Implementation notes: armeabi, berry2, crypto_stream/salsa2012

Computer: berry2
Microarchitecture: armeabi; Cortex-A7 (410fc075)
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20221122
Operation: crypto_stream
Primitive: salsa2012

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
14191	1596 0 0	11923 388 784	`armneon3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
14196	1596 0 0	13884 392 784	`armneon3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
14196	1628 0 0	12015 388 784	`armneon3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
14334	1596 0 0	11150 380 784	`armneon3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
14379	1604 0 0	23616 384 792	`armneon3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210118	20210114
19195	2780 0 4	15064 392 792	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
19201	2780 0 4	15064 392 792	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
21528	3512 0 4	15800 392 792	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
21577	2788 0 4	13115 388 792	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
23508	1516 0 0	23895 384 792	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210118	20210114
23522	1868 0 0	14528 392 784	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
24993	3068 0 1	25006 384 800	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210118	20210114
25558	1976 0 4	12299 388 792	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
27304	2492 0 4	12046 380 784	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
28328	17732 1184 0	1052912 73769 12048	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210323
28410	3476 0 4	13863 388 792	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
28479	17125 1184 0	1050020 73769 12048	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210323
28483	16228 1184 0	1049175 73761 12048	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210323
28832	6399 1440 0	1040318 74085 12048	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210323
28992	3884 0 1	25824 384 800	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210118	20210114
30984	904 0 0	11603 388 784	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
31200	832 0 0	10761 380 784	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
31702	3080 0 1	25017 384 800	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210118	20210114
32362	2732 0 4	13115 388 792	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
32605	904 0 0	11663 388 784	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
33256	1948 0 4	12271 388 792	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
36692	2196 0 4	12579 388 792	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
36823	1816 0 4	11368 380 784	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114
41940	1640 0 4	11191 380 784	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210118	20210114

Compiler output

Implementation: armneon
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -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: 1 error generated.

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	armneon 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