Implementation notes: amd64, cezanne, crypto_kem/bikel1

Compiler output

aes.c: aes.c:9:4: error: "This code requries support for AES_NI and SSSE3"
aes.c: #  error "This code requries support for AES_NI and SSSE3"
aes.c:    ^
aes.c: 1 error generated.

Compiler output

decode.c: In file included from decode.c:39:
decode.c: ./gf2x.h:22:10: error: always_inline function '_mm512_loadu_si512' requires target feature 'avx512f', but would be inlined into function 'gf2x_mod_add' that is compiled without support for 'avx512f'
decode.c:     va = LOAD(&a_qwords[i]);
decode.c:          ^
decode.c: ./x86_64_intrinsic.h:40:27: note: expanded from macro 'LOAD'
decode.c: #  define LOAD(mem)       _mm512_loadu_si512((mem))
decode.c:                           ^
decode.c: In file included from decode.c:39:
decode.c: ./gf2x.h:22:10: error: AVX vector return of type '__m512i' (vector of 8 'long long' values) without 'avx512f' enabled changes the ABI
decode.c: ./x86_64_intrinsic.h:40:27: note: expanded from macro 'LOAD'
decode.c: #  define LOAD(mem)       _mm512_loadu_si512((mem))
decode.c:                           ^
decode.c: In file included from decode.c:39:
decode.c: ./gf2x.h:23:10: error: always_inline function '_mm512_loadu_si512' requires target feature 'avx512f', but would be inlined into function 'gf2x_mod_add' that is compiled without support for 'avx512f'
decode.c:     vb = LOAD(&b_qwords[i]);
decode.c:          ^
decode.c: ./x86_64_intrinsic.h:40:27: note: expanded from macro 'LOAD'
decode.c: #  define LOAD(mem)       _mm512_loadu_si512((mem))
decode.c:                           ^
decode.c: In file included from decode.c:39:
decode.c: ./gf2x.h:23:10: error: AVX vector return of type '__m512i' (vector of 8 'long long' values) without 'avx512f' enabled changes the ABI
decode.c: ./x86_64_intrinsic.h:40:27: note: expanded from macro 'LOAD'
decode.c: #  define LOAD(mem)       _mm512_loadu_si512((mem))
decode.c:                           ^
decode.c: In file included from decode.c:39:
decode.c: ...

Compiler output

decode.c: In file included from decode.c:39:
decode.c: gf2x.h: In function 'gf2x_mod_add':
decode.c: gf2x.h:22:8: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
decode.c:    22 |     va = LOAD(&a_qwords[i]);
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:55,
decode.c:                  from x86_64_intrinsic.h:20,
decode.c:                  from defs.h:103,
decode.c:                  from bike_defs.h:10,
decode.c:                  from types.h:13,
decode.c:                  from decode.h:10,
decode.c:                  from decode.c:37:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx512fintrin.h:6429:1: error: inlining failed in call to 'always_inline' '_mm512_storeu_si512': target specific option mismatch
decode.c:  6429 | _mm512_storeu_si512 (void *__P, __m512i __A)
decode.c:       | ^~~~~~~~~~~~~~~~~~~
decode.c: In file included from defs.h:103,
decode.c:                  from bike_defs.h:10,
decode.c:                  from types.h:13,
decode.c:                  from decode.h:10,
decode.c:                  from decode.c:37:
decode.c: x86_64_intrinsic.h:41:27: note: called from here
decode.c:    41 | #  define STORE(mem, reg) _mm512_storeu_si512((mem), (reg))
decode.c:       |                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: gf2x.h:25:5: note: in expansion of macro 'STORE'
decode.c:    25 |     STORE(&c_qwords[i], va ^ vb);
decode.c:       |     ^~~~~
decode.c: ...

Compiler output

decode.c: decode.c:211:15: warning: unused function 'adder_size_53' [-Wunused-function]
decode.c: _INLINE_ void adder_size_53(OUT upc_t *upc,
decode.c:               ^
decode.c: decode.c:246:15: warning: unused function 'bit_sliced_adder_test' [-Wunused-function]
decode.c: _INLINE_ void bit_sliced_adder_test(OUT upc_t *upc,
decode.c:               ^
decode.c: 2 warnings generated.
gf2x_mul.c: gf2x_mul.c:116:15: warning: function 'karatzuba' is not needed and will not be emitted [-Wunneeded-internal-declaration]
gf2x_mul.c: _INLINE_ void karatzuba(OUT uint64_t *c,
gf2x_mul.c:               ^
gf2x_mul.c: 1 warning generated.
rkara3_mul_avx2.c: rkara3_mul_avx2.c:11:9: warning: unused function 'msbyte' [-Wunused-function]
rkara3_mul_avx2.c: __m256i msbyte( __m256i a ) { return _mm256_permute4x64_epi64(_mm256_srli_si256(a,15),0xfe); } // 11,11,11,10
rkara3_mul_avx2.c:         ^
rkara3_mul_avx2.c: rkara3_mul_avx2.c:169:6: warning: unused function 'mul_2bits_test' [-Wunused-function]
rkara3_mul_avx2.c: void mul_2bits_test( uint8_t *c , const uint8_t *a , uint8_t b , int len )
rkara3_mul_avx2.c:      ^
rkara3_mul_avx2.c: 2 warnings generated.

Compiler output

rkara3_mul_avx2.c: rkara3_mul_avx2.c:169:6: warning: 'mul_2bits_test' defined but not used [-Wunused-function]
rkara3_mul_avx2.c:   169 | void mul_2bits_test( uint8_t *c , const uint8_t *a , uint8_t b , int len )
rkara3_mul_avx2.c:       |      ^~~~~~~~~~~~~~

Namespace violations

aes.o aes256_enc T
aes.o aes256_key_expansion T
aes_ctr_prf.o aes_ctr_prf T
aes_ctr_prf.o init_aes_ctr_prf_state T
decode.o compute_syndrome T
decode.o decode T
error.o bike_errno B
gf2x_inv.o gf2x_mod_inv T
gf2x_ksqr_portable.o k_squaring T
gf2x_mul.o gf2x_mod_mul T
gf2x_mul.o gf2x_mod_sqr_in_place T
gf2x_mul_pclmul.o gf2x_mul_base T
gf2x_mul_pclmul.o gf2x_sqr T
rotate_portable.o rotate_right T
sampling.o generate_error_vector T
sampling.o generate_indices_mod_z T
sampling.o generate_sparse_rep T
sampling.o get_seeds T
sampling.o sample_uniform_r_bits T
sampling.o sample_uniform_r_bits_with_fixed_prf_context T
sampling_portable.o secure_set_bits T
sha.o sha T
utilities.o r_bits_vector_weight T

Namespace violations

aes.o aes256_enc T
aes.o aes256_key_expansion T
aes_ctr_prf.o aes_ctr_prf T
aes_ctr_prf.o init_aes_ctr_prf_state T
decode.o compute_syndrome T
decode.o decode T
error.o bike_errno B
gf2x_inv.o gf2x_mod_inv T
gf2x_ksqr_portable.o k_squaring T
gf2x_mul.o gf2x_mod_mul T
gf2x_mul.o gf2x_mod_sqr_in_place T
gf2x_mul_portable.o gf2x_mul_base T
gf2x_mul_portable.o gf2x_sqr T
rotate_portable.o rotate_right T
sampling.o generate_error_vector T
sampling.o generate_indices_mod_z T
sampling.o generate_sparse_rep T
sampling.o get_seeds T
sampling.o sample_uniform_r_bits T
sampling.o sample_uniform_r_bits_with_fixed_prf_context T
sampling_portable.o secure_set_bits T
sha.o sha T
utilities.o r_bits_vector_weight T

Namespace violations

aes.o aes256_enc T
aes.o aes256_key_expansion T
aes_ctr_prf.o aes_ctr_prf T
aes_ctr_prf.o init_aes_ctr_prf_state T
decode.o compute_syndrome T
decode.o decode T
error.o bike_errno B
gf2x_inv.o gf2x_mod_inv T
gf2x_ksqr_avx2.o generate_map T
gf2x_ksqr_avx2.o k_squaring T
gf2x_mul.o gf2x_mod_mul T
gf2x_mul.o gf2x_mod_sqr_in_place T
gf2x_mul_pclmul.o gf2x_mul_base T
gf2x_mul_pclmul.o gf2x_sqr T
rotate_avx2.o rotate_right T
sampling.o generate_error_vector T
sampling.o generate_indices_mod_z T
sampling.o generate_sparse_rep T
sampling.o get_seeds T
sampling.o sample_uniform_r_bits T
sampling.o sample_uniform_r_bits_with_fixed_prf_context T
sampling_avx2.o secure_set_bits T
sha.o sha T
utilities.o r_bits_vector_weight T

Namespace violations

decode.o compute_syndrome T
decode.o dump1 T
error.o bike_errno B
gf2x_ksqr_avx2.o generate_map T
rkara3_mul_avx2.o add_shr4 T
rkara3_mul_avx2.o rkara3_mul_24576 T
sampling.o generate_indices_mod_z T
sampling.o sample_uniform_r_bits_with_fixed_prf_context T

Namespace violations

aes_ctr_prf.o aes_ctr_prf T
aes_ctr_prf.o init_aes_ctr_prf_state T
decode.o compute_syndrome T
decode.o decode T
error.o bike_errno B
gf2x_inv.o gf2x_mod_inv T
gf2x_ksqr_portable.o k_squaring T
gf2x_mul.o gf2x_mod_mul T
gf2x_mul.o gf2x_mod_sqr_in_place T
gf2x_mul_portable.o gf2x_mul_base T
gf2x_mul_portable.o gf2x_sqr T
rotate_portable.o rotate_right T
sampling.o generate_error_vector T
sampling.o generate_indices_mod_z T
sampling.o generate_sparse_rep T
sampling.o get_seeds T
sampling.o sample_uniform_r_bits T
sampling.o sample_uniform_r_bits_with_fixed_prf_context T
sampling_portable.o secure_set_bits T
utilities.o r_bits_vector_weight T