Implementation notes: armeabi, bblack, crypto_stream/salsa208

Computer: bblack
Microarchitecture: armeabi; Cortex-A8 (413fc082)
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20230530
Operation: crypto_stream
Primitive: salsa208

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
7708	1604 0 0	15979 412 744	`armneon3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
7708	1604 0 0	15659 412 752	`armneon3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
7708	1604 0 0	24451 412 752	`armneon3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
7708	1596 0 0	10933 468 744	`armneon3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
7708	1596 0 0	12078 472 744	`armneon3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
7750	1604 0 0	14345 408 744	`armneon3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
7750	1612 0 0	10889 468 744	`armneon3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
7750	1594 0 0	10373 460 744	`armneon3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
7833	1604 0 0	15979 412 744	`armneon3`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
12666	1792 0 4	12250 456 752	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
12749	1796 0 4	12250 456 752	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
13083	1736 0 0	24583 412 752	`armneon`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
13083	1412 0 0	24627 412 752	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
13666	1392 0 0	12222 456 744	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
13708	2280 0 4	12738 456 752	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
13916	1872 0 4	11177 452 752	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
14457	4208 0 0	27059 412 752	`armneon2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
15208	2576 0 1	16563 412 760	`e/merged`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
15249	2564 0 1	16867 412 752	`e/merged`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
15249	2564 0 1	16867 412 752	`e/merged`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
15249	2564 0 1	15233 408 744	`e/merged`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
15666	2800 0 1	25579 412 760	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
16249	2728 0 1	25503 412 760	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
17291	1624 0 4	10377 444 744	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
17375	2740 0 1	25511 412 760	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
19624	1352 0 4	10657 452 752	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
19707	632 0 0	10317 452 744	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
21291	556 0 0	9685 444 744	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
21333	640 0 0	10285 452 744	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
21749	2520 0 4	11793 452 752	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
21999	728 0 0	15147 412 752	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
22041	728 0 0	15467 412 744	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
22915	624 0 0	13733 408 744	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24374	728 0 0	15467 412 744	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24457	2240 0 1	14909 408 744	`e/regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24541	2244 0 1	16543 412 752	`e/regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24541	2244 0 1	16223 412 760	`e/regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24582	2244 0 1	16543 412 752	`e/regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24582	1932 0 4	11201 452 752	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
24915	2296 0 1	16279 412 760	`e/ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
24915	1360 0 4	10665 452 752	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
25123	13016 868 0	755666 73497 12008	`T:cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25207	12306 1184 0	862922 73641 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
25291	11918 1184 0	861218 73641 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
25373	10674 804 0	754012 73493 12008	`T:cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25499	10674 804 0	754012 73493 12008	`T:cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25499	6041 488 0	748002 73173 12008	`T:cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25540	11447 1184 0	860681 73633 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
25624	1964 0 1	16263 412 752	`e/ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25624	1964 0 1	16263 412 752	`e/ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
25999	4876 1440 0	855392 73957 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
26124	1152 0 4	9901 444 744	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
27582	1480 0 4	10753 452 752	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530
28165	1788 0 1	14453 408 744	`e/ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230628	20230530
33165	1120 0 4	9869 444 744	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230628	20230530

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-7/lib/clang/7.0.1/include/arm_neon.h:28:2: error: "NEON support not enabled"
xor.c: #error "NEON support not enabled"
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:48:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(8))) int8_t int8x8_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:49:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(16))) int8_t int8x16_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:50:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(4))) int16_t int16x4_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:51:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(8))) int16_t int16x8_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:52:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(2))) int32_t int32x2_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:53:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(4))) int32_t int32x4_t;
xor.c: ^
xor.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:54:24: error: 'neon_vector_type' attribute is not supported for this target
xor.c: typedef __attribute__((neon_vector_type(1))) int64_t int64x1_t;
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/8/include/arm_neon.h:7192:1: error: inlining failed in call to always_inline 'vcombine_u32': target specific option mismatch
xor.c: vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
xor.c: ^~~~~~~~~~~~
xor.c: xor.c:40:23: note: called from here
xor.c: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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/8/include/arm_neon.h:7192:1: error: inlining failed in call to always_inline 'vcombine_u32': target specific option mismatch
xor.c: vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
xor.c: ^~~~~~~~~~~~
xor.c: xor.c:40:23: note: called from here
xor.c: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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: 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/8/include/arm_neon.h:8779:1: error: inlining failed in call to always_inline 'vext_u32': target specific option mismatch
xor.c: 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