Implementation notes: armeabi, novena, crypto_core/salsa20

Computer: novena
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20220506
Operation: crypto_core
Primitive: salsa20

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2400	384 0 0	20997 420 728	`armneon`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	12937 420 712	`armneon2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	12505 420 720	`armneon2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	11311 416 712	`armneon2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	11167 416 712	`armneon2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	21001 420 728	`armneon2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	8787 416 712	`armneon2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	10059 416 712	`armneon2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	8574 412 712	`armneon2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	380 0 0	8131 408 712	`armneon2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	1228 0 0	13769 420 712	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	1228 0 0	13337 420 720	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	1228 0 0	12003 416 712	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	1248 0 0	21857 420 728	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506
2400	960 0 0	9343 416 712	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	960 0 0	10615 416 712	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2400	842 0 0	9030 412 712	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
2401	802 0 0	8531 408 712	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220604	20220506
3999	1412 0 0	12307 416 712	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220604	20220506

Compiler output

Implementation: armneon
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

core.c: In file included from core.c:8:
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:20:9: error: unknown type name 'uint32x4_t'
core.c: const uint32x4_t abab = {-1,0,-1,0};
core.c: ^
core.c: core.c:22:3: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t k0k1k2k3 = (uint32x4_t) vld1q_u8((uint8_t *) k);
core.c: ^
core.c: core.c:23:3: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t k4k5k6k7 = (uint32x4_t) vld1q_u8((uint8_t *) (k + 16));
core.c: ^
core.c: core.c:24:3: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t c0c1c2c3 = (uint32x4_t) vld1q_u8((uint8_t *) c);
core.c: ^
core.c: core.c:25:3: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t n0n1n2n3 = (uint32x4_t) vld1q_u8((uint8_t *) in);
core.c: ^
core.c: core.c:27:3: error: use of undeclared identifier 'uint32x4_t'
core.c: uint32x4_t n1n2n3n0 = vextq_u32(n0n1n2n3,n0n1n2n3,1);
core.c: ^
core.c: core.c:28:3: error: use of undeclared identifier 'uint32x2_t'
core.c: uint32x2_t n1n2 = vget_low_u32(n1n2n3n0);
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	armneon
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon

Compiler output

Implementation: armneon
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

core.c: In file included from core.c:8:
core.c: core.c: In function ‘crypto_core_salsa20_armneon_constbranchindex’:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8870:1: error: inlining failed in call to ‘always_inline’ ‘vextq_u32’: target specific option mismatch
core.c: 8870 | vextq_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
core.c: | ^~~~~~~~~
core.c: core.c:50:23: note: called from here
core.c: 50 | uint32x4_t start3 = vextq_u32(k2k3n3k7,k2k3n3k7,1);
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:8:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8870:1: error: inlining failed in call to ‘always_inline’ ‘vextq_u32’: target specific option mismatch
core.c: 8870 | vextq_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
core.c: | ^~~~~~~~~
core.c: core.c:49:23: note: called from here
core.c: 49 | uint32x4_t start2 = vextq_u32(n1n2k6k1,n1n2k6k1,1);
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:8:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8870:1: error: inlining failed in call to ‘always_inline’ ‘vextq_u32’: target specific option mismatch
core.c: 8870 | vextq_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
core.c: | ^~~~~~~~~
core.c: core.c:48:23: note: called from here
core.c: 48 | uint32x4_t start1 = vextq_u32(k4k5k0n0,k4k5k0n0,1);
core.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:8:
core.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:7196:1: error: inlining failed in call to ‘always_inline’ ‘vcombine_u32’: target specific option mismatch
core.c: 7196 | vcombine_u32 (uint32x2_t __a, uint32x2_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	armneon
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon