Guard parameter-set specific backend files

[willieyz]

• Resolves: Guard parameter-set specific backend files #937

This PR add the guard for aarch64 and x86_64 backend file by a check for the parameter set, reference from mlkem-native: Example

Checking the .o with following script:

for level in 44 65 87; do                                               
    echo "=== ML-DSA-$level ==="                                        
    objdump -t test/build/mldsa$level/mldsa/src/native/aarch64/src/*.o 2>/dev/null | \
    grep -E "_asm$" | grep -v ltmp | \                                  
    sed "s/.*_MLDSA$level_//" | sort                                    
    echo                                                                
done 

=== ML-DSA-44 ===
44_intt_asm
44_ntt_asm
44_poly_caddq_asm
44_poly_chknorm_asm
44_poly_decompose_88_asm
44_poly_pointwise_montgomery_asm
44_poly_use_hint_88_asm
44_polyvecl_pointwise_acc_montgomery_l4_asm
44_polyz_unpack_17_asm
44_rej_uniform_asm
44_rej_uniform_eta2_asm

=== ML-DSA-65 ===
65_intt_asm
65_ntt_asm
65_poly_caddq_asm
65_poly_chknorm_asm
65_poly_decompose_32_asm
65_poly_pointwise_montgomery_asm
65_poly_use_hint_32_asm
65_polyvecl_pointwise_acc_montgomery_l5_asm
65_polyz_unpack_19_asm
65_rej_uniform_asm
65_rej_uniform_eta4_asm

=== ML-DSA-87 ===
87_intt_asm
87_ntt_asm
87_poly_caddq_asm
87_poly_chknorm_asm
87_poly_decompose_32_asm
87_poly_pointwise_montgomery_asm
87_poly_use_hint_32_asm
87_polyvecl_pointwise_acc_montgomery_l7_asm
87_polyz_unpack_19_asm
87_rej_uniform_asm
87_rej_uniform_eta2_asm

=== ML-DSA-44 (x86_64) ===
44_mld_poly_chknorm_avx2
44_mld_poly_decompose_88_avx2
44_mld_poly_use_hint_88_avx2
44_mld_polyz_unpack_17_avx2
44_mld_rej_uniform_avx2
44_mld_rej_uniform_eta2_avx2
44_poly_caddq_avx2

=== ML-DSA-65 (x86_64) ===
65_mld_poly_chknorm_avx2
65_mld_poly_decompose_32_avx2
65_mld_poly_use_hint_32_avx2
65_mld_polyz_unpack_19_avx2
65_mld_rej_uniform_avx2
65_mld_rej_uniform_eta4_avx2
65_poly_caddq_avx2

=== ML-DSA-87 (x86_64) ===
87_mld_poly_chknorm_avx2
87_mld_poly_decompose_32_avx2
87_mld_poly_use_hint_32_avx2
87_mld_polyz_unpack_19_avx2
87_mld_rej_uniform_avx2
87_mld_rej_uniform_eta2_avx2
87_poly_caddq_avx2

[oqs-bot]

CBMC Results (ML-DSA-44)

Full Results (174 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	2115s	2088s	+1.3%
sign_verify_internal	✅	252s	249s	+1%
mld_attempt_signature_generation	✅	208s	213s	-2%
polyvecl_pointwise_acc_montgomery_c	✅	206s	208s	-1%
rej_uniform_native	✅	138s	130s	+6%
poly_pointwise_montgomery_c	✅	136s	140s	-3%
mld_invntt_layer	✅	115s	116s	-1%
mld_ct_memcmp	✅	82s	84s	-2%
keccak_squeezeblocks_x4	✅	45s	43s	+5%
sign_signature_internal	✅	44s	44s	+0%
mld_ntt_layer	✅	42s	45s	-7%
polyvec_matrix_expand	✅	28s	29s	-3%
fqmul	✅	21s	19s	+11%
rej_uniform	✅	21s	20s	+5%
poly_uniform_eta_4x	✅	20s	15s	+33%
rej_uniform_c	✅	19s	19s	+0%
poly_chknorm_c	✅	18s	17s	+6%
poly_uniform_4x	✅	16s	15s	+7%
polymat_permute_bitrev_to_custom	✅	16s	15s	+7%
polyt0_unpack	✅	16s	16s	+0%
mld_ntt_butterfly_block	✅	15s	11s	+36%
mld_compute_t0_t1_tr_from_sk_components	✅	14s	12s	+17%
mld_polyvecl_permute_bitrev_to_custom_native	✅	14s	12s	+17%
keccakf1600x4_permute_native	✅	13s	12s	+8%
polyeta_unpack	✅	12s	12s	+0%
polyz_unpack_c	✅	12s	11s	+9%
keccak_absorb_once_x4	✅	11s	13s	-15%
mld_check_pct	✅	10s	10s	+0%
polyveck_add	✅	9s	8s	+12%
keccakf1600_permute	✅	8s	7s	+14%
polyveck_shiftl	✅	8s	5s	+60%
sign_pk_from_sk	✅	8s	5s	+60%
keccakf1600_permute_native	✅	7s	9s	-22%
mld_h	✅	7s	5s	+40%
polyveck_ntt	✅	7s	6s	+17%
polyveck_power2round	✅	7s	6s	+17%
shake128_init	✅	7s	2s	+250%
shake256x4_absorb_once	✅	7s	3s	+133%
sign_verify	✅	7s	3s	+133%
keccak_absorb	✅	6s	6s	+0%
mld_compute_pack_z	✅	6s	4s	+50%
poly_decompose_c	✅	6s	4s	+50%
polyveck_decompose	✅	6s	7s	-14%
polyveck_unpack_eta	✅	6s	2s	+200%
make_hint	✅	5s	3s	+67%
mld_ct_cmask_nonzero_u8	✅	5s	4s	+25%
mld_sample_s1_s2_serial	✅	5s	3s	+67%
pack_sk	✅	5s	3s	+67%
poly_add	✅	5s	5s	+0%
poly_chknorm	✅	5s	2s	+150%
poly_chknorm_native	✅	5s	4s	+25%
poly_invntt_tomont_c	✅	5s	7s	-29%
poly_power2round	✅	5s	2s	+150%
poly_sub	✅	5s	2s	+150%
poly_use_hint_c	✅	5s	5s	+0%
polyt0_pack	✅	5s	3s	+67%
polyt1_unpack	✅	5s	5s	+0%
polyvec_matrix_expand_serial	✅	5s	6s	-17%
polyvec_matrix_pointwise_montgomery	✅	5s	8s	-38%
polyveck_caddq	✅	5s	6s	-17%
polyveck_invntt_tomont	✅	5s	5s	+0%
polyveck_pack_eta	✅	5s	4s	+25%
polyveck_pack_w1	✅	5s	3s	+67%
polyveck_pointwise_poly_montgomery	✅	5s	5s	+0%
polyveck_use_hint	✅	5s	3s	+67%
polyvecl_chknorm	✅	5s	4s	+25%
polyvecl_ntt	✅	5s	4s	+25%
polyvecl_uniform_gamma1_serial	✅	5s	4s	+25%
shake128_absorb	✅	5s	3s	+67%
sign	✅	5s	6s	-17%
sign_keypair_internal	✅	5s	8s	-38%
sign_open	✅	5s	8s	-38%
sign_signature_extmu	✅	5s	6s	-17%
sign_signature_pre_hash_shake256	✅	5s	5s	+0%
unpack_sk	✅	5s	3s	+67%
keccakf1600_xor_bytes (big endian)	✅	4s	2s	+100%
mld_ct_cmask_nonzero_u32	✅	4s	3s	+33%
mld_prepare_domain_separation_prefix	✅	4s	5s	-20%
mld_sample_s1_s2	✅	4s	6s	-33%
ntt_native_x86_64	✅	4s	2s	+100%
pack_pk	✅	4s	4s	+0%
poly_caddq	✅	4s	4s	+0%
poly_caddq_native	✅	4s	2s	+100%
poly_caddq_native_aarch64	✅	4s	3s	+33%
poly_decompose	✅	4s	3s	+33%
poly_pointwise_montgomery	✅	4s	4s	+0%
poly_uniform_eta	✅	4s	5s	-20%
polyeta_pack	✅	4s	5s	-20%
polyveck_chknorm	✅	4s	5s	-20%
polyveck_pack_t0	✅	4s	2s	+100%
polyveck_sub	✅	4s	5s	-20%
polyvecl_permute_bitrev_to_custom	✅	4s	3s	+33%
polyvecl_uniform_gamma1	✅	4s	3s	+33%
polyvecl_unpack_eta	✅	4s	2s	+100%
polyvecl_unpack_z	✅	4s	6s	-33%
polyz_unpack_native	✅	4s	3s	+33%
rej_eta_c	✅	4s	3s	+33%
rej_eta_native	✅	4s	5s	-20%
shake128_finalize	✅	4s	2s	+100%
shake128x4_absorb_once	✅	4s	4s	+0%
shake256_init	✅	4s	2s	+100%
sign_signature	✅	4s	3s	+33%
sign_verify_extmu	✅	4s	6s	-33%
sign_verify_pre_hash_internal	✅	4s	4s	+0%
sign_verify_pre_hash_shake256	✅	4s	6s	-33%
unpack_hints	✅	4s	6s	-33%
caddq	✅	3s	5s	-40%
decompose	✅	3s	4s	-25%
fqscale	✅	3s	2s	+50%
keccak_init	✅	3s	2s	+50%
keccakf1600_xor_bytes	✅	3s	4s	-25%
mld_ct_abs_i32	✅	3s	3s	+0%
mld_ct_get_optblocker_u32	✅	3s	4s	-25%
mld_ct_sel_int32	✅	3s	3s	+0%
mld_keccakf1600_extract_bytes	✅	3s	3s	+0%
mld_value_barrier_i64	✅	3s	3s	+0%
mld_value_barrier_u32	✅	3s	2s	+50%
montgomery_reduce	✅	3s	2s	+50%
pack_sig_z	✅	3s	5s	-40%
poly_caddq_c	✅	3s	2s	+50%
poly_decompose_native	✅	3s	5s	-40%
poly_invntt_tomont	✅	3s	5s	-40%
poly_invntt_tomont_native	✅	3s	4s	-25%
poly_make_hint	✅	3s	5s	-40%
poly_ntt_c	✅	3s	2s	+50%
poly_ntt_native	✅	3s	4s	-25%
poly_shiftl	✅	3s	4s	-25%
poly_uniform	✅	3s	5s	-40%
poly_uniform_gamma1	✅	3s	3s	+0%
poly_use_hint_native	✅	3s	4s	-25%
polyt1_pack	✅	3s	2s	+50%
polyveck_make_hint	✅	3s	4s	-25%
polyveck_reduce	✅	3s	4s	-25%
polyveck_unpack_t0	✅	3s	3s	+0%
polyvecl_pack_eta	✅	3s	4s	-25%
polyvecl_pointwise_acc_montgomery	✅	3s	3s	+0%
polyvecl_pointwise_acc_montgomery_native	✅	3s	2s	+50%
polyz_pack	✅	3s	3s	+0%
polyz_unpack	✅	3s	2s	+50%
reduce32	✅	3s	2s	+50%
rej_eta	✅	3s	5s	-40%
shake128_squeeze	✅	3s	2s	+50%
shake128x4_squeezeblocks	✅	3s	3s	+0%
shake256	✅	3s	2s	+50%
shake256_finalize	✅	3s	5s	-40%
shake256_release	✅	3s	2s	+50%
sign_keypair	✅	3s	4s	-25%
sign_signature_pre_hash_internal	✅	3s	3s	+0%
unpack_pk	✅	3s	4s	-25%
unpack_sig	✅	3s	3s	+0%
use_hint	✅	3s	3s	+0%
keccak_finalize	✅	2s	3s	-33%
keccak_squeeze	✅	2s	2s	+0%
keccakf1600_extract_bytes (big endian)	✅	2s	4s	-50%
keccakf1600x4_xor_bytes	✅	2s	2s	+0%
mld_ct_cmask_neg_i32	✅	2s	3s	-33%
mld_ct_get_optblocker_u8	✅	2s	2s	+0%
mld_value_barrier_u8	✅	2s	3s	-33%
pack_sig_c_h	✅	2s	3s	-33%
poly_challenge	✅	2s	4s	-50%
poly_ntt	✅	2s	4s	-50%
poly_pointwise_montgomery_native	✅	2s	4s	-50%
poly_reduce	✅	2s	2s	+0%
poly_uniform_gamma1_4x	✅	2s	4s	-50%
poly_use_hint	✅	2s	1s	+100%
polyw1_pack	✅	2s	4s	-50%
power2round	✅	2s	2s	+0%
shake128_release	✅	2s	2s	+0%
shake256_absorb	✅	2s	2s	+0%
shake256_squeeze	✅	2s	4s	-50%
shake256x4_squeezeblocks	✅	2s	5s	-60%
sys_check_capability	✅	2s	3s	-33%
keccakf1600x4_extract_bytes	✅	1s	2s	-50%
keccakf1600x4_permute	✅	1s	2s	-50%
mld_ct_get_optblocker_i64	✅	1s	2s	-50%

[oqs-bot]

CBMC Results (ML-DSA-87)

Full Results (174 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	2520s	2207s	+14.2%
mld_attempt_signature_generation	✅	267s	231s	+16%
sign_verify_internal	✅	240s	213s	+13%
polyvecl_pointwise_acc_montgomery_c	✅	204s	162s	+26%
poly_pointwise_montgomery_c	✅	167s	130s	+28%
rej_uniform_native	✅	161s	120s	+34%
polyvec_matrix_expand	✅	149s	128s	+16%
polyvec_matrix_expand_serial	✅	114s	101s	+13%
mld_ct_memcmp	✅	98s	78s	+26%
mld_invntt_layer	✅	80s	71s	+13%
mld_ntt_layer	✅	61s	49s	+24%
keccak_squeezeblocks_x4	✅	46s	44s	+5%
sign_signature_internal	✅	44s	40s	+10%
mld_compute_t0_t1_tr_from_sk_components	✅	25s	25s	+0%
polymat_permute_bitrev_to_custom	✅	25s	24s	+4%
fqmul	✅	22s	19s	+16%
rej_uniform	✅	22s	22s	+0%
rej_uniform_c	✅	20s	18s	+11%
poly_chknorm_c	✅	19s	17s	+12%
poly_uniform_eta_4x	✅	17s	16s	+6%
polyeta_unpack	✅	17s	13s	+31%
polyvec_matrix_pointwise_montgomery	✅	16s	14s	+14%
polyveck_power2round	✅	16s	15s	+7%
poly_uniform_4x	✅	15s	15s	+0%
polyt0_unpack	✅	15s	14s	+7%
polyveck_add	✅	15s	14s	+7%
keccakf1600x4_permute_native	✅	13s	13s	+0%
mld_ntt_butterfly_block	✅	13s	11s	+18%
polyveck_reduce	✅	13s	10s	+30%
keccak_absorb_once_x4	✅	12s	12s	+0%
polyveck_chknorm	✅	12s	6s	+100%
keccakf1600_permute_native	✅	10s	9s	+11%
mld_polyvecl_permute_bitrev_to_custom_native	✅	10s	9s	+11%
mld_sample_s1_s2	✅	9s	8s	+12%
poly_invntt_tomont_c	✅	9s	8s	+12%
polyveck_caddq	✅	9s	8s	+12%
mld_check_pct	✅	8s	7s	+14%
poly_decompose_c	✅	8s	7s	+14%
poly_power2round	✅	8s	5s	+60%
polyveck_decompose	✅	8s	9s	-11%
polyveck_ntt	✅	8s	7s	+14%
polyveck_pointwise_poly_montgomery	✅	8s	6s	+33%
sign	✅	8s	8s	+0%
sign_keypair_internal	✅	8s	5s	+60%
sign_pk_from_sk	✅	8s	9s	-11%
keccak_absorb	✅	7s	4s	+75%
keccakf1600_permute	✅	7s	9s	-22%
mld_compute_pack_z	✅	7s	6s	+17%
polyveck_invntt_tomont	✅	7s	9s	-22%
polyveck_sub	✅	7s	7s	+0%
polyveck_use_hint	✅	7s	6s	+17%
polyvecl_chknorm	✅	7s	4s	+75%
polyvecl_ntt	✅	7s	9s	-22%
mld_sample_s1_s2_serial	✅	6s	6s	+0%
poly_challenge	✅	6s	4s	+50%
polyveck_shiftl	✅	6s	7s	-14%
polyveck_unpack_t0	✅	6s	4s	+50%
polyvecl_uniform_gamma1	✅	6s	4s	+50%
sign_signature_extmu	✅	6s	5s	+20%
unpack_hints	✅	6s	5s	+20%
poly_caddq	✅	5s	3s	+67%
poly_caddq_native	✅	5s	2s	+150%
poly_invntt_tomont_native	✅	5s	2s	+150%
poly_make_hint	✅	5s	3s	+67%
poly_ntt_native	✅	5s	3s	+67%
polyveck_make_hint	✅	5s	5s	+0%
polyvecl_pack_eta	✅	5s	2s	+150%
polyvecl_uniform_gamma1_serial	✅	5s	3s	+67%
polyw1_pack	✅	5s	3s	+67%
rej_eta_c	✅	5s	5s	+0%
shake128_finalize	✅	5s	3s	+67%
shake128_release	✅	5s	2s	+150%
sign_keypair	✅	5s	3s	+67%
use_hint	✅	5s	5s	+0%
keccak_squeeze	✅	4s	2s	+100%
keccakf1600x4_xor_bytes	✅	4s	3s	+33%
mld_ct_abs_i32	✅	4s	2s	+100%
mld_ct_cmask_nonzero_u32	✅	4s	2s	+100%
mld_ct_get_optblocker_i64	✅	4s	1s	+300%
mld_h	✅	4s	6s	-33%
poly_add	✅	4s	5s	-20%
poly_caddq_c	✅	4s	5s	-20%
poly_decompose	✅	4s	2s	+100%
poly_decompose_native	✅	4s	4s	+0%
poly_ntt	✅	4s	2s	+100%
poly_uniform_gamma1	✅	4s	2s	+100%
poly_uniform_gamma1_4x	✅	4s	5s	-20%
polyeta_pack	✅	4s	4s	+0%
polyt1_pack	✅	4s	2s	+100%
polyveck_pack_eta	✅	4s	2s	+100%
polyveck_pack_t0	✅	4s	4s	+0%
polyveck_unpack_eta	✅	4s	7s	-43%
polyvecl_pointwise_acc_montgomery_native	✅	4s	4s	+0%
polyvecl_unpack_eta	✅	4s	4s	+0%
polyvecl_unpack_z	✅	4s	6s	-33%
polyz_pack	✅	4s	3s	+33%
polyz_unpack_c	✅	4s	6s	-33%
polyz_unpack_native	✅	4s	2s	+100%
rej_eta_native	✅	4s	3s	+33%
sign_verify_pre_hash_internal	✅	4s	3s	+33%
sign_verify_pre_hash_shake256	✅	4s	4s	+0%
unpack_sk	✅	4s	5s	-20%
caddq	✅	3s	4s	-25%
decompose	✅	3s	4s	-25%
fqscale	✅	3s	3s	+0%
keccakf1600_xor_bytes (big endian)	✅	3s	3s	+0%
keccakf1600x4_extract_bytes	✅	3s	5s	-40%
keccakf1600x4_permute	✅	3s	3s	+0%
mld_ct_get_optblocker_u32	✅	3s	2s	+50%
mld_keccakf1600_extract_bytes	✅	3s	2s	+50%
mld_prepare_domain_separation_prefix	✅	3s	5s	-40%
mld_value_barrier_u8	✅	3s	2s	+50%
pack_sig_c_h	✅	3s	2s	+50%
pack_sig_z	✅	3s	3s	+0%
pack_sk	✅	3s	2s	+50%
poly_ntt_c	✅	3s	2s	+50%
poly_pointwise_montgomery	✅	3s	2s	+50%
poly_pointwise_montgomery_native	✅	3s	2s	+50%
poly_reduce	✅	3s	3s	+0%
poly_shiftl	✅	3s	2s	+50%
poly_uniform_eta	✅	3s	4s	-25%
poly_use_hint_c	✅	3s	3s	+0%
poly_use_hint_native	✅	3s	3s	+0%
polyt0_pack	✅	3s	4s	-25%
polyt1_unpack	✅	3s	5s	-40%
polyvecl_permute_bitrev_to_custom	✅	3s	4s	-25%
polyvecl_pointwise_acc_montgomery	✅	3s	2s	+50%
power2round	✅	3s	3s	+0%
reduce32	✅	3s	2s	+50%
rej_eta	✅	3s	2s	+50%
shake128_init	✅	3s	5s	-40%
shake128_squeeze	✅	3s	2s	+50%
shake256_absorb	✅	3s	1s	+200%
shake256_finalize	✅	3s	2s	+50%
shake256x4_squeezeblocks	✅	3s	2s	+50%
sign_open	✅	3s	4s	-25%
sign_signature	✅	3s	4s	-25%
sign_signature_pre_hash_internal	✅	3s	4s	-25%
sign_verify_extmu	✅	3s	4s	-25%
sys_check_capability	✅	3s	3s	+0%
unpack_pk	✅	3s	3s	+0%
unpack_sig	✅	3s	4s	-25%
keccak_finalize	✅	2s	5s	-60%
keccak_init	✅	2s	2s	+0%
keccakf1600_extract_bytes (big endian)	✅	2s	3s	-33%
make_hint	✅	2s	3s	-33%
mld_ct_cmask_nonzero_u8	✅	2s	4s	-50%
mld_ct_get_optblocker_u8	✅	2s	2s	+0%
mld_ct_sel_int32	✅	2s	1s	+100%
mld_value_barrier_i64	✅	2s	3s	-33%
mld_value_barrier_u32	✅	2s	3s	-33%
montgomery_reduce	✅	2s	4s	-50%
ntt_native_x86_64	✅	2s	3s	-33%
pack_pk	✅	2s	2s	+0%
poly_caddq_native_aarch64	✅	2s	4s	-50%
poly_chknorm	✅	2s	5s	-60%
poly_chknorm_native	✅	2s	2s	+0%
poly_invntt_tomont	✅	2s	5s	-60%
poly_sub	✅	2s	4s	-50%
poly_uniform	✅	2s	3s	-33%
poly_use_hint	✅	2s	2s	+0%
polyveck_pack_w1	✅	2s	1s	+100%
polyz_unpack	✅	2s	4s	-50%
shake128_absorb	✅	2s	2s	+0%
shake128x4_absorb_once	✅	2s	1s	+100%
shake256	✅	2s	4s	-50%
shake256_init	✅	2s	2s	+0%
shake256_release	✅	2s	5s	-60%
shake256_squeeze	✅	2s	2s	+0%
shake256x4_absorb_once	✅	2s	2s	+0%
sign_signature_pre_hash_shake256	✅	2s	7s	-71%
sign_verify	✅	2s	5s	-60%
keccakf1600_xor_bytes	✅	1s	2s	-50%
mld_ct_cmask_neg_i32	✅	1s	2s	-50%
shake128x4_squeezeblocks	✅	1s	4s	-75%

[oqs-bot]

CBMC Results (ML-DSA-65)

Full Results (174 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	2411s	2319s	+4.0%
sign_verify_internal	✅	365s	357s	+2%
polyvecl_pointwise_acc_montgomery_c	✅	249s	229s	+9%
mld_attempt_signature_generation	✅	209s	202s	+3%
rej_uniform_native	✅	140s	130s	+8%
poly_pointwise_montgomery_c	✅	139s	136s	+2%
polyvec_matrix_expand	✅	100s	93s	+8%
mld_ct_memcmp	✅	84s	79s	+6%
mld_invntt_layer	✅	75s	72s	+4%
polyvec_matrix_expand_serial	✅	64s	63s	+2%
mld_ntt_layer	✅	55s	55s	+0%
sign_signature_internal	✅	47s	44s	+7%
keccak_squeezeblocks_x4	✅	44s	44s	+0%
mld_compute_t0_t1_tr_from_sk_components	✅	26s	24s	+8%
rej_uniform	✅	20s	20s	+0%
fqmul	✅	19s	19s	+0%
rej_uniform_c	✅	19s	17s	+12%
polymat_permute_bitrev_to_custom	✅	18s	20s	-10%
polyvec_matrix_pointwise_montgomery	✅	17s	14s	+21%
polyveck_decompose	✅	17s	16s	+6%
poly_chknorm_c	✅	16s	18s	-11%
poly_uniform_4x	✅	16s	18s	-11%
poly_uniform_eta_4x	✅	16s	17s	-6%
mld_ntt_butterfly_block	✅	14s	12s	+17%
polyt0_unpack	✅	14s	15s	-7%
mld_polyvecl_permute_bitrev_to_custom_native	✅	13s	10s	+30%
polyveck_add	✅	13s	10s	+30%
keccak_absorb_once_x4	✅	12s	12s	+0%
keccakf1600x4_permute_native	✅	12s	13s	-8%
polyveck_power2round	✅	11s	10s	+10%
poly_invntt_tomont_c	✅	10s	9s	+11%
polyvecl_ntt	✅	10s	8s	+25%
polyveck_invntt_tomont	✅	9s	9s	+0%
polyveck_use_hint	✅	9s	7s	+29%
sign_pk_from_sk	✅	9s	8s	+12%
keccakf1600_permute	✅	8s	7s	+14%
poly_decompose_c	✅	8s	8s	+0%
polyeta_unpack	✅	8s	5s	+60%
polyveck_ntt	✅	8s	9s	-11%
sign	✅	8s	9s	-11%
keccakf1600_permute_native	✅	7s	7s	+0%
mld_check_pct	✅	7s	5s	+40%
mld_compute_pack_z	✅	7s	6s	+17%
polyveck_caddq	✅	7s	6s	+17%
polyveck_reduce	✅	7s	6s	+17%
poly_challenge	✅	6s	3s	+100%
poly_ntt_native	✅	6s	2s	+200%
poly_power2round	✅	6s	6s	+0%
poly_uniform_gamma1_4x	✅	6s	4s	+50%
polyveck_pointwise_poly_montgomery	✅	6s	4s	+50%
polyveck_shiftl	✅	6s	12s	-50%
polyveck_sub	✅	6s	9s	-33%
sys_check_capability	✅	6s	4s	+50%
keccak_absorb	✅	5s	5s	+0%
mld_h	✅	5s	2s	+150%
mld_sample_s1_s2_serial	✅	5s	5s	+0%
ntt_native_x86_64	✅	5s	3s	+67%
poly_add	✅	5s	4s	+25%
poly_caddq	✅	5s	3s	+67%
poly_caddq_native_aarch64	✅	5s	2s	+150%
poly_decompose	✅	5s	4s	+25%
poly_ntt_c	✅	5s	5s	+0%
poly_uniform	✅	5s	4s	+25%
polyveck_chknorm	✅	5s	6s	-17%
polyvecl_chknorm	✅	5s	6s	-17%
polyvecl_pointwise_acc_montgomery	✅	5s	3s	+67%
polyz_unpack_c	✅	5s	5s	+0%
power2round	✅	5s	4s	+25%
sign_signature_pre_hash_shake256	✅	5s	4s	+25%
unpack_sk	✅	5s	3s	+67%
fqscale	✅	4s	3s	+33%
keccakf1600_xor_bytes	✅	4s	3s	+33%
mld_keccakf1600_extract_bytes	✅	4s	3s	+33%
mld_prepare_domain_separation_prefix	✅	4s	3s	+33%
pack_sig_c_h	✅	4s	1s	+300%
pack_sk	✅	4s	2s	+100%
poly_chknorm_native	✅	4s	5s	-20%
poly_decompose_native	✅	4s	4s	+0%
poly_invntt_tomont	✅	4s	2s	+100%
poly_make_hint	✅	4s	4s	+0%
poly_pointwise_montgomery	✅	4s	5s	-20%
poly_uniform_gamma1	✅	4s	3s	+33%
poly_use_hint_c	✅	4s	4s	+0%
polyt1_unpack	✅	4s	3s	+33%
polyveck_make_hint	✅	4s	3s	+33%
polyveck_pack_eta	✅	4s	3s	+33%
polyveck_pack_t0	✅	4s	2s	+100%
polyveck_pack_w1	✅	4s	4s	+0%
polyvecl_pointwise_acc_montgomery_native	✅	4s	3s	+33%
polyvecl_unpack_z	✅	4s	3s	+33%
polyz_pack	✅	4s	1s	+300%
reduce32	✅	4s	3s	+33%
shake128x4_squeezeblocks	✅	4s	2s	+100%
shake256_finalize	✅	4s	4s	+0%
shake256_release	✅	4s	2s	+100%
sign_keypair_internal	✅	4s	5s	-20%
sign_open	✅	4s	7s	-43%
sign_signature	✅	4s	5s	-20%
sign_signature_extmu	✅	4s	5s	-20%
sign_verify	✅	4s	3s	+33%
unpack_hints	✅	4s	6s	-33%
unpack_pk	✅	4s	4s	+0%
caddq	✅	3s	3s	+0%
decompose	✅	3s	4s	-25%
keccak_squeeze	✅	3s	3s	+0%
keccakf1600_extract_bytes (big endian)	✅	3s	2s	+50%
keccakf1600_xor_bytes (big endian)	✅	3s	3s	+0%
keccakf1600x4_extract_bytes	✅	3s	2s	+50%
keccakf1600x4_permute	✅	3s	4s	-25%
keccakf1600x4_xor_bytes	✅	3s	1s	+200%
make_hint	✅	3s	4s	-25%
mld_ct_cmask_nonzero_u32	✅	3s	3s	+0%
mld_ct_cmask_nonzero_u8	✅	3s	2s	+50%
mld_ct_get_optblocker_u32	✅	3s	1s	+200%
mld_sample_s1_s2	✅	3s	5s	-40%
mld_value_barrier_u32	✅	3s	4s	-25%
mld_value_barrier_u8	✅	3s	3s	+0%
pack_sig_z	✅	3s	4s	-25%
poly_caddq_native	✅	3s	4s	-25%
poly_chknorm	✅	3s	3s	+0%
poly_invntt_tomont_native	✅	3s	3s	+0%
poly_ntt	✅	3s	2s	+50%
poly_pointwise_montgomery_native	✅	3s	3s	+0%
poly_shiftl	✅	3s	4s	-25%
poly_sub	✅	3s	5s	-40%
poly_use_hint	✅	3s	2s	+50%
poly_use_hint_native	✅	3s	3s	+0%
polyeta_pack	✅	3s	3s	+0%
polyt0_pack	✅	3s	6s	-50%
polyt1_pack	✅	3s	3s	+0%
polyveck_unpack_eta	✅	3s	4s	-25%
polyveck_unpack_t0	✅	3s	3s	+0%
polyvecl_pack_eta	✅	3s	4s	-25%
polyvecl_unpack_eta	✅	3s	4s	-25%
rej_eta_c	✅	3s	4s	-25%
rej_eta_native	✅	3s	4s	-25%
shake128_init	✅	3s	2s	+50%
shake256	✅	3s	3s	+0%
shake256_absorb	✅	3s	1s	+200%
shake256_init	✅	3s	3s	+0%
shake256x4_absorb_once	✅	3s	3s	+0%
shake256x4_squeezeblocks	✅	3s	3s	+0%
sign_keypair	✅	3s	2s	+50%
sign_signature_pre_hash_internal	✅	3s	7s	-57%
sign_verify_extmu	✅	3s	3s	+0%
sign_verify_pre_hash_internal	✅	3s	2s	+50%
sign_verify_pre_hash_shake256	✅	3s	2s	+50%
keccak_finalize	✅	2s	3s	-33%
mld_ct_cmask_neg_i32	✅	2s	1s	+100%
mld_ct_get_optblocker_i64	✅	2s	3s	-33%
mld_ct_get_optblocker_u8	✅	2s	3s	-33%
mld_ct_sel_int32	✅	2s	2s	+0%
montgomery_reduce	✅	2s	3s	-33%
pack_pk	✅	2s	6s	-67%
poly_caddq_c	✅	2s	4s	-50%
poly_reduce	✅	2s	2s	+0%
poly_uniform_eta	✅	2s	4s	-50%
polyvecl_permute_bitrev_to_custom	✅	2s	2s	+0%
polyvecl_uniform_gamma1	✅	2s	5s	-60%
polyz_unpack	✅	2s	3s	-33%
polyz_unpack_native	✅	2s	2s	+0%
rej_eta	✅	2s	4s	-50%
shake128_absorb	✅	2s	1s	+100%
shake128_squeeze	✅	2s	2s	+0%
shake128x4_absorb_once	✅	2s	3s	-33%
shake256_squeeze	✅	2s	2s	+0%
unpack_sig	✅	2s	3s	-33%
use_hint	✅	2s	3s	-33%
keccak_init	✅	1s	1s	+0%
mld_ct_abs_i32	✅	1s	2s	-50%
mld_value_barrier_i64	✅	1s	1s	+0%
polyvecl_uniform_gamma1_serial	✅	1s	4s	-75%
polyw1_pack	✅	1s	3s	-67%
shake128_finalize	✅	1s	1s	+0%
shake128_release	✅	1s	3s	-67%