Implementation notes: amd64, hunsnivy, crypto_kem/bikel3

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

gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c:58:9: error: always_inline function '_mm256_sub_epi16' requires target feature 'avx2', but would be inlined into function 'generate_map' that is compiled without support for 'avx2'
gf2x_ksqr_avx2.c:   inc = SUB_I16(inc, vr);
gf2x_ksqr_avx2.c:         ^
gf2x_ksqr_avx2.c: ./x86_64_intrinsic.h:64:28: note: expanded from macro 'SUB_I16'
gf2x_ksqr_avx2.c: #  define SUB_I16(a, b)    _mm256_sub_epi16(a, b)
gf2x_ksqr_avx2.c:                            ^
gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c:67:17: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'generate_map' that is compiled without support for 'avx2'
gf2x_ksqr_avx2.c:       vmap[j] = ADD_I16(vmap[j], inc);
gf2x_ksqr_avx2.c:                 ^
gf2x_ksqr_avx2.c: ./x86_64_intrinsic.h:63:28: note: expanded from macro 'ADD_I16'
gf2x_ksqr_avx2.c: #  define ADD_I16(a, b)    _mm256_add_epi16(a, b)
gf2x_ksqr_avx2.c:                            ^
gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c:68:17: error: always_inline function '_mm256_cmpgt_epi16' requires target feature 'avx2', but would be inlined into function 'generate_map' that is compiled without support for 'avx2'
gf2x_ksqr_avx2.c:       vtmp[j] = CMPGT_I16(zero, vmap[j]);
gf2x_ksqr_avx2.c:                 ^
gf2x_ksqr_avx2.c: ./x86_64_intrinsic.h:70:27: note: expanded from macro 'CMPGT_I16'
gf2x_ksqr_avx2.c: #  define CMPGT_I16(a, b) _mm256_cmpgt_epi16(a, b)
gf2x_ksqr_avx2.c:                           ^
gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c:69:17: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'generate_map' that is compiled without support for 'avx2'
gf2x_ksqr_avx2.c:       vmap[j] = ADD_I16(vmap[j], vtmp[j] & vr);
gf2x_ksqr_avx2.c:                 ^
gf2x_ksqr_avx2.c: ./x86_64_intrinsic.h:63:28: note: expanded from macro 'ADD_I16'
gf2x_ksqr_avx2.c: #  define ADD_I16(a, b)    _mm256_add_epi16(a, b)
gf2x_ksqr_avx2.c:                            ^
gf2x_ksqr_avx2.c: 4 errors generated.

Compiler output

gf2x_ksqr_avx2.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
gf2x_ksqr_avx2.c:                  from x86_64_intrinsic.h:20,
gf2x_ksqr_avx2.c:                  from defs.h:103,
gf2x_ksqr_avx2.c:                  from bike_defs.h:10,
gf2x_ksqr_avx2.c:                  from types.h:13,
gf2x_ksqr_avx2.c:                  from utilities.h:13,
gf2x_ksqr_avx2.c:                  from cleanup.h:10,
gf2x_ksqr_avx2.c:                  from gf2x_ksqr_avx2.c:13:
gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c: In function 'bytes_to_bin':
gf2x_ksqr_avx2.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:433:1: error: inlining failed in call to 'always_inline' '_mm256_movemask_epi8': target specific option mismatch
gf2x_ksqr_avx2.c:   433 | _mm256_movemask_epi8 (__m256i __A)
gf2x_ksqr_avx2.c:       | ^~~~~~~~~~~~~~~~~~~~
gf2x_ksqr_avx2.c: In file included from defs.h:103,
gf2x_ksqr_avx2.c:                  from bike_defs.h:10,
gf2x_ksqr_avx2.c:                  from types.h:13,
gf2x_ksqr_avx2.c:                  from utilities.h:13,
gf2x_ksqr_avx2.c:                  from cleanup.h:10,
gf2x_ksqr_avx2.c:                  from gf2x_ksqr_avx2.c:13:
gf2x_ksqr_avx2.c: x86_64_intrinsic.h:79:23: note: called from here
gf2x_ksqr_avx2.c:    79 | #  define MOVEMASK(a) _mm256_movemask_epi8(a)
gf2x_ksqr_avx2.c:       |                       ^~~~~~~~~~~~~~~~~~~~~~~
gf2x_ksqr_avx2.c: gf2x_ksqr_avx2.c:85:17: note: in expansion of macro 'MOVEMASK'
gf2x_ksqr_avx2.c:    85 |     bin32[i]  = MOVEMASK(t);
gf2x_ksqr_avx2.c:       |                 ^~~~~~~~
gf2x_ksqr_avx2.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
gf2x_ksqr_avx2.c: ...

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:177:15: warning: unused function 'adder_size_63' [-Wunused-function]
decode.c: _INLINE_ void adder_size_63(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: decode.c:358:8: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c:                         x = _mm256_permute2x128_si256(buf[j], buf[j+128], 0x20);
decode.c:                             ^
decode.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
decode.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
decode.c:            ^
decode.c: decode.c:359:8: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c:                         y = _mm256_permute2x128_si256(buf[j], buf[j+128], 0x31);
decode.c:                             ^
decode.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:821:12: note: expanded from macro '_mm256_permute2x128_si256'
decode.c:   (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M))
decode.c:            ^
decode.c: decode.c:366:8: error: always_inline function '_mm256_unpacklo_epi64' requires target feature 'avx2', but would be inlined into function 'find_err1' that is compiled without support for 'avx2'
decode.c:                         x = _mm256_unpacklo_epi64(buf[j], buf[j+64]);
decode.c:                             ^
decode.c: decode.c:367:8: error: always_inline function '_mm256_unpackhi_epi64' requires target feature 'avx2', but would be inlined into function 'find_err1' that is compiled without support for 'avx2'
decode.c:                         y = _mm256_unpackhi_epi64(buf[j], buf[j+64]);
decode.c:                             ^
decode.c: decode.c:374:8: error: always_inline function '_mm256_unpacklo_epi64' requires target feature 'avx2', but would be inlined into function 'find_err1' that is compiled without support for 'avx2'
decode.c: ...

Compiler output

decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
decode.c:                  from x86_64_intrinsic.h:20,
decode.c:                  from defs.h:106,
decode.c:                  from bike_defs.h:10,
decode.c:                  from types.h:15,
decode.c:                  from decode.h:17,
decode.c:                  from decode.c:39:
decode.c: decode.c: In function 'find_err1':
decode.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:1081:1: error: inlining failed in call to 'always_inline' '_mm256_permute2x128_si256': target specific option mismatch
decode.c:  1081 | _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
decode.c:       | ^~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: decode.c:359:8: note: called from here
decode.c:   359 |    y = _mm256_permute2x128_si256(buf[j], buf[j+128], 0x31);
decode.c:       |        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
decode.c:                  from x86_64_intrinsic.h:20,
decode.c:                  from defs.h:106,
decode.c:                  from bike_defs.h:10,
decode.c:                  from types.h:15,
decode.c:                  from decode.h:17,
decode.c:                  from decode.c:39:
decode.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:1081:1: error: inlining failed in call to 'always_inline' '_mm256_permute2x128_si256': target specific option mismatch
decode.c:  1081 | _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
decode.c:       | ^~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: decode.c:358:8: note: called from here
decode.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_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