Implementation notes: amd64, avx512imath, crypto_kem/ntskem13136

Computer: avx512imath
Architecture: amd64
CPU ID: GenuineIntel-00050657-bfebfbff
SUPERCOP version: 20210125
Operation: crypto_kem
Primitive: ntskem13136

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1613243	91058 84 16	116658 956 1808	`T:avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
1655969	89584 84 16	115026 956 1808	`T:avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
1661355	113009 84 16	141306 956 1808	`T:avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
1691709	82524 84 16	106881 948 1776	`T:avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
1844067	82664 84 16	108274 956 1808	`T:sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
2111020	106624 84 16	134986 956 1808	`T:sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
2166031	81438 84 16	106962 956 1808	`T:sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
2182053	76121 84 16	100537 948 1776	`T:sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
3261151	124907 84 16	154714 956 1808	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
3417093	76700 84 16	103938 956 1808	`T:opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
3711682	75364 84 16	102434 956 1808	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
3824459	70231 84 16	96073 948 1776	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
27104229	37274 76 16	67250 924 1808	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
28151802	26736 76 16	53954 924 1808	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
28821207	24916 76 16	51970 924 1808	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125
29992193	21287 76 16	47073 916 1776	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210324	20210125

Namespace violations

Implementation: T:avx2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bitslice_bma_128.o bitslice_bma T
bitslice_fft_256.o _twist_factors13_136_128 R
bitslice_fft_256.o bitslice_fft13_256 T
bitslice_fft_256.o twiddle_factors R
bitslice_fft_256.o twist_factors D
ff.o bitslice_mul13_128 T
ff.o bitslice_mul13_256 T
ff.o bitslice_mul13_64 T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_13 T
ff.o ff_mul_13 T
ff.o ff_reduce_13 T
ff.o ff_release T
ff.o ff_sqr_13 T
ff.o vector_ff_inv_13 T
ff.o vector_ff_mul_13 T
ff.o vector_ff_pow16_13 T
ff.o vector_ff_pow4_13 T
ff.o vector_ff_pow8_13 T
ff.o vector_ff_sqr_13 T
ff.o vector_ff_sqr_inv_13 T
ff.o vector_ff_transpose_xor_13 T
keccak.o shake_256 T
m4r.o _gray_codes_lut D
m4r.o _gray_codes_lut2 R
m4r.o _gray_codes_lut3 R
m4r.o _gray_codes_lut4 R
m4r.o _gray_codes_lut5 R
m4r.o _gray_codes_lut6 R
m4r.o _gray_codes_lut7 R
m4r.o _gray_codes_lut8 R
m4r.o _m4ri_gauss_submatrix T
m4r.o _m4ri_make_table_rev T
m4r.o m4r_rref T
matrix_ff2.o alloc_matrix_ff2 T
matrix_ff2.o calloc_matrix_ff2 T
matrix_ff2.o clone_matrix_ff2 T
matrix_ff2.o column_swap_matrix_ff2 T
matrix_ff2.o free_matrix_ff2 T
matrix_ff2.o is_equal_matrix_ff2 T
matrix_ff2.o reduce_row_echelon_matrix_ff2 T
matrix_ff2.o zero_matrix_ff2 T
nts_kem.o compute_syndrome T
nts_kem.o correct_error_and_recover_ke T
nts_kem.o create_matrix_G T
nts_kem.o create_random_goppa_polynomial T
nts_kem.o deserialise_private_key T
nts_kem.o fisher_yates_shuffle T
nts_kem.o is_valid_goppa_polynomial T
nts_kem.o load_input_ciphertext T
nts_kem.o nts_kem_ciphertext_size T
nts_kem.o nts_kem_create T
nts_kem.o nts_kem_decapsulate T
nts_kem.o nts_kem_encapsulate T
nts_kem.o nts_kem_init_from_private_key T
nts_kem.o nts_kem_key_size T
nts_kem.o nts_kem_release T
nts_kem.o pack_buffer T
nts_kem.o random_vector T
nts_kem.o serialise_private_key T
nts_kem.o serialise_public_key T
nts_kem.o unpack_buffer T
polynomial.o clone_poly T
polynomial.o create_random_poly T
polynomial.o evaluate_poly T
polynomial.o formal_derivative_poly T
polynomial.o free_poly T
polynomial.o gcd_poly T
polynomial.o init_poly T
polynomial.o is_equal_poly T
polynomial.o modulo_reduce_poly T
polynomial.o poly_from_roots T
polynomial.o update_poly_degree T
polynomial.o zero_poly T
random.o random_uint16_bounded T
random.o randombit T
utils.o cpucycles T
utils.o cpucycles_persecond T
vector_utils.o vector_ff_or_256 T
vector_utils.o vector_ff_or_64 T
vector_utils.o vector_load_1d_128 T
vector_utils.o vector_load_1d_256 T
vector_utils.o vector_load_1d_64 T
vector_utils.o vector_load_2d_128 T
vector_utils.o vector_load_2d_256 T
vector_utils.o vector_load_2d_64 T
vector_utils.o vector_store_1d_256 T
vector_utils.o vector_store_1d_64 T
vector_utils.o vector_store_2d_256 T
vector_utils.o vector_store_2d_64 T

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:avx2

Namespace violations

Implementation: T:opt
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bitslice_bma_64.o bitslice_bma T
bitslice_fft_64.o _twist_factors13_136_64 R
bitslice_fft_64.o bitslice_fft13_64 T
bitslice_fft_64.o twiddle_factors R
bitslice_fft_64.o twist_factors D
ff.o bitslice_mul13_64 T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_13 T
ff.o ff_mul_13 T
ff.o ff_reduce_13 T
ff.o ff_release T
ff.o ff_sqr_13 T
ff.o vector_ff_inv_13 T
ff.o vector_ff_mul_13 T
ff.o vector_ff_pow16_13 T
ff.o vector_ff_pow4_13 T
ff.o vector_ff_pow8_13 T
ff.o vector_ff_sqr_13 T
ff.o vector_ff_sqr_inv_13 T
ff.o vector_ff_transpose_xor_13 T
keccak.o shake_256 T
m4r.o _gray_codes_lut D
m4r.o _gray_codes_lut2 R
m4r.o _gray_codes_lut3 R
m4r.o _gray_codes_lut4 R
m4r.o _gray_codes_lut5 R
m4r.o _gray_codes_lut6 R
m4r.o _gray_codes_lut7 R
m4r.o _gray_codes_lut8 R
m4r.o _m4ri_gauss_submatrix T
m4r.o _m4ri_make_table_rev T
m4r.o m4r_rref T
matrix_ff2.o alloc_matrix_ff2 T
matrix_ff2.o calloc_matrix_ff2 T
matrix_ff2.o clone_matrix_ff2 T
matrix_ff2.o column_swap_matrix_ff2 T
matrix_ff2.o free_matrix_ff2 T
matrix_ff2.o is_equal_matrix_ff2 T
matrix_ff2.o reduce_row_echelon_matrix_ff2 T
matrix_ff2.o zero_matrix_ff2 T
nts_kem.o compute_syndrome T
nts_kem.o correct_error_and_recover_ke T
nts_kem.o create_matrix_G T
nts_kem.o create_random_goppa_polynomial T
nts_kem.o deserialise_private_key T
nts_kem.o fisher_yates_shuffle T
nts_kem.o is_valid_goppa_polynomial T
nts_kem.o load_input_ciphertext T
nts_kem.o nts_kem_ciphertext_size T
nts_kem.o nts_kem_create T
nts_kem.o nts_kem_decapsulate T
nts_kem.o nts_kem_encapsulate T
nts_kem.o nts_kem_init_from_private_key T
nts_kem.o nts_kem_key_size T
nts_kem.o nts_kem_release T
nts_kem.o pack_buffer T
nts_kem.o random_vector T
nts_kem.o serialise_private_key T
nts_kem.o serialise_public_key T
nts_kem.o unpack_buffer T
polynomial.o clone_poly T
polynomial.o create_random_poly T
polynomial.o evaluate_poly T
polynomial.o formal_derivative_poly T
polynomial.o free_poly T
polynomial.o gcd_poly T
polynomial.o init_poly T
polynomial.o is_equal_poly T
polynomial.o modulo_reduce_poly T
polynomial.o poly_from_roots T
polynomial.o update_poly_degree T
polynomial.o zero_poly T
random.o random_uint16_bounded T
random.o randombit T
vector_utils.o vector_ff_or_64 T
vector_utils.o vector_load_1d_64 T
vector_utils.o vector_load_2d_64 T
vector_utils.o vector_store_1d_64 T
vector_utils.o vector_store_2d_64 T

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

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

Namespace violations

Implementation: T:ref
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

additive_fft.o _additive_fft_construct_basis T
additive_fft.o _additive_fft_core T
additive_fft.o _additive_fft_ff_value T
additive_fft.o additive_fft T
additive_fft.o ff_poly_taylor_expansion T
berlekamp_massey.o berlekamp_massey T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_13 T
ff.o ff_mul_13 T
ff.o ff_reduce_13 T
ff.o ff_release T
ff.o ff_sqr_13 T
keccak.o Keccak T
keccak.o KeccakF1600_StatePermute T
keccak.o LFSR86540 T
keccak.o sha3_256 T
keccak.o sha3_384 T
keccak.o sha3_512 T
keccak.o shake_256 T
m4r.o _gray_codes_lut D
m4r.o _gray_codes_lut2 R
m4r.o _gray_codes_lut3 R
m4r.o _gray_codes_lut4 R
m4r.o _gray_codes_lut5 R
m4r.o _gray_codes_lut6 R
m4r.o _gray_codes_lut7 R
m4r.o _gray_codes_lut8 R
m4r.o _m4ri_gauss_submatrix T
m4r.o _m4ri_make_table_rev T
m4r.o m4r_rref T
matrix_ff2.o alloc_matrix_ff2 T
matrix_ff2.o calloc_matrix_ff2 T
matrix_ff2.o clone_matrix_ff2 T
matrix_ff2.o column_swap_matrix_ff2 T
matrix_ff2.o free_matrix_ff2 T
matrix_ff2.o is_equal_matrix_ff2 T
matrix_ff2.o reduce_row_echelon_matrix_ff2 T
matrix_ff2.o zero_matrix_ff2 T
nts_kem.o compute_syndrome T
nts_kem.o correct_error_and_recover_ke T
nts_kem.o create_matrix_G T
nts_kem.o create_random_goppa_polynomial T
nts_kem.o deserialise_private_key T
nts_kem.o fisher_yates_shuffle T
nts_kem.o is_valid_goppa_polynomial T
nts_kem.o nts_kem_ciphertext_size T
nts_kem.o nts_kem_create T
nts_kem.o nts_kem_decapsulate T
nts_kem.o nts_kem_encapsulate T
nts_kem.o nts_kem_init_from_private_key T
nts_kem.o nts_kem_key_size T
nts_kem.o nts_kem_release T
nts_kem.o pack_buffer T
nts_kem.o random_vector T
nts_kem.o serialise_private_key T
nts_kem.o serialise_public_key T
nts_kem.o unpack_buffer T
polynomial.o clone_poly T
polynomial.o create_random_poly T
polynomial.o evaluate_poly T
polynomial.o formal_derivative_poly T
polynomial.o free_poly T
polynomial.o gcd_poly T
polynomial.o init_poly T
polynomial.o is_equal_poly T
polynomial.o modulo_reduce_poly T
polynomial.o poly_from_roots T
polynomial.o update_poly_degree T
polynomial.o zero_poly T
random.o random_uint16_bounded T
random.o randombit T
stack.o stack_create T
stack.o stack_free T
stack.o stack_pop T
stack.o stack_push T
stack.o stack_size T

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

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

Namespace violations

Implementation: T:sse2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bitslice_bma_128.o bitslice_bma T
bitslice_fft_128.o _twist_factors13_136_128 R
bitslice_fft_128.o bitslice_fft13_128 T
bitslice_fft_128.o twiddle_factors R
bitslice_fft_128.o twist_factors D
ff.o bitslice_mul13_128 T
ff.o bitslice_mul13_64 T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_13 T
ff.o ff_mul_13 T
ff.o ff_reduce_13 T
ff.o ff_release T
ff.o ff_sqr_13 T
ff.o vector_ff_inv_13 T
ff.o vector_ff_mul_13 T
ff.o vector_ff_pow16_13 T
ff.o vector_ff_pow4_13 T
ff.o vector_ff_pow8_13 T
ff.o vector_ff_sqr_13 T
ff.o vector_ff_sqr_inv_13 T
ff.o vector_ff_transpose_xor_13 T
keccak.o shake_256 T
m4r.o _gray_codes_lut D
m4r.o _gray_codes_lut2 R
m4r.o _gray_codes_lut3 R
m4r.o _gray_codes_lut4 R
m4r.o _gray_codes_lut5 R
m4r.o _gray_codes_lut6 R
m4r.o _gray_codes_lut7 R
m4r.o _gray_codes_lut8 R
m4r.o _m4ri_gauss_submatrix T
m4r.o _m4ri_make_table_rev T
m4r.o m4r_rref T
matrix_ff2.o alloc_matrix_ff2 T
matrix_ff2.o calloc_matrix_ff2 T
matrix_ff2.o clone_matrix_ff2 T
matrix_ff2.o column_swap_matrix_ff2 T
matrix_ff2.o free_matrix_ff2 T
matrix_ff2.o is_equal_matrix_ff2 T
matrix_ff2.o reduce_row_echelon_matrix_ff2 T
matrix_ff2.o zero_matrix_ff2 T
nts_kem.o compute_syndrome T
nts_kem.o correct_error_and_recover_ke T
nts_kem.o create_matrix_G T
nts_kem.o create_random_goppa_polynomial T
nts_kem.o deserialise_private_key T
nts_kem.o fisher_yates_shuffle T
nts_kem.o is_valid_goppa_polynomial T
nts_kem.o load_input_ciphertext T
nts_kem.o nts_kem_ciphertext_size T
nts_kem.o nts_kem_create T
nts_kem.o nts_kem_decapsulate T
nts_kem.o nts_kem_encapsulate T
nts_kem.o nts_kem_init_from_private_key T
nts_kem.o nts_kem_key_size T
nts_kem.o nts_kem_release T
nts_kem.o pack_buffer T
nts_kem.o random_vector T
nts_kem.o serialise_private_key T
nts_kem.o serialise_public_key T
nts_kem.o unpack_buffer T
polynomial.o clone_poly T
polynomial.o create_random_poly T
polynomial.o evaluate_poly T
polynomial.o formal_derivative_poly T
polynomial.o free_poly T
polynomial.o gcd_poly T
polynomial.o init_poly T
polynomial.o is_equal_poly T
polynomial.o modulo_reduce_poly T
polynomial.o poly_from_roots T
polynomial.o update_poly_degree T
polynomial.o zero_poly T
random.o random_uint16_bounded T
random.o randombit T
utils.o cpucycles T
utils.o cpucycles_persecond T
vector_utils.o vector_ff_or_128 T
vector_utils.o vector_ff_or_64 T
vector_utils.o vector_load_1d_128 T
vector_utils.o vector_load_1d_64 T
vector_utils.o vector_load_2d_128 T
vector_utils.o vector_load_2d_64 T
vector_utils.o vector_store_1d_128 T
vector_utils.o vector_store_1d_64 T
vector_utils.o vector_store_2d_128 T
vector_utils.o vector_store_2d_64 T

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2