Implementation notes: armeabi, novenaimx6, crypto_core/aes256encrypt

Computer: novenaimx6
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20191221
Operation: crypto_core
Primitive: aes256encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3106	40 0 0	7723 460 816	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3110	76 0 0	11111 428 816	`openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3122	76 0 0	12175 428 840	`openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3123	40 0 0	7275 452 816	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3128	76 0 0	11111 428 816	`openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3138	76 0 0	12167 428 840	`openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3145	76 0 0	10025 424 816	`openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3164	40 0 0	7787 460 816	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3221	40 0 0	10156 464 816	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3300	3964 0 0	11557 452 816	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3310	3592 0 0	13558 456 816	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3318	4584 0 0	14550 456 816	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3325	6680 0 0	16646 456 816	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3355	2960 0 0	10557 452 816	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3363	6020 0 0	13613 452 816	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3435	3968 0 0	15897 420 840	`dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3508	6076 0 0	16945 420 816	`dolbeau/std-4ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3531	6076 0 0	15859 416 816	`dolbeau/std-4ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3561	3908 0 0	10997 444 816	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3587	2940 0 0	14873 420 840	`dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3624	6080 0 0	18009 420 840	`dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3628	2888 0 0	9973 444 816	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3636	3976 0 0	14849 420 816	`dolbeau/std-2ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3645	3976 0 0	14849 420 816	`dolbeau/std-2ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3654	3976 0 0	13763 416 816	`dolbeau/std-2ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3672	2948 0 0	13817 420 816	`dolbeau/std-1ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3673	3976 0 0	15905 420 840	`dolbeau/std-2ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3690	2948 0 0	13817 420 816	`dolbeau/std-1ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3700	2948 0 0	12731 416 816	`dolbeau/std-1ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3702	5992 0 0	13077 444 816	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
3730	6076 0 0	16945 420 816	`dolbeau/std-4ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3736	2948 0 0	14873 420 840	`dolbeau/std-1ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
3838	5964 0 0	13501 452 816	`dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
4056	2880 0 0	10413 452 816	`dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
6496	6076 0 0	18001 420 840	`dolbeau/std-4ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
7453	3904 0 0	11437 452 816	`dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
874452	3364 0 0	13314 456 816	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
986243	2836 0 0	14741 420 840	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
986401	2844 0 0	13685 420 816	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
986454	2844 0 0	13685 420 816	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
1032720	2844 0 0	14741 420 840	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
1821666	1128 0 0	8713 452 816	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
1990299	1632 0 0	11391 416 816	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200103	20191221
2085571	1070 0 0	8593 452 816	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221
2150684	1008 0 0	8081 444 816	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200103	20191221

Compiler output

Implementation: dolbeau/armv8crypto
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

core.c: core.c:47:16: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
core.c: temp_lds = armv8_aese_sbox(rotl_aes_edrk);
core.c: ^
core.c: core.c:24:38: note: expanded from macro 'armv8_aese_sbox'
core.c: vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
core.c: ^
core.c: core.c:47:16: error: passing 'int' to parameter of incompatible type 'uint8x16_t' (vector of 16 'uint8_t' values)
core.c: temp_lds = armv8_aese_sbox(rotl_aes_edrk);
core.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:24:38: note: expanded from macro 'armv8_aese_sbox'
core.c: vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
core.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/arm_neon.h:6548:21: note: expanded from macro 'vgetq_lane_u32'
core.c: uint32x4_t __s0 = __p0; \
core.c: ^~~~
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/arm_neon.h:30727:49: note: passing argument to parameter '__p0' here
core.c: __ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
core.c: ^
core.c: core.c:60:16: error: passing 'int' to parameter of incompatible type 'uint8x16_t' (vector of 16 'uint8_t' values)
core.c: temp_lds = armv8_aese_sbox(tmp11);
core.c: ^~~~~~~~~~~~~~~~~~~~~~
core.c: core.c:24:38: note: expanded from macro 'armv8_aese_sbox'
core.c: vgetq_lane_u32(vreinterpretq_u32_u8(vaeseq_u8(vreinterpretq_u8_u32(vdupq_n_u32(input)), vzero)),0)
core.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/arm_neon.h:6548:21: note: expanded from macro 'vgetq_lane_u32'
core.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/armv8crypto
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/armv8crypto
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/armv8crypto
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/armv8crypto
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/armv8crypto

Compiler output

Implementation: dolbeau/armv8crypto
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

core.c: In file included from core.c:9:0:
core.c: core.c: In function 'aes256_armv8_encrypt':
core.c: /usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:9023:1: error: inlining failed in call to always_inline 'vld1q_u8': target specific option mismatch
core.c: vld1q_u8 (const uint8_t * __a)
core.c: ^~~~~~~~
core.c: core.c:91:14: note: called from here
core.c: uint8x16_t temp = vld1q_u8(n);
core.c: ^~~~
core.c: In file included from core.c:9:0:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:9035:1: error: inlining failed in call to always_inline 'vld1q_u32': target specific option mismatch
core.c: vld1q_u32 (const uint32_t * __a)
core.c: ^~~~~~~~~
core.c: core.c:106:7: note: called from here
core.c: t = vld1q_u32((unsigned int*)(rkeys+i*16));\
core.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:9:0:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:9523:1: error: inlining failed in call to always_inline 'vst1q_u8': target specific option mismatch
core.c: vst1q_u8 (uint8_t * __a, uint8x16_t __b)
core.c: ^~~~~~~~
core.c: core.c:125:3: note: called from here
core.c: vst1q_u8(out, temp);
core.c: ^~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:9:0:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:12235:1: error: inlining failed in call to always_inline 'veorq_u8': target specific option mismatch
core.c: veorq_u8 (uint8x16_t __a, uint8x16_t __b)
core.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/armv8crypto
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/armv8crypto
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/armv8crypto
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/armv8crypto