Implementation notes: armeabi, novena, crypto_core/aes128encrypt

Computer: novena
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20220506
Operation: crypto_core
Primitive: aes128encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2000	72 0 0	12767 428 712	`T:openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2000	72 0 0	12359 428 720	`T:openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2000	72 0 0	11157 424 712	`T:openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2000	72 0 0	11005 424 712	`T:openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2000	72 0 0	20863 428 728	`T:openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2000	36 0 0	8510 432 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2000	36 0 0	9766 432 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2000	36 0 0	8349 428 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2000	36 0 0	7902 424 712	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	2896 0 0	15397 420 712	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	3452 0 0	15541 420 720	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	2896 0 0	13651 416 712	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	3436 0 0	24045 420 728	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	2876 0 0	11243 416 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	3344 0 0	12971 416 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	2856 0 0	10571 408 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	3936 0 0	16437 420 712	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	4492 0 0	16581 420 720	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	3936 0 0	14691 416 712	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	4476 0 0	25085 420 728	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	3896 0 0	12259 416 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	6076 0 0	18573 420 712	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	6588 0 0	18677 420 720	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	6144 0 0	17003 416 712	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	6600 0 0	27213 420 728	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	5924 0 0	14291 416 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	6428 0 0	16051 416 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	5920 0 0	14098 412 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	5940 0 0	13659 408 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2402	4352 0 0	13979 416 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2799	2828 0 0	11002 412 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2800	3180 0 0	14035 416 712	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	4200 0 0	15059 416 712	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	3840 0 0	12018 412 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2801	3880 0 0	11595 408 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
4000	6076 0 0	16827 416 712	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
444836	2556 0 0	12111 416 712	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
573645	3276 0 0	23857 420 728	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
600048	3276 0 0	15353 420 720	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
813666	2716 0 0	15209 420 712	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1271302	1508 0 0	12231 416 712	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1290105	1038 0 0	8735 408 712	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
1308505	1084 0 0	9383 416 712	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
1457317	1516 0 0	12375 416 712	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1780144	1062 0 0	9206 412 712	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506

Compiler output

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

core.c: In file included from core.c:9:
core.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/arm_neon.h:32:2: error: "NEON support not enabled"
core.c: #error "NEON support not enabled"
core.c: ^
core.c: core.c:15:3: error: use of undeclared identifier 'uint8x16_t'
core.c: uint8x16_t temp = vld1q_u8(n);
core.c: ^
core.c: core.c:29:5: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t t;
core.c: ^
core.c: core.c:30:5: error: use of undeclared identifier 't'
core.c: t = vld1q_u32((unsigned int*)(rkeys+i*16));\
core.c: ^
core.c: core.c:30:9: warning: implicit declaration of function 'vld1q_u32' is invalid in C99 [-Wimplicit-function-declaration]
core.c: t = vld1q_u32((unsigned int*)(rkeys+i*16));\
core.c: ^
core.c: core.c:31:62: error: use of undeclared identifier 'temp'
core.c: asm("aese %0.16b, %1.16b\naesmc %0.16b, %0.16b\n" : "+w"(temp) : "w"(t));
core.c: ^
core.c: core.c:46:3: error: use of undeclared identifier 'temp'
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+144)));
core.c: ^
core.c: core.c:46:10: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+144)));
core.c: ^
core.c: ...

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

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

Compiler output

Implementation: T:dolbeau/armv8crypto
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

core.c: core.c:46:10: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+144)));
core.c: ^
core.c: core.c:46:8: error: assigning to 'uint8x16_t' (vector of 16 'uint8_t' values) from incompatible type 'int'
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+144)));
core.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: 1 warning and 1 error generated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:dolbeau/armv8crypto

Compiler output

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

core.c: In file included from core.c:9:
core.c: core.c: In function ‘aes128_armv8_encrypt’:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:10403:1: error: inlining failed in call to ‘always_inline’ ‘vld1q_u8’: target specific option mismatch
core.c: 10403 | vld1q_u8 (const uint8_t * __a)
core.c: | ^~~~~~~~
core.c: core.c:15:21: note: called from here
core.c: 15 | uint8x16_t temp = vld1q_u8(n);
core.c: | ^~~~~~~~~~~
core.c: In file included from core.c:9:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:10417:1: error: inlining failed in call to ‘always_inline’ ‘vld1q_u32’: target specific option mismatch
core.c: 10417 | vld1q_u32 (const uint32_t * __a)
core.c: | ^~~~~~~~~
core.c: core.c:30:9: note: called from here
core.c: 30 | t = vld1q_u32((unsigned int*)(rkeys+i*16));\
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:9:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:10981:1: error: inlining failed in call to ‘always_inline’ ‘vst1q_u8’: target specific option mismatch
core.c: 10981 | vst1q_u8 (uint8_t * __a, uint8x16_t __b)
core.c: | ^~~~~~~~
core.c: core.c:49:3: note: called from here
core.c: 49 | vst1q_u8(out, temp);
core.c: | ^~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:9:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:14048:1: error: inlining failed in call to ‘always_inline’ ‘veorq_u8’: target specific option mismatch
core.c: 14048 | 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	T:dolbeau/armv8crypto
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:dolbeau/armv8crypto
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:dolbeau/armv8crypto
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:dolbeau/armv8crypto