Implementation notes: amd64, latour, crypto_kem/ntskem13136

Computer: latour
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20201130
Operation: crypto_kem
Primitive: ntskem13136

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
4673655	103443 84 16	120393 984 1568	`T:sse2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
4742658	105235 84 16	123201 984 1568	`T:sse2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
4772349	103443 84 16	120393 984 1568	`T:sse2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
4951962	86292 84 16	102183 976 1568	`T:sse2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
6442821	104078 84 16	122286 888 1632	`T:opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
6502077	102860 84 16	120590 888 1632	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
6632172	96672 84 16	116113 984 1568	`T:opt`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
6764193	95263 84 16	113737 984 1568	`T:opt`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
6797412	96576 84 16	115905 984 1568	`T:opt`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
6929181	78231 84 16	95599 976 1568	`T:opt`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
7770033	138584 84 16	158902 888 1632	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
7904394	70295 84 16	87061 880 1600	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
8399655	95263 84 16	113737 984 1568	`T:opt`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
38594232	35112 76 16	54457 944 1568	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
38659212	31674 76 16	50097 944 1568	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
38686689	31674 76 16	50097 944 1568	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
40090527	34980 76 16	54249 944 1568	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
41402637	22413 76 16	39639 936 1568	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200904	20200826
44131104	24969 76 16	43150 856 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
44540199	38658 76 16	58830 856 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
44602551	23554 76 16	41214 856 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826
50297481	20637 76 16	37365 848 1600	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200904	20200826

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bitslice_fft_256.c: bitslice_fft_256.c:103:29: error: always_inline function '_mm256_setr_epi32' requires target feature 'xsave', but would be inlined into function 'bitslice_butterflies13_256' that is compiled without support for 'xsave'
bitslice_fft_256.c: const __m256i mask256 = _mm256_setr_epi32(0, 2, 4, 6, 1, 3, 5, 7);
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:127:25: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'bitslice_butterflies13_256' that is compiled without support for 'xsave'
bitslice_fft_256.c: out[j][i] = _mm256_set_epi32(-u32[7], -u32[6], -u32[5], -u32[4],
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:140:20: error: always_inline function '_mm256_permutevar8x32_epi32' requires target feature 'xsave', but would be inlined into function 'bitslice_butterflies13_256' that is compiled without support for 'xsave'
bitslice_fft_256.c: t[0] = _mm256_permutevar8x32_epi32(out[ j ][b], mask256);
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:141:20: error: always_inline function '_mm256_permutevar8x32_epi32' requires target feature 'xsave', but would be inlined into function 'bitslice_butterflies13_256' that is compiled without support for 'xsave'
bitslice_fft_256.c: t[1] = _mm256_permutevar8x32_epi32(out[j+1][b], mask256);
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:142:20: error: '__builtin_ia32_permti256' needs target feature avx2
bitslice_fft_256.c: v[b] = _mm256_permute2x128_si256(t[0], t[1], 0x20);
bitslice_fft_256.c: ^
bitslice_fft_256.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:882:12: note: expanded from macro '_mm256_permute2x128_si256'
bitslice_fft_256.c: (__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (M)); })
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:143:20: error: always_inline function '_mm256_setzero_si256' requires target feature 'xsave', but would be inlined into function 'bitslice_butterflies13_256' that is compiled without support for 'xsave'
bitslice_fft_256.c: v[b] = _mm256_permute4x64_epi64(v[b], 0xD8);
bitslice_fft_256.c: ^
bitslice_fft_256.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
bitslice_fft_256.c: (__v4di)_mm256_setzero_si256(), \
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:144:20: error: '__builtin_ia32_permti256' needs target feature avx2
bitslice_fft_256.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bitslice_bma_128.c: bitslice_bma_128.c:315:21: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'bitslice_bma' that is compiled without support for 'ssse3'
bitslice_bma_128.c: out[1][j] = _mm_shuffle_epi8(out[0][j], mask);
bitslice_bma_128.c: ^
bitslice_bma_128.c: bitslice_bma_128.c:316:21: error: '__builtin_ia32_palignr128' needs target feature ssse3
bitslice_bma_128.c: out[0][j] = _mm_alignr_epi8(out[0][j], psi[0][j], 15);
bitslice_bma_128.c: ^
bitslice_bma_128.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/tmmintrin.h:69:12: note: expanded from macro '_mm_alignr_epi8'
bitslice_bma_128.c: (__m128i)__builtin_ia32_palignr128((__v16qi)(__m128i)(a), \
bitslice_bma_128.c: ^
bitslice_bma_128.c: 2 errors generated.

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:avx2 T:sse2

Compiler output

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

bitslice_fft_256.c: bitslice_fft_256.c: In function 'bitslice_butterflies13_256':
bitslice_fft_256.c: bitslice_fft_256.c:103:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
bitslice_fft_256.c: const __m256i mask256 = _mm256_setr_epi32(0, 2, 4, 6, 1, 3, 5, 7);
bitslice_fft_256.c: ^
bitslice_fft_256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
bitslice_fft_256.c: from bitslice_fft_256.h:21,
bitslice_fft_256.c: from bitslice_fft_256.c:19:
bitslice_fft_256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1338:1: error: inlining failed in call to always_inline '_mm256_setr_epi32': target specific option mismatch
bitslice_fft_256.c: _mm256_setr_epi32 (int __A, int __B, int __C, int __D,
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:103:19: error: called from here
bitslice_fft_256.c: const __m256i mask256 = _mm256_setr_epi32(0, 2, 4, 6, 1, 3, 5, 7);
bitslice_fft_256.c: ^
bitslice_fft_256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
bitslice_fft_256.c: from bitslice_fft_256.h:21,
bitslice_fft_256.c: from bitslice_fft_256.c:19:
bitslice_fft_256.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1232:1: error: inlining failed in call to always_inline '_mm256_set_epi32': target specific option mismatch
bitslice_fft_256.c: _mm256_set_epi32 (int __A, int __B, int __C, int __D,
bitslice_fft_256.c: ^
bitslice_fft_256.c: bitslice_fft_256.c:127:25: error: called from here
bitslice_fft_256.c: out[j][i] = _mm256_set_epi32(-u32[7], -u32[6], -u32[5], -u32[4],
bitslice_fft_256.c: ^
bitslice_fft_256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
bitslice_fft_256.c: from bitslice_fft_256.h:21,
bitslice_fft_256.c: from bitslice_fft_256.c:19:
bitslice_fft_256.c: ...

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

Compiler output

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

nts_kem.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:37:0,
nts_kem.c: from ff.h:18,
nts_kem.c: from nts_kem.c:18:
nts_kem.c: nts_kem.c: In function 'create_matrix_G':
nts_kem.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:454:1: error: inlining failed in call to always_inline '_mm_extract_epi64': target specific option mismatch
nts_kem.c: _mm_extract_epi64 (__m128i __X, const int __N)
nts_kem.c: ^
nts_kem.c: nts_kem.c:860:22: error: called from here
nts_kem.c: v[i >> 6] |= (((_mm_extract_epi64(vh[l >> 7][j], 1) & (1ULL << (l & 63))) >> (l & 63)) << (i & 63));
nts_kem.c: ^
nts_kem.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:37:0,
nts_kem.c: from ff.h:18,
nts_kem.c: from nts_kem.c:18:
nts_kem.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:454:1: error: inlining failed in call to always_inline '_mm_extract_epi64': target specific option mismatch
nts_kem.c: _mm_extract_epi64 (__m128i __X, const int __N)
nts_kem.c: ^
nts_kem.c: nts_kem.c:863:22: error: called from here
nts_kem.c: v[i >> 6] |= (((_mm_extract_epi64(vh[l >> 7][j], 0) & (1ULL << (l & 63))) >> (l & 63)) << (i & 63));
nts_kem.c: ^
nts_kem.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:37:0,
nts_kem.c: from ff.h:18,
nts_kem.c: from nts_kem.c:18:
nts_kem.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:454:1: error: inlining failed in call to always_inline '_mm_extract_epi64': target specific option mismatch
nts_kem.c: _mm_extract_epi64 (__m128i __X, const int __N)
nts_kem.c: ^
nts_kem.c: ...

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

Namespace violations

Implementation: T:opt
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -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: 9, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt
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: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -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: 9, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ref
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: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -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
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sse2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sse2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sse2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sse2