Implementation notes: aarch64, jetsontx1, crypto_stream/chacha20

Computer: jetsontx1
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20191017
Operation: crypto_stream
Primitive: chacha20

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
8103	3956 0 1	15801 760 808	`dolbeau/arm-neon`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
8109	2864 0 1	10975 752 792	`dolbeau/arm-neon`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
8112	4436 0 4	15503 808 808	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
8123	3956 0 1	13961 760 792	`dolbeau/arm-neon`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
8123	3956 0 1	13961 760 792	`dolbeau/arm-neon`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
8157	7564 0 1	18895 808 792	`dolbeau/arm-neon`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
8162	3756 0 4	13498 800 792	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
8186	8472 0 1	21615 808 808	`dolbeau/arm-neon`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
9120	4644 0 4	15727 808 808	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
9124	3900 0 4	13658 800 792	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
9555	3076 0 1	11215 752 792	`dolbeau/generic-gccsimd128`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
9560	4164 0 1	16025 760 808	`dolbeau/generic-gccsimd128`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
9563	4164 0 1	14185 760 792	`dolbeau/generic-gccsimd128`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
9563	4164 0 1	14185 760 792	`dolbeau/generic-gccsimd128`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
9591	7964 0 1	19295 808 792	`dolbeau/generic-gccsimd128`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
9611	8892 0 1	22031 808 808	`dolbeau/generic-gccsimd128`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
10814	11236 0 1	22543 808 792	`dolbeau/generic-gccsimd256`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191023	20191017
10847	12180 0 1	25295 808 808	`dolbeau/generic-gccsimd256`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191023	20191017
10856	7900 0 4	17666 800 792	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
10876	4756 0 1	12895 752 792	`dolbeau/generic-gccsimd256`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191023	20191017
10878	5812 0 1	15833 760 792	`dolbeau/generic-gccsimd256`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191023	20191017
10878	5812 0 1	15833 760 792	`dolbeau/generic-gccsimd256`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191023	20191017
10901	5828 0 1	17689 760 808	`dolbeau/generic-gccsimd256`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191023	20191017
10968	8556 0 4	19647 808 808	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
11170	3176 0 4	11910 784 784	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12579	2780 0 4	13847 808 808	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12596	2780 0 4	13847 808 808	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12610	3060 0 4	14119 808 808	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12615	2204 0 4	11930 800 792	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12674	1892 0 4	10638 784 784	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
12939	2176 0 1	10279 752 792	`e/merged`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13736	5432 0 1	18591 808 808	`e/merged`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
13862	3292 0 4	12054 784 784	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
13891	2612 0 1	14449 760 808	`e/ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13900	6800 0 4	15550 784 784	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
13917	2564 0 1	12561 760 792	`e/regs`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13922	2564 0 1	12561 760 792	`e/regs`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13934	2580 0 1	14417 760 808	`e/regs`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13960	2836 0 1	12833 760 792	`e/merged`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13965	2836 0 1	14673 760 808	`e/merged`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
13978	5028 0 1	16383 808 792	`e/regs`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
13986	2836 0 1	12833 760 792	`e/merged`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
14027	5032 0 1	18191 808 808	`e/regs`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
14099	7800 0 4	17562 800 792	`dolbeau/generic-gccsimd256`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191023	20191017
14149	4124 0 4	13858 800 792	`dolbeau/arm-neon`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
14198	2612 0 1	12609 760 792	`e/ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
14229	5424 0 1	16783 808 792	`e/merged`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
14308	2612 0 1	12609 760 792	`e/ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
14817	4204 0 4	13954 800 792	`dolbeau/generic-gccsimd128`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
16038	5052 0 1	18207 808 808	`e/ref`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
16088	4412 0 1	15759 808 792	`e/ref`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
16550	3552 0 4	13274 800 792	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
16986	1532 0 1	9639 752 792	`e/ref`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
17104	1992 0 4	11730 800 792	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
17446	1980 0 1	10087 752 792	`e/regs`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
20376	1824 0 4	10550 784 784	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
21799	1664 0 4	10406 784 784	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
22131	1992 0 4	11722 800 792	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
23240	2432 0 4	12154 800 792	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
25060	2892 0 4	12618 800 792	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910

Compiler output

Implementation: dolbeau/arm-sve
Security model: unknown
Compiler: armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE

chacha.c: In file included from chacha.c:12:
chacha.c: /opt/arm/arm-hpc-compiler-19.3_Generic-AArch64_Ubuntu-16.04_aarch64-linux/lib/clang/7.1.0/include/arm_sve.h:28:2: error: "SVE support not enabled"
chacha.c: #error "SVE support not enabled"
chacha.c: ^
chacha.c: In file included from chacha.c:95:
chacha.c: ./uX.h:21:9: error: expected ';' after expression
chacha.c: uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: ^
chacha.c: ;
chacha.c: ./uX.h:21:1: error: use of undeclared identifier 'uint64_t'
chacha.c: uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: ^
chacha.c: ./uX.h:21:10: error: use of undeclared identifier 'vc'
chacha.c: uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: ^
chacha.c: ./uX.h:21:15: warning: implicit declaration of function 'svcntb' is invalid in C99 [-Wimplicit-function-declaration]
chacha.c: uint64_t vc = svcntb(); /* how many bytes in a vector */
chacha.c: ^
chacha.c: ./uX.h:22:15: error: use of undeclared identifier 'vc'
chacha.c: if (bytes>=16*vc) {
chacha.c: ^
chacha.c: ./uX.h:24:3: error: unknown type name 'svuint32_t'; did you mean '__uint32_t'?
chacha.c: svuint32_t x_0 = svdup_n_u32(x[0]);
chacha.c: ^~~~~~~~~~
chacha.c: __uint32_t
chacha.c: ...

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

Compiler	Implementations
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE	dolbeau/arm-sve
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O3 -fPIC -fPIE	dolbeau/arm-sve

Compiler output

Implementation: dolbeau/arm-sve
Security model: unknown
Compiler: clang -mcpu=native -march=armv8a+crypto -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

chacha.c: chacha.c:12:10: fatal error: 'arm_sve.h' file not found
chacha.c: #include <arm_sve.h>
chacha.c: ^~~~~~~~~~~
chacha.c: 1 error generated.

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

Compiler	Implementations
clang -mcpu=native -march=armv8a+crypto -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/arm-sve
clang -mcpu=native -march=armv8a+crypto -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/arm-sve
clang -mcpu=native -march=armv8a+crypto -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/arm-sve
clang -mcpu=native -march=armv8a+crypto -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/arm-sve

Compiler output

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

chacha.c: chacha.c:12:10: fatal error: arm_sve.h: No such file or directory
chacha.c: #include <arm_sve.h>
chacha.c: ^~~~~~~~~~~
chacha.c: compilation terminated.

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: krovetz/vec128
Security model: unknown
Compiler: armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE

stream.c: stream.c:80:2: error: -- Implementation supports only machines with neon, altivec or SSE2
stream.c: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: ^
stream.c: stream.c:151:14: warning: implicit declaration of function 'NONCE' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: vec s3 = NONCE(np);
stream.c: ^
stream.c: stream.c:151:9: error: initializing 'vec' (vector of 4 'unsigned int' values) with an expression of incompatible type 'int'
stream.c: vec s3 = NONCE(np);
stream.c: ^ ~~~~~~~~~
stream.c: stream.c:152:36: error: use of undeclared identifier 'VBPI'
stream.c: for (iters = 0; iters < inlen/(BPI*64); iters++) {
stream.c: ^
stream.c: stream.c:91:19: note: expanded from macro 'BPI'
stream.c: #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: ^
stream.c: stream.c:152:36: error: use of undeclared identifier 'GPR_TOO'
stream.c: stream.c:91:26: note: expanded from macro 'BPI'
stream.c: #define BPI (VBPI + GPR_TOO) /* Blocks computed per loop iteration */
stream.c: ^
stream.c: stream.c:155:19: error: use of undeclared identifier 'ONE'
stream.c: v7 = v3 + ONE;
stream.c: ^
stream.c: stream.c:176:13: warning: implicit declaration of function 'ROTW16' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: DQROUND_VECTORS(v0,v1,v2,v3)
stream.c: ^
stream.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE	krovetz/vec128
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O3 -fPIC -fPIE	krovetz/vec128
clang -mcpu=native -march=armv8a+crypto -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -mcpu=native -march=armv8a+crypto -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -mcpu=native -march=armv8a+crypto -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128
clang -mcpu=native -march=armv8a+crypto -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	krovetz/vec128

Compiler output

Implementation: krovetz/vec128
Security model: unknown
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: #error -- Implementation supports only machines with neon, altivec or SSE2
stream.c: ^~~~~
stream.c: stream.c: In function 'crypto_stream_chacha20_krovetz_vec128_xor':
stream.c: stream.c:151:14: warning: implicit declaration of function 'NONCE' [-Wimplicit-function-declaration]
stream.c: 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: #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: 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: #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: 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: #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: 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