Implementation notes: aarch64, jetsontx1, crypto_stream/chacha20

Computer: jetsontx1
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20191017
Operation: crypto_stream
Primitive: chacha20
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
81033956 0 115801 760 808dolbeau/arm-neonclang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
81092864 0 110975 752 792dolbeau/arm-neonclang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
81124436 0 415503 808 808dolbeau/arm-neongcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
81233956 0 113961 760 792dolbeau/arm-neonclang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
81233956 0 113961 760 792dolbeau/arm-neonclang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
81577564 0 118895 808 792dolbeau/arm-neonarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019101720190910
81623756 0 413498 800 792dolbeau/arm-neongcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
81868472 0 121615 808 808dolbeau/arm-neonarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019101720190910
91204644 0 415727 808 808dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
91243900 0 413658 800 792dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
95553076 0 111215 752 792dolbeau/generic-gccsimd128clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
95604164 0 116025 760 808dolbeau/generic-gccsimd128clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
95634164 0 114185 760 792dolbeau/generic-gccsimd128clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
95634164 0 114185 760 792dolbeau/generic-gccsimd128clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
95917964 0 119295 808 792dolbeau/generic-gccsimd128armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019101720190910
96118892 0 122031 808 808dolbeau/generic-gccsimd128armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019101720190910
1081411236 0 122543 808 792dolbeau/generic-gccsimd256armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019102320191017
1084712180 0 125295 808 808dolbeau/generic-gccsimd256armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019102320191017
108567900 0 417666 800 792dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
108764756 0 112895 752 792dolbeau/generic-gccsimd256clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102320191017
108785812 0 115833 760 792dolbeau/generic-gccsimd256clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102320191017
108785812 0 115833 760 792dolbeau/generic-gccsimd256clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102320191017
109015828 0 117689 760 808dolbeau/generic-gccsimd256clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019102320191017
109688556 0 419647 808 808dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
111703176 0 411910 784 784dolbeau/arm-neongcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
125792780 0 413847 808 808e/refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
125962780 0 413847 808 808e/regsgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
126103060 0 414119 808 808e/mergedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
126152204 0 411930 800 792e/mergedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
126741892 0 410638 784 784e/mergedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
129392176 0 110279 752 792e/mergedclang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
137365432 0 118591 808 808e/mergedarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019101720190910
138623292 0 412054 784 784dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
138912612 0 114449 760 808e/refclang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139006800 0 415550 784 784dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
139172564 0 112561 760 792e/regsclang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139222564 0 112561 760 792e/regsclang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139342580 0 114417 760 808e/regsclang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139602836 0 112833 760 792e/mergedclang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139652836 0 114673 760 808e/mergedclang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
139785028 0 116383 808 792e/regsarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019101720190910
139862836 0 112833 760 792e/mergedclang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
140275032 0 118191 808 808e/regsarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019101720190910
140997800 0 417562 800 792dolbeau/generic-gccsimd256gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019102320191017
141494124 0 413858 800 792dolbeau/arm-neongcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
141982612 0 112609 760 792e/refclang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
142295424 0 116783 808 792e/mergedarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019101720190910
143082612 0 112609 760 792e/refclang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
148174204 0 413954 800 792dolbeau/generic-gccsimd128gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
160385052 0 118207 808 808e/refarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE2019101720190910
160884412 0 115759 808 792e/refarmclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE2019101720190910
165503552 0 413274 800 792e/mergedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
169861532 0 19639 752 792e/refclang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
171041992 0 411730 800 792e/regsgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
174461980 0 110087 752 792e/regsclang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720190910
203761824 0 410550 784 784e/regsgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
217991664 0 410406 784 784e/refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
221311992 0 411722 800 792e/refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
232402432 0 412154 800 792e/refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910
250602892 0 412618 800 792e/regsgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101720190910

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:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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