Implementation notes: armeabi, novena, crypto_stream/salsa208

Computer: novena
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20220506
Operation: crypto_stream
Primitive: salsa208

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
8801	1604 0 0	16465 424 744	`armneon3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
8801	1604 0 0	15249 424 752	`armneon3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
8801	1632 0 0	14855 420 744	`armneon3`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
8801	1604 0 0	14719 420 744	`armneon3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
8801	1604 0 0	23753 424 760	`armneon3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
8801	1596 0 0	11483 436 744	`armneon3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
8801	1596 0 0	12835 436 744	`armneon3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
8801	1594 0 0	10487 428 744	`armneon3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
9600	1612 0 0	11050 432 744	`armneon3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
12002	2312 0 0	24457 424 760	`armneon2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
12402	1176 0 0	23317 424 760	`armneon`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
13601	2152 0 4	13363 420 752	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
13601	1744 0 4	12955 420 752	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
13601	1236 0 0	12823 420 744	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
13602	1740 0 4	11603 420 752	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
14001	1440 0 0	23953 424 760	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
14402	3360 0 4	14571 420 752	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
14802	2500 0 1	16073 424 760	`e/merged`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
14802	2728 0 1	24809 424 768	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
15601	2488 0 1	17281 424 752	`e/merged`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
15601	2488 0 1	15535 420 744	`e/merged`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
15601	2608 0 1	24685 424 768	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
16001	2576 0 1	24653 424 768	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
16002	2484 0 1	15631 420 744	`e/merged`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
16401	1632 0 4	10495 412 744	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
16801	12272 868 0	962998 73533 12008	`T:cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
16801	11996 1184 0	1070225 73657 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
16802	18010 1184 0	1077509 73653 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
17201	6017 488 0	957119 73213 12008	`T:cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
17202	10062 804 0	962122 73533 12008	`T:cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
17602	11295 1184 0	1069356 73645 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
17602	6174 1504 0	1063369 73965 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
18801	2556 0 4	11986 416 752	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
18801	576 0 0	10815 420 744	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
18802	13071 1900 0	963509 74529 12008	`T:cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
18802	1696 0 4	11555 420 752	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
19602	728 0 0	15953 424 744	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
19602	728 0 0	14737 424 752	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
19602	624 0 0	10430 416 744	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
20402	1284 0 4	11147 420 752	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
20403	624 0 0	14107 420 744	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
20802	632 0 0	14219 420 744	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
21202	2144 0 1	15709 424 760	`e/ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
21602	1924 0 1	16709 424 752	`e/ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22002	2196 0 1	16981 424 752	`e/regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22002	2228 0 1	15363 420 744	`e/regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22002	2196 0 1	15235 420 744	`e/regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22002	1992 0 4	11426 416 752	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
22401	2196 0 1	15765 424 760	`e/regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22401	1608 0 4	10467 412 744	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
22402	1680 0 1	14819 420 744	`e/ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
22802	1692 0 1	14731 420 744	`e/ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220605	20220506
24402	1576 0 4	11010 416 752	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
24402	1148 0 4	10011 412 744	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506
27602	568 0 0	9811 412 744	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220605	20220506

Compiler output

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

xor.c: In file included from xor.c:9:
xor.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/arm_neon.h:32:2: error: "NEON support not enabled"
xor.c: #error "NEON support not enabled"
xor.c: ^
xor.c: xor.c:21:9: error: unknown type name 'uint32x4_t'
xor.c: const uint32x4_t abab = {-1,0,-1,0};
xor.c: ^
xor.c: xor.c:22:9: error: unknown type name 'uint64x1_t'
xor.c: const uint64x1_t nextblock = {1};
xor.c: ^
xor.c: xor.c:23:3: error: use of undeclared identifier 'uint32x4_t'
xor.c: uint32x4_t k0k1k2k3 = (uint32x4_t) vld1q_u8((uint8_t *) k);
xor.c: ^
xor.c: xor.c:24:3: error: use of undeclared identifier 'uint32x4_t'
xor.c: uint32x4_t k4k5k6k7 = (uint32x4_t) vld1q_u8((uint8_t *) (k + 16));
xor.c: ^
xor.c: xor.c:25:3: error: use of undeclared identifier 'uint32x4_t'
xor.c: uint32x4_t start0 = (uint32x4_t) vld1q_u8((uint8_t *) sigma);
xor.c: ^
xor.c: xor.c:26:3: error: use of undeclared identifier 'uint32x2_t'
xor.c: uint32x2_t n0n1 = (uint32x2_t) vld1_u8((uint8_t *) n);
xor.c: ^
xor.c: xor.c:27:3: error: use of undeclared identifier 'uint32x2_t'
xor.c: uint32x2_t n2n3 = {0,0};
xor.c: ^
xor.c: ...

Number of similar (compiler,implementation) pairs: 8, 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
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon2

Compiler output

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

xor.c: In file included from xor.c:9:
xor.c: xor.c: In function ‘crypto_stream_salsa208_armneon_constbranchindex_xor’:
xor.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
xor.c: 7196 | vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
xor.c: | ^~~~~~~~~~~~
xor.c: xor.c:40:23: note: called from here
xor.c: 40 | uint32x4_t start1 = vcombine_u32(k5k0,n0k4);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.c: | ^~~~~~~~
xor.c: xor.c:38:21: note: called from here
xor.c: 38 | uint32x2_t k7k2 = vext_u32(k6k7,k2k3,1);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.c: | ^~~~~~~~
xor.c: xor.c:36:21: note: called from here
xor.c: 36 | uint32x2_t k1n1 = vext_u32(k0k1,n1n0,1);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.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

Compiler output

Implementation: armneon2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

xor.c: In file included from xor.c:9:
xor.c: xor.c: In function ‘crypto_stream_salsa208_armneon2_constbranchindex_xor’:
xor.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
xor.c: 7196 | vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
xor.c: | ^~~~~~~~~~~~
xor.c: xor.c:40:23: note: called from here
xor.c: 40 | uint32x4_t start1 = vcombine_u32(k5k0,n0k4);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.c: | ^~~~~~~~
xor.c: xor.c:38:21: note: called from here
xor.c: 38 | uint32x2_t k7k2 = vext_u32(k6k7,k2k3,1);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.c: | ^~~~~~~~
xor.c: xor.c:36:21: note: called from here
xor.c: 36 | uint32x2_t k1n1 = vext_u32(k0k1,n1n0,1);
xor.c: | ^~~~~~~~~~~~~~~~~~~~~
xor.c: In file included from xor.c:9:
xor.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:8783:1: error: inlining failed in call to ‘always_inline’ ‘vext_u32’: target specific option mismatch
xor.c: 8783 | vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
xor.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	armneon2