Implementation notes: aarch64, jetsontx1, crypto_hash/simd256

Computer: jetsontx1
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20191017
Operation: crypto_hash
Primitive: simd256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
61935	51852 0 0	61711 792 744	`sphlib`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
73530	46340 0 0	55047 792 728	`sphlib`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
75348	44600 0 0	56671 808 736	`sphlib`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
75510	43332 0 0	54017 760 736	`sphlib`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
75513	41300 0 0	49969 760 720	`sphlib`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
75527	42584 0 0	52655 808 720	`sphlib`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
75587	41300 0 0	49969 760 720	`sphlib`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
77299	40604 0 0	47383 752 720	`sphlib`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
80267	43816 0 0	52407 792 728	`sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
82446	29156 0 0	39055 792 744	`sphlib-small`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
90919	24268 0 0	32929 760 720	`sphlib-small`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
90943	24268 0 0	32929 760 720	`sphlib-small`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
90999	27096 0 0	37777 760 736	`sphlib-small`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
91234	28316 0 0	40415 808 736	`sphlib-small`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
91780	25540 0 0	35639 808 720	`sphlib-small`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
91896	24732 0 0	33463 792 728	`sphlib-small`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
94949	22292 0 0	29079 752 720	`sphlib-small`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
102688	25536 0 0	34167 792 728	`sphlib-small`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
106689	45811 388 0	55878 1212 744	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
117737	42108 0 0	49883 776 720	`sphlib`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
124863	33335 388 0	44050 1220 736	`opt`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
125110	25395 388 0	35162 1220 720	`opt`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
125602	27669 388 0	38028 1172 736	`opt`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
126994	22789 388 0	31676 1172 720	`opt`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
127031	22789 388 0	31676 1172 720	`opt`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
133798	15051 388 0	23934 1204 728	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
138055	23924 0 0	31723 776 720	`sphlib-small`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
146167	13429 388 0	20426 1164 720	`opt`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
153990	15915 388 0	24694 1204 728	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
187088	13223 388 0	21178 1188 720	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
2466595	22385 388 0	33300 1172 736	`ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
2468033	20931 388 0	33162 1220 736	`ref`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O3_-fPIC_-fPIE`	20191017	20190910
2473568	12081 388 0	20980 1172 720	`ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
2473900	12081 388 0	20980 1172 720	`ref`	`clang_-mcpu=native_-march=armv8a+crypto_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
2481814	12219 388 0	22442 1220 720	`ref`	`armclang_-march=armv8a+crypto_-mcpu=cortex-a57_-mtune=cortex-a57_-O2_-fPIC_-fPIE`	20191017	20190910
2524191	4077 388 0	11074 1164 720	`ref`	`clang_-mcpu=native_-march=armv8a+crypto_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191017	20190910
2689093	11263 388 0	21318 1212 744	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
2720905	5023 388 0	13894 1204 728	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
2981518	4859 388 0	13606 1204 728	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910
4569729	4331 388 0	12242 1188 720	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191017	20190910

Compiler output

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

reference.c: reference.c:69:82: warning: expression result unused [-Wunused-value]
reference.c: state->A[j] = state->D[j] + w[j] + F(state->A[j], state->B[j], state->C[j]), s;
reference.c: ^
reference.c: 1 warning generated.

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

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

Compiler output

Implementation: vect128
Security model: unknown
Compiler: armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE

vector.c: In file included from vector.c:5:
vector.c: ./vector.h:252:2: error: "I don't know how to vectorize on this architecture."
vector.c: #error "I don't know how to vectorize on this architecture."
vector.c: ^
vector.c: ./vector.h:344:38: error: array has incomplete element type 'const union cv'
vector.c: static const union cv FFT64_Twiddle[] = {
vector.c: ^
vector.c: ./vector.h:344:22: note: forward declaration of 'union cv'
vector.c: static const union cv FFT64_Twiddle[] = {
vector.c: ^
vector.c: ./vector.h:355:39: error: array has incomplete element type 'const union cv'
vector.c: static const union cv FFT128_Twiddle[] = {
vector.c: ^
vector.c: ./vector.h:344:22: note: forward declaration of 'union cv'
vector.c: static const union cv FFT64_Twiddle[] = {
vector.c: ^
vector.c: ./vector.h:367:39: error: array has incomplete element type 'const union cv'
vector.c: static const union cv FFT256_Twiddle[] = {
vector.c: ^
vector.c: ./vector.h:344:22: note: forward declaration of 'union cv'
vector.c: static const union cv FFT64_Twiddle[] = {
vector.c: ^
vector.c: vector.c:24:30: warning: implicit declaration of function 'CV' is invalid in C99 [-Wimplicit-function-declaration]
vector.c: static const union cv V128 = CV(128);
vector.c: ^
vector.c: ...

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

Compiler	Implementations
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O2 -fPIC -fPIE	vect128
armclang -march=armv8a+crypto -mcpu=cortex-a57 -mtune=cortex-a57 -O3 -fPIC -fPIE	vect128
clang -mcpu=native -march=armv8a+crypto -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	vect128
clang -mcpu=native -march=armv8a+crypto -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	vect128
clang -mcpu=native -march=armv8a+crypto -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	vect128
clang -mcpu=native -march=armv8a+crypto -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	vect128

Compiler output

Implementation: vect128
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

vector.c: In file included from vector.c:5:
vector.c: vector.h:252:2: error: #error "I don't know how to vectorize on this architecture."
vector.c: #error "I don't know how to vectorize on this architecture."
vector.c: ^~~~~
vector.c: vector.h:344:25: error: array type has incomplete element type 'union cv'
vector.c: static const union cv FFT64_Twiddle[] = {
vector.c: ^~~~~~~~~~~~~
vector.c: vector.h:355:25: error: array type has incomplete element type 'union cv'
vector.c: static const union cv FFT128_Twiddle[] = {
vector.c: ^~~~~~~~~~~~~~
vector.c: vector.h:367:25: error: array type has incomplete element type 'union cv'
vector.c: static const union cv FFT256_Twiddle[] = {
vector.c: ^~~~~~~~~~~~~~
vector.c: vector.c:24:20: error: variable 'V128' has initializer but incomplete type
vector.c: static const union cv V128 = CV(128);
vector.c: ^~
vector.c: vector.c:24:30: warning: implicit declaration of function 'CV' [-Wimplicit-function-declaration]
vector.c: static const union cv V128 = CV(128);
vector.c: ^~
vector.c: vector.c:25:20: error: variable 'V255' has initializer but incomplete type
vector.c: static const union cv V255 = CV(255);
vector.c: ^~
vector.c: vector.c:26:20: error: variable 'V257' has initializer but incomplete type
vector.c: static const union cv V257 = CV(257);
vector.c: ^~
vector.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	vect128
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	vect128
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	vect128
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	vect128

Namespace violations

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

nist.o Final T
nist.o Hash T
nist.o IV_224 D
nist.o IV_256 D
nist.o IV_384 D
nist.o IV_512 D
nist.o IncreaseCounter T
nist.o Init T
nist.o InitIV T
nist.o Update T
optimized.o FFT_128_full T
optimized.o FFT_128_halfzero T
optimized.o FFT_256_halfzero T
optimized.o FFT_64 T
optimized.o RequiredAlignment T
optimized.o Round4 T
optimized.o Round8 T
optimized.o SIMD_Compress T
optimized.o SupportedLength T
optimized.o VERSION T
optimized.o fft128_natural T
optimized.o fft256_natural T
optimized.o p8_xor R
optimized.o revbin T

Number of similar (compiler,implementation) pairs: 10, namely:

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

Namespace violations

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

nist.o Final T
nist.o Hash T
nist.o IV_224 D
nist.o IV_256 D
nist.o IV_384 D
nist.o IV_512 D
nist.o IncreaseCounter T
nist.o Init T
nist.o InitIV T
nist.o Update T
reference.o IF T
reference.o MAJ T
reference.o P R
reference.o RequiredAlignment T
reference.o Round T
reference.o SIMD_Compress T
reference.o Step T
reference.o SupportedLength T
reference.o VERSION T
reference.o message_expansion T
reference.o p4 R
reference.o p8 R

Number of similar (compiler,implementation) pairs: 10, namely:

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

Namespace violations

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

simd.o sph_simd224 T
simd.o sph_simd224_addbits_and_close T
simd.o sph_simd224_close T
simd.o sph_simd224_init T
simd.o sph_simd256 T
simd.o sph_simd256_addbits_and_close T
simd.o sph_simd256_close T
simd.o sph_simd256_init T
simd.o sph_simd384 T
simd.o sph_simd384_addbits_and_close T
simd.o sph_simd384_close T
simd.o sph_simd384_init T
simd.o sph_simd512 T
simd.o sph_simd512_addbits_and_close T
simd.o sph_simd512_close T
simd.o sph_simd512_init T

Number of similar (compiler,implementation) pairs: 20, namely:

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