Implementation notes: amd64, jasper, crypto_kem/ntskem1264

Compiler output

bitslice_fft_256.c: bitslice_fft_256.c:87:25: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx'
bitslice_fft_256.c:             out[i][b] = _mm256_set_epi64x(-((in[0][b] >> reversal[4*i+3]) & 1),
bitslice_fft_256.c:                         ^
bitslice_fft_256.c: bitslice_fft_256.c:87:25: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bitslice_fft_256.c: bitslice_fft_256.c:99:22: error: '__builtin_ia32_pshufd256' needs target feature avx2
bitslice_fft_256.c:                 vb = _mm256_shuffle_epi32(tmp[b], _MM_SHUFFLE(3, 2, 3, 2));
bitslice_fft_256.c:                      ^
bitslice_fft_256.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:470:12: note: expanded from macro '_mm256_shuffle_epi32'
bitslice_fft_256.c:   (__m256i)__builtin_ia32_pshufd256((__v8si)(__m256i)(a), (int)(imm))
bitslice_fft_256.c:            ^
bitslice_fft_256.c: bitslice_fft_256.c:100:22: error: '__builtin_ia32_pslldqi256_byteshift' needs target feature avx2
bitslice_fft_256.c:                 va = _mm256_slli_si256(out[k][b], 8);
bitslice_fft_256.c:                      ^
bitslice_fft_256.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:497:12: note: expanded from macro '_mm256_slli_si256'
bitslice_fft_256.c:   (__m256i)__builtin_ia32_pslldqi256_byteshift((__v4di)(__m256i)(a), (int)(imm))
bitslice_fft_256.c:            ^
bitslice_fft_256.c: bitslice_fft_256.c:101:22: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx2'
bitslice_fft_256.c:                 vb = _mm256_xor_si256(va, vb);
bitslice_fft_256.c:                      ^
bitslice_fft_256.c: bitslice_fft_256.c:101:22: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bitslice_fft_256.c: bitslice_fft_256.c:102:29: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx2'
bitslice_fft_256.c:                 out[k][b] = _mm256_xor_si256(out[k][b], vb);
bitslice_fft_256.c:                             ^
bitslice_fft_256.c: bitslice_fft_256.c:102:29: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bitslice_fft_256.c: bitslice_fft_256.c:112:22: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'bitslice_butterflies12_256' that is compiled without support for 'avx'
bitslice_fft_256.c: ...

Compiler output

bitslice_fft_256.c: bitslice_fft_256.c: In function 'bitslice_butterflies12_256':
bitslice_fft_256.c: bitslice_fft_256.c:87:23: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
bitslice_fft_256.c:    87 |             out[i][b] = _mm256_set_epi64x(-((in[0][b] >> reversal[4*i+3]) & 1),
bitslice_fft_256.c:       |             ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    88 |                                           -((in[0][b] >> reversal[4*i+2]) & 1),
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    89 |                                           -((in[0][b] >> reversal[4*i+1]) & 1),
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    90 |                                           -((in[0][b] >> reversal[4*i+0]) & 1));
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:51,
bitslice_fft_256.c:                  from bitslice_fft_256.h:21,
bitslice_fft_256.c:                  from bitslice_fft_256.c:18:
bitslice_fft_256.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avxintrin.h:1296:1: error: inlining failed in call to 'always_inline' '_mm256_set_epi64x': target specific option mismatch
bitslice_fft_256.c:  1296 | _mm256_set_epi64x (long long __A, long long __B, long long __C,
bitslice_fft_256.c:       | ^~~~~~~~~~~~~~~~~
bitslice_fft_256.c: bitslice_fft_256.c:87:25: note: called from here
bitslice_fft_256.c:    87 |             out[i][b] = _mm256_set_epi64x(-((in[0][b] >> reversal[4*i+3]) & 1),
bitslice_fft_256.c:       |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    88 |                                           -((in[0][b] >> reversal[4*i+2]) & 1),
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    89 |                                           -((in[0][b] >> reversal[4*i+1]) & 1),
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c:    90 |                                           -((in[0][b] >> reversal[4*i+0]) & 1));
bitslice_fft_256.c:       |                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_fft_256.c: ...

Namespace violations

bitslice_bma_64.o bitslice_bma T
bitslice_fft_64.o _twist_factors12_64_64 R
bitslice_fft_64.o a64_consts_64 D
bitslice_fft_64.o bitslice_fft12_64 T
bitslice_fft_64.o twiddle_factors R
bitslice_fft_64.o twist_factors D
ff.o bitslice_mul12_64 T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_12 T
ff.o ff_mul_12 T
ff.o ff_reduce_12 T
ff.o ff_release T
ff.o ff_sqr_12 T
ff.o vector_ff_inv_12 T
ff.o vector_ff_mul_12 T
ff.o vector_ff_pow16_12 T
ff.o vector_ff_pow4_12 T
ff.o vector_ff_pow8_12 T
ff.o vector_ff_sqr_12 T
ff.o vector_ff_sqr_inv_12 T
ff.o vector_ff_transpose_xor_12 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

Namespace violations

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_12 T
ff.o ff_mul_12 T
ff.o ff_reduce_12 T
ff.o ff_release T
ff.o ff_sqr_12 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

Namespace violations

bitslice_bma_128.o bitslice_bma T
bitslice_fft_128.o _twist_factors12_64_64 R
bitslice_fft_128.o a64_consts_128 D
bitslice_fft_128.o bitslice_fft12_128 T
bitslice_fft_128.o twiddle_factors R
bitslice_fft_128.o twist_factors D
ff.o bitslice_mul12_128 T
ff.o bitslice_mul12_64 T
ff.o ff_add_m T
ff.o ff_create T
ff.o ff_inv_12 T
ff.o ff_mul_12 T
ff.o ff_reduce_12 T
ff.o ff_release T
ff.o ff_sqr_12 T
ff.o vector_ff_inv_12 T
ff.o vector_ff_mul_12 T
ff.o vector_ff_pow16_12 T
ff.o vector_ff_pow4_12 T
ff.o vector_ff_pow8_12 T
ff.o vector_ff_sqr_12 T
ff.o vector_ff_sqr_inv_12 T
ff.o vector_ff_transpose_xor_12 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