Implementation notes: aarch64, pi3bplus, crypto_stream/chacha20

Computer: pi3bplus
Microarchitecture: aarch64; Cortex-A53 (410fd034)
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 202311020231107
Operation: crypto_stream
Primitive: chacha20

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
8375	3752 0 4	17063 824 816	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
8375	4704 0 4	18871 824 816	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
9375	3292 0 4	15447 808 800	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
10750	3928 0 4	17255 824 816	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
10750	4880 0 4	19063 824 816	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
12750	4172 0 4	17358 816 808	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
13500	3488 0 4	15671 808 800	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
14125	2148 0 4	14311 808 800	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
15000	2896 0 4	16207 824 816	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
15000	3528 0 4	17687 824 816	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
15250	4384 0 4	17598 816 808	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
15250	3232 0 4	17407 824 816	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
15875	4620 0 4	18799 824 816	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
16000	6228 0 4	18407 808 800	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
18000	7868 0 4	21070 816 808	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
18750	7128 0 4	20455 824 816	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
19250	8312 0 4	22495 824 816	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
23875	2168 0 4	15487 824 816	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
24375	2704 0 4	16015 824 816	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
28000	1876 0 4	14023 808 800	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
30750	2028 0 4	14175 808 800	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
34250	3680 0 4	16854 816 808	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
42875	3068 0 4	16246 816 808	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107
51125	2604 0 4	15782 816 808	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231111	20231107

Compiler output

Implementation: T:cryptopp
Security model: timingleaks
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.cpp: stream.cpp:1:10: fatal error: cryptopp/chacha.h: No such file or directory
stream.cpp: 1 | #include <cryptopp/chacha.h>
stream.cpp: | ^~~~~~~~~~~~~~~~~~~
stream.cpp: compilation terminated.

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

Compiler	Implementations
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:cryptopp
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:cryptopp
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:cryptopp
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:cryptopp

Compiler output

Implementation: dolbeau/arm-sve
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

chacha.c: In file included from chacha.c:94:
chacha.c: uX.h: In function 'crypto_stream_chacha20_dolbeau_arm_sve_constbranchindex_ECRYPT_encrypt_bytes':
chacha.c: uX.h:21:15: error: ACLE function 'svcntb' requires ISA extension 'sve'
chacha.c: 21 | uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: | ^~~~~~
chacha.c: uX.h:21:15: note: you can enable 'sve' using the command-line option '-march', or by using the 'target' attribute or pragma

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve

Compiler output

Implementation: dolbeau/arm-sve2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

chacha.c: In file included from chacha.c:94:
chacha.c: uX.h: In function 'crypto_stream_chacha20_dolbeau_arm_sve2_constbranchindex_ECRYPT_encrypt_bytes':
chacha.c: uX.h:18:15: error: ACLE function 'svcntb' requires ISA extension 'sve'
chacha.c: 18 | uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: | ^~~~~~
chacha.c: uX.h:18:15: note: you can enable 'sve' using the command-line option '-march', or by using the 'target' attribute or pragma

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/arm-sve2

Compiler output

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: stream.c:80:2: error: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: 80 | #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: | ^~~~~
stream.c: stream.c: In function 'crypto_stream_chacha20_krovetz_vec128_constbranchindex_xor':
stream.c: stream.c:151:14: warning: implicit declaration of function 'NONCE' [-Wimplicit-function-declaration]
stream.c: 151 | vec s3 = NONCE(np);
stream.c: | ^~~~~
stream.c: stream.c:151:14: error: incompatible types when initializing type 'vec' {aka '__vector(4) unsigned int'} using type 'int'
stream.c: stream.c:91:19: error: 'VBPI' undeclared (first use in this function); did you mean 'BPI'?
stream.c: 91 | #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: | ^~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: 152 | for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: | ^~~
stream.c: stream.c:91:19: note: each undeclared identifier is reported only once for each function it appears in
stream.c: 91 | #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: | ^~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: 152 | for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: | ^~~
stream.c: stream.c:91:26: error: 'GPR_TOO' undeclared (first use in this function)
stream.c: 91 | #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: | ^~~~~~~
stream.c: stream.c:152:36: note: in expansion of macro 'BPI'
stream.c: 152 | for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128