Implementation notes: armeabi, novena, crypto_core/aes256encrypt

Computer: novena
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20220506
Operation: crypto_core
Primitive: aes256encrypt

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2001	76 0 0	11137 424 712	`T:openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2001	76 0 0	20867 428 728	`T:openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	2924 0 0	11291 416 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	3944 0 0	12307 416 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	76 0 0	12755 428 712	`T:openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	76 0 0	12347 428 720	`T:openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	76 0 0	11009 424 712	`T:openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2400	40 0 0	8570 432 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	40 0 0	9834 432 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	40 0 0	8385 428 712	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2400	40 0 0	7922 424 712	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2401	6556 0 0	16179 416 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2799	4532 0 0	14155 416 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2800	2916 0 0	15413 420 712	`T:dolbeau/std-1ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	2916 0 0	15005 420 720	`T:dolbeau/std-1ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	2916 0 0	13667 416 712	`T:dolbeau/std-1ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	2876 0 0	23485 420 728	`T:dolbeau/std-1ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	3532 0 0	13155 416 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2800	2896 0 0	10611 408 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2800	3920 0 0	24533 420 728	`T:dolbeau/std-2ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	3920 0 0	11635 408 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2800	6060 0 0	18557 420 712	`T:dolbeau/std-4ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	6060 0 0	18149 420 720	`T:dolbeau/std-4ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	6060 0 0	16811 416 712	`T:dolbeau/std-4ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2800	5980 0 0	13699 408 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2801	3956 0 0	16453 420 712	`T:dolbeau/std-2ft`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2801	3956 0 0	16045 420 720	`T:dolbeau/std-2ft`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2801	3956 0 0	14707 416 712	`T:dolbeau/std-2ft`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2801	6196 0 0	17051 416 712	`T:dolbeau/std-4ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2801	6012 0 0	26621 420 728	`T:dolbeau/std-4ft`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2801	5960 0 0	14138 412 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
3200	2872 0 0	11050 412 712	`T:dolbeau/std-1ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
3200	4248 0 0	15107 416 712	`T:dolbeau/std-2ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
3200	5976 0 0	14339 416 712	`T:dolbeau/std-4ft`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
3201	3228 0 0	14083 416 712	`T:dolbeau/std-1ft`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
3201	3896 0 0	12074 412 712	`T:dolbeau/std-2ft`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
614449	2668 0 0	12279 416 712	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
792063	3468 0 0	24049 420 728	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
838467	3468 0 0	15529 420 720	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1123691	2908 0 0	15377 420 712	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1713738	1112 0 0	9463 416 712	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
1756542	1548 0 0	12271 416 712	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
1766943	1074 0 0	8783 408 712	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220603	20220506
2049366	1556 0 0	12391 416 712	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220603	20220506
2497002	1114 0 0	9278 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:22:3: error: use of undeclared identifier 'uint8x16_t'
core.c: uint8x16_t vzero = vreinterpretq_u8_u32(vdupq_n_u32(0));
core.c: ^
core.c: core.c:47:16: warning: implicit declaration of function 'vgetq_lane_u32' is invalid in C99 [-Wimplicit-function-declaration]
core.c: temp_lds = armv8_aese_sbox(rotl_aes_edrk);
core.c: ^
core.c: core.c:24:2: 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: warning: implicit declaration of function 'vreinterpretq_u32_u8' is invalid in C99 [-Wimplicit-function-declaration]
core.c: core.c:24:17: 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: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
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: warning: implicit declaration of function 'vreinterpretq_u8_u32' is invalid in C99 [-Wimplicit-function-declaration]
core.c: core.c:24:48: 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: ...

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: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-11/lib/clang/11.0.1/include/arm_neon.h:7509:21: note: expanded from macro 'vgetq_lane_u32'
core.c: uint32x4_t __s0 = __p0; \
core.c: ^~~~
core.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/arm_neon.h:32650:49: 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: warning: implicit declaration of function 'vaeseq_u8' is invalid in C99 [-Wimplicit-function-declaration]
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: core.c:60:16: error: passing 'int' to parameter of incompatible type 'uint8x16_t' (vector of 16 'uint8_t' values)
core.c: ...

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 ‘aes256_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:91:21: note: called from here
core.c: 91 | 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:106:9: note: called from here
core.c: 106 | 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:125:3: note: called from here
core.c: 125 | 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