20141025	20141014
1549007	`ref`	`gcc -mcpu=cortex-a5 -O2 -fomit-frame-pointer`	20141025	20141014
1600676	`optimized_nonSSE`	`gcc -mcpu=cortex-a5 -O3 -fomit-frame-pointer`	20141025	20141014
1663269	`ref`	`gcc -mcpu=cortex-a9 -O2 -fomit-frame-pointer`	20141025	20141014
1719056	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20141025	20141014
1762727	`optimized_nonSSE`	`gcc -mcpu=strongarm -O3 -fomit-frame-pointer`	20141025	20141014
1764384	`optimized_nonSSE`	`gcc -mcpu=arm810 -O3 -fomit-frame-pointer`	20141025	20141014
1764563	`optimized_nonSSE`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20141025	20141014
1766888	`optimized_nonSSE`	`gcc -mcpu=strongarm110 -O3 -fomit-frame-pointer`	20141025	20141014
1768294	`optimized_nonSSE`	`gcc -mcpu=arm8 -O3 -fomit-frame-pointer`	20141025	20141014
1769128	`optimized_nonSSE`	`gcc -mcpu=strongarm1100 -O3 -fomit-frame-pointer`	20141025	20141014
1782893	`ref`	`gcc -O2 -fomit-frame-pointer`	20141025	20141014
1827756	`ref`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -O2 -fomit-frame-pointer`	20141025	20141014
1852155	`ref`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -Os -fomit-frame-pointer`	20141025	20141014
1975241	`ref`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -Os -fomit-frame-pointer`	20141025	20141014
2707249	`ref`	`gcc -mcpu=cortex-a8 -mfloat-abi=hard -mfpu=neon -O -fomit-frame-pointer`	20141025	20141014
2707808	`ref`	`gcc -mcpu=cortex-a9 -mfloat-abi=hard -mfpu=neon -O -fomit-frame-pointer`	20141025	20141014
3389938	`optimized_nonSSE`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20141025	20141014
9169939	`ref`	`gcc`	20141025	20141014
9172620	`ref`	`cc`	20141025	20141014
9176117	`ref`	`gcc -funroll-loops`	20141025	20141014
11863062	`optimized_nonSSE`	`gcc -funroll-loops`	20141025	20141014
12017104	`optimized_nonSSE`	`gcc`	20141025	20141014
12117069	`optimized_nonSSE`	`cc`	20141025	20141014

Test failure

Implementation: crypto_aead/pi64cipher256v1/optimized_nonSSE
Compiler: clang -O3 -fomit-frame-pointer

error 111
crypto_aead_decrypt returns nonzero

Number of similar (compiler,implementation) pairs: 22, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=neon -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=neon -fomit-frame-pointer -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive	optimized_nonSSE ref
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=vfpv3-d16 -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=vfpv3-d16 -fomit-frame-pointer -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive	optimized_nonSSE ref
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -mavx -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -mavx -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer	optimized_nonSSE ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer	optimized_nonSSE ref

Compiler output

Implementation: crypto_aead/pi64cipher256v1/optimized_nonSSE
Compiler: clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=neon -fomit-frame-pointer -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive

encrypt.c: clang: warning: argument unused during compilation: '-fpolly'
encrypt.c: clang: warning: argument unused during compilation: '-fvectorize'
encrypt.c: clang: warning: argument unused during compilation: '-fslp-vectorize'
encrypt.c: clang: warning: argument unused during compilation: '-fslp-vectorize-aggressive'

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=neon -fomit-frame-pointer -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive	optimized_nonSSE ref
clang -O3 -fwrapv -march=armv7-a -mfloat-abi=hard -mfpu=vfpv3-d16 -fomit-frame-pointer -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive	optimized_nonSSE ref

Compiler output

Implementation: crypto_aead/pi64cipher256v1/optimized_nonSSE
Compiler: clang -O3 -fwrapv -mavx2 -fomit-frame-pointer

encrypt.c: clang: warning: argument unused during compilation: '-mavx2'