Implementation notes: armeabi, bblack, crypto_stream/salsa2012

Computer: bblack
Microarchitecture: armeabi; Cortex-A8 (413fc082)
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: salsa2012

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
10000	1604 0 0	15667 412 752	`armneon3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
10036	1594 0 0	10373 460 744	`armneon3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
10040	1604 0 0	15987 412 744	`armneon3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
10040	1604 0 0	15987 412 744	`armneon3`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
10040	1604 0 0	14353 408 744	`armneon3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
10040	1604 0 0	24467 412 752	`armneon3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
10040	1596 0 0	10937 468 744	`armneon3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
10040	1596 0 0	12082 472 744	`armneon3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
10040	1612 0 0	10893 468 744	`armneon3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
16500	1824 0 4	12282 456 752	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
16708	1824 0 4	12282 456 752	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
17164	2044 0 0	24915 412 752	`armneon`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
17376	1412 0 0	24647 412 752	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
17872	1392 0 0	12222 456 744	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
18332	1884 0 4	11197 452 752	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
18332	2292 0 4	12750 456 752	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
19584	2564 0 1	16875 412 752	`e/merged`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
19584	2576 0 1	16571 412 760	`e/merged`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
19584	2564 0 1	16875 412 752	`e/merged`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
19620	2564 0 1	15241 408 744	`e/merged`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
20168	2800 0 1	25595 412 760	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
20708	2728 0 1	25519 412 760	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
22164	2740 0 1	25527 412 760	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
22376	1360 0 4	10665 452 752	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
22540	1624 0 4	10377 444 744	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
24248	632 0 0	10317 452 744	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
25500	640 0 0	10285 452 744	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
25832	556 0 0	9685 444 744	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
25956	2528 0 4	11805 452 752	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
26040	3812 0 0	26683 412 752	`armneon2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
26248	728 0 0	15479 412 744	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
26248	728 0 0	15159 412 752	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
26248	728 0 0	15479 412 744	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
26832	624 0 0	13741 408 744	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
28376	12306 1184 0	862922 73641 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
28956	10682 804 0	754044 73493 12008	`T:cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29000	10682 804 0	754044 73493 12008	`T:cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29080	11926 1184 0	861218 73641 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
29124	13024 868 0	755666 73497 12008	`T:cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29124	2240 0 1	14921 408 744	`e/regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29204	2244 0 1	16551 412 752	`e/regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29208	2244 0 1	16551 412 752	`e/regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29208	2244 0 1	16231 412 760	`e/regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29336	6049 488 0	748042 73173 12008	`T:cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29504	2296 0 1	16287 412 760	`e/ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
29664	11447 1184 0	860681 73633 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
29876	4876 1440 0	855392 73957 12008	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
30164	1964 0 4	11233 452 752	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
30332	1324 0 4	10633 452 752	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
30500	1964 0 1	16271 412 752	`e/ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
30580	1964 0 1	16271 412 752	`e/ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
31376	1152 0 4	9905 444 744	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
32832	1788 0 1	14461 408 744	`e/ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231212
32956	1464 0 4	10737 452 752	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212
37416	1120 0 4	9869 444 744	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231212

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_salsa2012_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_salsa2012_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