Skip to content

Add Armv8.1-m MVE memcpy, memset, zeroize#1271

Draft
bremoran wants to merge 4 commits into
mainfrom
armv81m-mve-memory
Draft

Add Armv8.1-m MVE memcpy, memset, zeroize#1271
bremoran wants to merge 4 commits into
mainfrom
armv81m-mve-memory

Conversation

@bremoran

@bremoran bremoran commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

No description provided.

 - Port of pq-code-package/mlkem-native#1547

Signed-off-by: Matthias J. Kannwischer <matthias@zerorisc.com>
 - Port of pq-code-package/mlkem-native#1791

Signed-off-by: Matthias J. Kannwischer <matthias@zerorisc.com>
@bremoran bremoran requested a review from a team as a code owner July 8, 2026 17:37
bremoran added 2 commits July 8, 2026 18:40
Zephyr's k_cycle_get_32() can wrap during long NUCLEO benchmark windows, producing huge unsigned deltas in the benchmark output. Use k_cycle_get_64() for Zephyr targets.

Also make ML-DSA benchmark percentile sorting and formatting robust for large uint64_t cycle values.

Signed-off-by: Brendan Moran <brendan.moran@arm.com>
Signed-off-by: Brendan Moran <brendan.moran@arm.com>
@bremoran bremoran force-pushed the armv81m-mve-memory branch from b4ac391 to 18a1f41 Compare July 8, 2026 17:41
@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-44, REDUCE-RAM)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 1388s 1364s +1.8%
polyvec_matrix_pointwise_montgomery_yvec 151s 149s +1%
poly_pointwise_montgomery_c 117s 112s +4%
mld_invntt_layer 108s 105s +3%
polyveck_chknorm 66s 67s -1%
sign_verify_internal 51s 49s +4%
mld_ntt_layer 44s 41s +7%
fqmul 40s 39s +3%
keccakf1600x4_permute_native 23s 22s +5%
mld_attempt_signature_generation 23s 19s +21%
mld_ntt_butterfly_block 23s 23s +0%
poly_ntt_c 19s 21s -10%
rej_uniform_c 15s 16s -6%
poly_chknorm_c 13s 11s +18%
polyeta_unpack 13s 14s -7%
compute_pack_t0_t1 12s 12s +0%
keccak_absorb_once_x4 12s 8s +50%
mld_check_pct 12s 15s -20%
poly_uniform_eta_4x 12s 12s +0%
polyvecl_chknorm 11s 11s +0%
poly_invntt_tomont_c 10s 11s -9%
polyt0_unpack 10s 12s -17%
poly_add 8s 7s +14%
polyz_unpack_c 8s 8s +0%
mld_keccakf1600_permute_c 7s 7s +0%
poly_decompose_c 7s 5s +40%
poly_reduce 7s 4s +75%
polyveck_decompose 7s 7s +0%
polyvecl_pointwise_acc_montgomery 7s 3s +133%
rej_uniform 7s 8s -12%
poly_permute_bitrev_to_custom_optional 6s 5s +20%
rej_uniform_eta_native_aarch64 6s 3s +100%
rej_uniform_native 6s 5s +20%
sig_unpack_hints 6s 2s +200%
sign_keypair 6s 5s +20%
sign_pk_from_sk 6s 5s +20%
sign_signature_pre_hash_internal 6s 4s +50%
sign_verify 6s 4s +50%
caddq 5s 6s -17%
mld_compute_pack_z 5s 6s -17%
mld_h 5s 4s +25%
pointwise_acc_native_x86_64 5s 4s +25%
pointwise_native_aarch64 5s 2s +150%
pointwise_native_x86_64 5s 4s +25%
poly_challenge 5s 6s -17%
poly_pointwise_montgomery 5s 3s +67%
poly_power2round 5s 4s +25%
poly_uniform_eta 5s 2s +150%
polyvec_matrix_pointwise_montgomery_row 5s 6s -17%
polyz_unpack 5s 3s +67%
reduce32 5s 3s +67%
rej_eta_c 5s 4s +25%
rej_uniform_native_aarch64 5s 3s +67%
sign_keypair_internal 5s 4s +25%
sign_signature_internal 5s 4s +25%
sign_verify_extmu 5s 5s +0%
decompose 4s 3s +33%
intt_native_aarch64 4s 3s +33%
intt_native_x86_64 4s 2s +100%
keccak_squeezeblocks_x4 4s 3s +33%
mld_ct_abs_i32 4s 3s +33%
mld_ct_cmask_neg_i32 4s 2s +100%
pack_sk_rho_key_tr_s2 4s 5s -20%
pointwise_acc_native_aarch64 4s 6s -33%
poly_caddq_native_x86_64 4s 4s +0%
poly_chknorm_native 4s 4s +0%
poly_chknorm_native_x86_64 4s 2s +100%
poly_decompose_88_native_aarch64 4s 3s +33%
poly_permute_bitrev_to_custom_optional_native 4s 3s +33%
poly_pointwise_montgomery_native 4s 2s +100%
poly_shiftl 4s 4s +0%
poly_uniform 4s 3s +33%
poly_uniform_gamma1 4s 3s +33%
poly_uniform_gamma1_4x 4s 5s -20%
polyt0_pack 4s 4s +0%
polyt1_unpack 4s 2s +100%
polyveck_invntt_tomont 4s 5s -20%
polyvecl_pointwise_acc_montgomery_c 4s 4s +0%
polyvecl_unpack_z 4s 3s +33%
polyz_unpack_17_native_aarch64 4s 2s +100%
polyz_unpack_native 4s 3s +33%
shake128x4_absorb_once 4s 2s +100%
sign_verify_pre_hash_shake256 4s 5s -20%
sys_check_capability 4s 2s +100%
yvec_init 4s 1s +300%
fqscale 3s 2s +50%
keccak_absorb 3s 3s +0%
keccak_f1600_x1_native_aarch64 3s 3s +0%
keccak_f1600_x1_native_aarch64_v84a 3s 2s +50%
keccak_f1600_x4_native_aarch64_v84a 3s 3s +0%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 3s 2s +50%
keccak_finalize 3s 2s +50%
keccak_squeeze 3s 2s +50%
make_hint 3s 3s +0%
mld_ct_get_optblocker_i64 3s 4s -25%
mld_ct_sel_int32 3s 3s +0%
mld_polymat_expand_entry 3s 2s +50%
mld_prepare_domain_separation_prefix 3s 3s +0%
mld_sample_s1_s2 3s 1s +200%
mld_value_barrier_i64 3s 3s +0%
mld_value_barrier_u8 3s 4s -25%
ntt_native_x86_64 3s 3s +0%
poly_caddq_c 3s 3s +0%
poly_decompose_32_native_aarch64 3s 4s -25%
poly_decompose_native 3s 2s +50%
poly_decompose_native_x86_64 3s 2s +50%
poly_ntt_native 3s 3s +0%
poly_uniform_4x 3s 3s +0%
poly_use_hint 3s 2s +50%
poly_use_hint_native_aarch64 3s 3s +0%
poly_use_hint_native_x86_64 3s - new
polyeta_pack 3s 3s +0%
polyvec_matrix_expand 3s 3s +0%
polyveck_caddq 3s 3s +0%
polyveck_pack_w1 3s 3s +0%
polyveck_reduce 3s 4s -25%
polyveck_unpack_eta 3s 2s +50%
polyvecl_ntt 3s 3s +0%
polyvecl_pointwise_acc_montgomery_native 3s 3s +0%
polyvecl_uniform_gamma1 3s 2s +50%
polyvecl_unpack_eta 3s 4s -25%
polyw1_pack_88 3s 2s +50%
polyz_pack 3s 2s +50%
power2round 3s 2s +50%
rej_eta 3s 5s -40%
rej_eta_native 3s 3s +0%
shake128_finalize 3s 3s +0%
shake128_release 3s 2s +50%
shake128_squeeze 3s 2s +50%
shake256 3s 1s +200%
shake256_init 3s 4s -25%
shake256_release 3s 1s +200%
shake256x4_absorb_once 3s 1s +200%
sign_signature 3s 6s -50%
sign_signature_extmu 3s 4s -25%
sign_signature_pre_hash_shake256 3s 4s -25%
sign_verify_pre_hash_internal 3s 5s -40%
sk_s1hat_get_poly 3s 2s +50%
sk_s2hat_get_poly 3s 5s -40%
unpack_pk_t1 3s 3s +0%
unpack_sk_s2hat 3s 4s -25%
use_hint 3s 2s +50%
keccak_f1600_x4_native_avx2 2s 2s +0%
keccak_init 2s 3s -33%
keccakf1600_extract_bytes (big endian) 2s 4s -50%
keccakf1600_permute 2s 2s +0%
keccakf1600_permute_native 2s 3s -33%
keccakf1600_xor_bytes (big endian) 2s 6s -67%
keccakf1600x4_extract_bytes 2s 2s +0%
keccakf1600x4_extract_bytes_native 2s 4s -50%
keccakf1600x4_permute 2s 4s -50%
keccakf1600x4_xor_bytes 2s 3s -33%
keccakf1600x4_xor_bytes_native 2s 5s -60%
mld_ct_cmask_nonzero_u32 2s 3s -33%
mld_ct_cmask_nonzero_u8 2s 2s +0%
mld_ct_get_optblocker_u32 2s 2s +0%
mld_ct_get_optblocker_u8 2s 2s +0%
mld_ct_memcmp 2s 1s +100%
mld_keccakf1600_extract_bytes 2s 2s +0%
mld_sample_s1_s2_serial 2s 4s -50%
montgomery_reduce 2s 2s +0%
ntt_native_aarch64 2s 4s -50%
nttunpack_native_x86_64 2s 4s -50%
pack_sig_c 2s 5s -60%
pack_sig_h 2s 4s -50%
pack_sig_z 2s 2s +0%
pack_sk_s1 2s 3s -33%
poly_caddq 2s 4s -50%
poly_caddq_native 2s 3s -33%
poly_caddq_native_aarch64 2s 3s -33%
poly_chknorm 2s 3s -33%
poly_chknorm_native_aarch64 2s 2s +0%
poly_decompose 2s 2s +0%
poly_invntt_tomont 2s 2s +0%
poly_invntt_tomont_native 2s 3s -33%
poly_ntt 2s 3s -33%
poly_sub 2s 3s -33%
poly_use_hint_c 2s 5s -60%
poly_use_hint_native 2s 3s -33%
polyt1_pack 2s 3s -33%
polyvec_matrix_expand_serial 2s 4s -50%
polyveck_ntt 2s 2s +0%
polyvecl_pack_eta 2s 2s +0%
polyvecl_uniform_gamma1_serial 2s 2s +0%
polyw1_pack 2s 4s -50%
polyw1_pack_32 2s 3s -33%
polyz_unpack_19_native_aarch64 2s 4s -50%
polyz_unpack_native_x86_64 2s 3s -33%
shake128_absorb 2s 3s -33%
shake128_init 2s 2s +0%
shake256_absorb 2s 2s +0%
shake256_finalize 2s 2s +0%
shake256_squeeze 2s 2s +0%
shake256x4_squeezeblocks 2s 2s +0%
unpack_sk 2s 3s -33%
unpack_sk_s1hat 2s 3s -33%
unpack_sk_t0hat 2s 2s +0%
yvec_get_poly 2s 3s -33%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 1s 3s -67%
keccakf1600_xor_bytes 1s 3s -67%
mld_keccakf1600x4_extract_bytes_c 1s 4s -75%
mld_keccakf1600x4_xor_bytes_c 1s 4s -75%
mld_value_barrier_u32 1s 1s +0%
polyveck_pack_eta 1s 4s -75%
shake128x4_squeezeblocks 1s 2s -50%
sk_t0hat_get_poly 1s 1s +0%

@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-87, REDUCE-RAM)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 1404s 1436s -2.2%
polyvec_matrix_pointwise_montgomery_yvec 182s 196s -7%
mld_invntt_layer 111s 111s +0%
poly_pointwise_montgomery_c 111s 125s -11%
mld_ntt_layer 45s 44s +2%
sign_verify_internal 44s 47s -6%
fqmul 40s 39s +3%
mld_attempt_signature_generation 33s 34s -3%
polyvecl_chknorm 32s 38s -16%
keccakf1600x4_permute_native 24s 25s -4%
mld_ntt_butterfly_block 21s 23s -9%
poly_ntt_c 17s 19s -11%
mld_check_pct 16s 15s +7%
rej_uniform_c 16s 18s -11%
polyeta_unpack 13s 13s +0%
polyvec_matrix_pointwise_montgomery_row 13s 13s +0%
poly_uniform_eta_4x 12s 12s +0%
compute_pack_t0_t1 11s 12s -8%
poly_chknorm_c 11s 13s -15%
polyt0_unpack 11s 14s -21%
polyveck_decompose 11s 12s -8%
poly_invntt_tomont_c 10s 9s +11%
keccak_absorb_once_x4 9s 8s +12%
polyveck_chknorm 9s 9s +0%
polyvecl_ntt 9s 8s +12%
mld_sample_s1_s2 8s 8s +0%
poly_decompose_native 8s 2s +300%
polyz_unpack_c 8s 7s +14%
rej_uniform_native 8s 5s +60%
keccak_squeezeblocks_x4 7s 4s +75%
pointwise_acc_native_aarch64 7s 5s +40%
polyveck_caddq 7s 8s -12%
polyveck_reduce 7s 6s +17%
mld_keccakf1600_permute_c 6s 8s -25%
mld_sample_s1_s2_serial 6s 6s +0%
pointwise_acc_native_x86_64 6s 8s -25%
pointwise_native_x86_64 6s 5s +20%
poly_add 6s 8s -25%
poly_use_hint_native 6s 1s +500%
rej_uniform 6s 7s -14%
rej_uniform_eta_native_aarch64 6s 3s +100%
mld_compute_pack_z 5s 6s -17%
poly_caddq_native_aarch64 5s 3s +67%
poly_chknorm_native 5s 1s +400%
poly_decompose_c 5s 6s -17%
poly_pointwise_montgomery 5s 3s +67%
poly_reduce 5s 4s +25%
poly_sub 5s 5s +0%
polyveck_invntt_tomont 5s 4s +25%
polyvecl_unpack_eta 5s 3s +67%
power2round 5s 3s +67%
sign_keypair 5s 4s +25%
decompose 4s 2s +100%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 4s 2s +100%
keccak_finalize 4s 1s +300%
mld_ct_memcmp 4s 1s +300%
mld_h 4s 2s +100%
poly_caddq_c 4s 3s +33%
poly_caddq_native 4s 3s +33%
poly_caddq_native_x86_64 4s 3s +33%
poly_challenge 4s 4s +0%
poly_decompose_88_native_aarch64 4s 2s +100%
poly_invntt_tomont 4s 4s +0%
poly_invntt_tomont_native 4s 2s +100%
poly_ntt 4s 2s +100%
poly_permute_bitrev_to_custom_optional_native 4s 3s +33%
poly_power2round 4s 7s -43%
poly_uniform_gamma1 4s 3s +33%
polyvecl_unpack_z 4s 3s +33%
polyw1_pack 4s 2s +100%
polyz_pack 4s 4s +0%
polyz_unpack 4s 3s +33%
rej_eta_c 4s 4s +0%
rej_eta_native 4s 4s +0%
rej_uniform_native_aarch64 4s 3s +33%
shake256_absorb 4s 3s +33%
shake256_release 4s 5s -20%
sig_unpack_hints 4s 4s +0%
sign_keypair_internal 4s 6s -33%
sign_pk_from_sk 4s 6s -33%
sign_signature 4s 4s +0%
sign_signature_extmu 4s 4s +0%
sign_signature_internal 4s 3s +33%
sign_signature_pre_hash_internal 4s 2s +100%
sign_signature_pre_hash_shake256 4s 3s +33%
sign_verify 4s 2s +100%
unpack_sk_s1hat 4s 3s +33%
use_hint 4s 3s +33%
yvec_init 4s 4s +0%
caddq 3s 3s +0%
intt_native_x86_64 3s 4s -25%
keccak_absorb 3s 4s -25%
keccak_f1600_x1_native_aarch64 3s 2s +50%
keccak_f1600_x4_native_aarch64_v84a 3s 1s +200%
keccak_squeeze 3s 5s -40%
keccakf1600_extract_bytes (big endian) 3s 3s +0%
keccakf1600_permute_native 3s 3s +0%
keccakf1600x4_extract_bytes_native 3s 4s -25%
keccakf1600x4_permute 3s 2s +50%
mld_ct_cmask_nonzero_u32 3s 5s -40%
mld_ct_get_optblocker_i64 3s 2s +50%
mld_ct_get_optblocker_u8 3s 3s +0%
montgomery_reduce 3s 2s +50%
ntt_native_aarch64 3s 4s -25%
ntt_native_x86_64 3s 2s +50%
pack_sig_c 3s 2s +50%
pack_sig_z 3s 3s +0%
pack_sk_s1 3s 2s +50%
pointwise_native_aarch64 3s 4s -25%
poly_chknorm_native_aarch64 3s 5s -40%
poly_decompose 3s 2s +50%
poly_decompose_32_native_aarch64 3s 3s +0%
poly_decompose_native_x86_64 3s 3s +0%
poly_ntt_native 3s 4s -25%
poly_shiftl 3s 4s -25%
poly_uniform 3s 4s -25%
poly_uniform_eta 3s 5s -40%
poly_uniform_gamma1_4x 3s 3s +0%
poly_use_hint 3s 4s -25%
poly_use_hint_c 3s 4s -25%
poly_use_hint_native_aarch64 3s 3s +0%
poly_use_hint_native_x86_64 3s - new
polyt0_pack 3s 3s +0%
polyt1_pack 3s 5s -40%
polyt1_unpack 3s 3s +0%
polyvec_matrix_expand 3s 3s +0%
polyveck_ntt 3s 3s +0%
polyveck_pack_eta 3s 5s -40%
polyveck_pack_w1 3s 3s +0%
polyveck_unpack_eta 3s 3s +0%
polyvecl_pointwise_acc_montgomery 3s 2s +50%
polyvecl_uniform_gamma1 3s 3s +0%
polyw1_pack_32 3s 3s +0%
polyz_unpack_19_native_aarch64 3s 5s -40%
polyz_unpack_native 3s 1s +200%
polyz_unpack_native_x86_64 3s 3s +0%
shake128_init 3s 2s +50%
shake128_release 3s 3s +0%
shake128x4_absorb_once 3s 4s -25%
shake256_init 3s 3s +0%
shake256x4_absorb_once 3s 5s -40%
shake256x4_squeezeblocks 3s 4s -25%
sign_verify_extmu 3s 4s -25%
sign_verify_pre_hash_internal 3s 3s +0%
sk_s1hat_get_poly 3s 3s +0%
sk_s2hat_get_poly 3s 2s +50%
sk_t0hat_get_poly 3s 3s +0%
unpack_sk 3s 4s -25%
unpack_sk_t0hat 3s 4s -25%
intt_native_aarch64 2s 4s -50%
keccak_f1600_x1_native_aarch64_v84a 2s 2s +0%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 2s 2s +0%
keccakf1600_permute 2s 2s +0%
keccakf1600_xor_bytes 2s 1s +100%
keccakf1600_xor_bytes (big endian) 2s 2s +0%
keccakf1600x4_extract_bytes 2s 1s +100%
keccakf1600x4_xor_bytes_native 2s 2s +0%
make_hint 2s 2s +0%
mld_ct_cmask_neg_i32 2s 2s +0%
mld_ct_cmask_nonzero_u8 2s 2s +0%
mld_ct_get_optblocker_u32 2s 2s +0%
mld_ct_sel_int32 2s 2s +0%
mld_keccakf1600_extract_bytes 2s 1s +100%
mld_keccakf1600x4_extract_bytes_c 2s 3s -33%
mld_polymat_expand_entry 2s 4s -50%
mld_prepare_domain_separation_prefix 2s 3s -33%
mld_value_barrier_i64 2s 2s +0%
mld_value_barrier_u32 2s 3s -33%
nttunpack_native_x86_64 2s 3s -33%
pack_sig_h 2s 3s -33%
pack_sk_rho_key_tr_s2 2s 2s +0%
poly_caddq 2s 5s -60%
poly_chknorm_native_x86_64 2s 2s +0%
poly_permute_bitrev_to_custom_optional 2s 2s +0%
poly_pointwise_montgomery_native 2s 3s -33%
poly_uniform_4x 2s 3s -33%
polyeta_pack 2s 3s -33%
polyvec_matrix_expand_serial 2s 3s -33%
polyvecl_pack_eta 2s 2s +0%
polyvecl_pointwise_acc_montgomery_native 2s 2s +0%
polyvecl_uniform_gamma1_serial 2s 2s +0%
polyw1_pack_88 2s 2s +0%
polyz_unpack_17_native_aarch64 2s 4s -50%
reduce32 2s 3s -33%
rej_eta 2s 2s +0%
shake128_absorb 2s 2s +0%
shake128_finalize 2s 2s +0%
shake128_squeeze 2s 1s +100%
shake256_finalize 2s 3s -33%
shake256_squeeze 2s 2s +0%
sign_verify_pre_hash_shake256 2s 7s -71%
unpack_pk_t1 2s 2s +0%
unpack_sk_s2hat 2s 3s -33%
yvec_get_poly 2s 2s +0%
fqscale 1s 1s +0%
keccak_f1600_x4_native_avx2 1s 3s -67%
keccak_init 1s 1s +0%
keccakf1600x4_xor_bytes 1s 1s +0%
mld_ct_abs_i32 1s 1s +0%
mld_keccakf1600x4_xor_bytes_c 1s 1s +0%
mld_value_barrier_u8 1s 2s -50%
poly_chknorm 1s 4s -75%
polyvecl_pointwise_acc_montgomery_c 1s 2s -50%
shake128x4_squeezeblocks 1s 1s +0%
shake256 1s 3s -67%
sys_check_capability 1s 2s -50%

@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-65)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 1803s 1784s +1.1%
polyvecl_pointwise_acc_montgomery_c 214s 210s +2%
sign_verify_internal 174s 177s -2%
poly_pointwise_montgomery_c 124s 125s -1%
mld_invntt_layer 108s 109s -1%
polyvec_matrix_expand 104s 110s -5%
mld_attempt_signature_generation 64s 63s +2%
sign_signature_internal 58s 55s +5%
mld_ntt_layer 41s 41s +0%
fqmul 40s 40s +0%
polyvec_matrix_expand_serial 28s 27s +4%
keccakf1600x4_permute_native 23s 23s +0%
mld_ntt_butterfly_block 21s 24s -12%
poly_ntt_c 20s 19s +5%
polyvec_matrix_pointwise_montgomery_yvec 19s 18s +6%
poly_chknorm_c 17s 15s +13%
mld_check_pct 16s 14s +14%
polyt0_unpack 16s 16s +0%
compute_pack_t0_t1 14s 13s +8%
rej_uniform_c 14s 14s +0%
polyz_unpack_c 13s 13s +0%
rej_uniform 13s 18s -28%
poly_uniform_4x 12s 13s -8%
polyveck_decompose 12s 12s +0%
poly_invntt_tomont_c 11s 11s +0%
poly_uniform_eta_4x 11s 14s -21%
keccak_absorb_once_x4 9s 8s +12%
mld_compute_pack_z 8s 7s +14%
polyveck_invntt_tomont 8s 8s +0%
sign_signature_extmu 8s 2s +300%
keccak_init 7s 1s +600%
poly_add 7s 9s -22%
polyveck_chknorm 7s 6s +17%
rej_eta_native 7s 3s +133%
mld_keccakf1600_permute_c 6s 6s +0%
pointwise_acc_native_x86_64 6s 8s -25%
poly_decompose_c 6s 5s +20%
polyt1_unpack 6s 5s +20%
polyveck_caddq 6s 6s +0%
polyveck_ntt 6s 7s -14%
polyvecl_chknorm 6s 7s -14%
polyvecl_pointwise_acc_montgomery 6s 3s +100%
rej_uniform_native 6s 4s +50%
sign_keypair 6s 3s +100%
sign_pk_from_sk 6s 6s +0%
sign_signature_pre_hash_internal 6s 3s +100%
sign_verify 6s 3s +100%
sign_verify_pre_hash_shake256 6s 5s +20%
mld_h 5s 2s +150%
mld_sample_s1_s2 5s 6s -17%
mld_sample_s1_s2_serial 5s 4s +25%
ntt_native_aarch64 5s 2s +150%
nttunpack_native_x86_64 5s 3s +67%
pointwise_acc_native_aarch64 5s 6s -17%
poly_invntt_tomont 5s 3s +67%
poly_invntt_tomont_native 5s 2s +150%
poly_use_hint_c 5s 5s +0%
polyvecl_ntt 5s 4s +25%
polyvecl_uniform_gamma1_serial 5s 3s +67%
polyz_pack 5s 3s +67%
polyz_unpack_native_x86_64 5s 3s +67%
rej_eta_c 5s 5s +0%
sign_verify_extmu 5s 3s +67%
unpack_pk_t1 5s 5s +0%
decompose 4s 1s +300%
fqscale 4s 3s +33%
intt_native_x86_64 4s 3s +33%
keccak_squeeze 4s 4s +0%
mld_ct_abs_i32 4s 2s +100%
mld_keccakf1600x4_xor_bytes_c 4s 2s +100%
mld_polymat_expand_entry 4s 4s +0%
pack_sk_rho_key_tr_s2 4s 2s +100%
poly_caddq_c 4s 2s +100%
poly_challenge 4s 6s -33%
poly_chknorm_native_aarch64 4s 3s +33%
poly_decompose_native_x86_64 4s 3s +33%
poly_power2round 4s 4s +0%
poly_shiftl 4s 3s +33%
poly_uniform 4s 4s +0%
poly_use_hint_native_aarch64 4s 3s +33%
polyeta_unpack 4s 8s -50%
polyveck_reduce 4s 4s +0%
polyvecl_pointwise_acc_montgomery_native 4s 2s +100%
polyw1_pack 4s 4s +0%
polyw1_pack_32 4s 4s +0%
polyz_unpack_17_native_aarch64 4s 3s +33%
shake128x4_squeezeblocks 4s 3s +33%
shake256_squeeze 4s 3s +33%
shake256x4_squeezeblocks 4s 2s +100%
sig_unpack_hints 4s 2s +100%
sign_signature_pre_hash_shake256 4s 3s +33%
sign_verify_pre_hash_internal 4s 5s -20%
sk_t0hat_get_poly 4s 2s +100%
unpack_sk 4s 3s +33%
unpack_sk_t0hat 4s 5s -20%
caddq 3s 3s +0%
intt_native_aarch64 3s 3s +0%
keccak_absorb 3s 3s +0%
keccak_f1600_x4_native_avx2 3s 2s +50%
keccak_finalize 3s 2s +50%
keccak_squeezeblocks_x4 3s 5s -40%
keccakf1600_extract_bytes (big endian) 3s 2s +50%
keccakf1600_xor_bytes 3s 2s +50%
keccakf1600x4_extract_bytes 3s 4s -25%
keccakf1600x4_extract_bytes_native 3s 4s -25%
keccakf1600x4_xor_bytes 3s 1s +200%
keccakf1600x4_xor_bytes_native 3s 3s +0%
make_hint 3s 2s +50%
mld_ct_cmask_neg_i32 3s 2s +50%
mld_ct_cmask_nonzero_u8 3s 3s +0%
mld_ct_get_optblocker_u8 3s 2s +50%
mld_ct_memcmp 3s 2s +50%
mld_keccakf1600_extract_bytes 3s 1s +200%
mld_prepare_domain_separation_prefix 3s 2s +50%
mld_value_barrier_i64 3s 2s +50%
mld_value_barrier_u32 3s 3s +0%
montgomery_reduce 3s 4s -25%
pack_sig_c 3s 5s -40%
pack_sig_z 3s 2s +50%
pack_sk_s1 3s 5s -40%
pointwise_native_aarch64 3s 5s -40%
poly_caddq_native 3s 2s +50%
poly_caddq_native_x86_64 3s 3s +0%
poly_chknorm_native 3s 2s +50%
poly_decompose_32_native_aarch64 3s 3s +0%
poly_decompose_88_native_aarch64 3s 1s +200%
poly_ntt 3s 2s +50%
poly_pointwise_montgomery 3s 3s +0%
poly_pointwise_montgomery_native 3s 3s +0%
poly_reduce 3s 3s +0%
poly_sub 3s 3s +0%
poly_use_hint_native_x86_64 3s - new
polyeta_pack 3s 3s +0%
polyveck_pack_w1 3s 3s +0%
polyvecl_pack_eta 3s 3s +0%
polyvecl_uniform_gamma1 3s 2s +50%
polyvecl_unpack_z 3s 3s +0%
polyw1_pack_88 3s 2s +50%
polyz_unpack 3s 3s +0%
polyz_unpack_19_native_aarch64 3s 3s +0%
reduce32 3s 3s +0%
rej_uniform_eta_native_aarch64 3s 4s -25%
rej_uniform_native_aarch64 3s 3s +0%
shake128_finalize 3s 1s +200%
shake128_squeeze 3s 2s +50%
shake256_absorb 3s 2s +50%
shake256_init 3s 2s +50%
shake256x4_absorb_once 3s 3s +0%
sign_signature 3s 6s -50%
unpack_sk_s2hat 3s 4s -25%
yvec_get_poly 3s 3s +0%
yvec_init 3s 3s +0%
keccak_f1600_x4_native_aarch64_v84a 2s 4s -50%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 2s 2s +0%
keccakf1600_permute 2s 2s +0%
keccakf1600_permute_native 2s 3s -33%
keccakf1600_xor_bytes (big endian) 2s 2s +0%
keccakf1600x4_permute 2s 4s -50%
mld_ct_cmask_nonzero_u32 2s 4s -50%
mld_ct_get_optblocker_u32 2s 3s -33%
mld_keccakf1600x4_extract_bytes_c 2s 3s -33%
ntt_native_x86_64 2s 2s +0%
pack_sig_h 2s 5s -60%
pointwise_native_x86_64 2s 3s -33%
poly_caddq_native_aarch64 2s 2s +0%
poly_chknorm 2s 4s -50%
poly_chknorm_native_x86_64 2s 3s -33%
poly_decompose_native 2s 3s -33%
poly_ntt_native 2s 4s -50%
poly_permute_bitrev_to_custom_optional 2s 2s +0%
poly_permute_bitrev_to_custom_optional_native 2s 4s -50%
poly_uniform_gamma1 2s 3s -33%
poly_uniform_gamma1_4x 2s 4s -50%
poly_use_hint 2s 3s -33%
poly_use_hint_native 2s 2s +0%
polyt0_pack 2s 3s -33%
polyt1_pack 2s 3s -33%
polyvec_matrix_pointwise_montgomery_row 2s 1s +100%
polyveck_pack_eta 2s 4s -50%
polyveck_unpack_eta 2s 6s -67%
polyvecl_unpack_eta 2s 3s -33%
polyz_unpack_native 2s 4s -50%
rej_eta 2s 2s +0%
shake128_absorb 2s 2s +0%
shake128_init 2s 2s +0%
shake128_release 2s 3s -33%
shake256 2s 2s +0%
shake256_finalize 2s 1s +100%
shake256_release 2s 2s +0%
sign_keypair_internal 2s 5s -60%
sk_s1hat_get_poly 2s 6s -67%
sys_check_capability 2s 4s -50%
unpack_sk_s1hat 2s 2s +0%
use_hint 2s 2s +0%
keccak_f1600_x1_native_aarch64 1s 2s -50%
keccak_f1600_x1_native_aarch64_v84a 1s 3s -67%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 1s 2s -50%
mld_ct_get_optblocker_i64 1s 2s -50%
mld_ct_sel_int32 1s 3s -67%
mld_value_barrier_u8 1s 3s -67%
poly_caddq 1s 2s -50%
poly_decompose 1s 2s -50%
poly_uniform_eta 1s 4s -75%
power2round 1s 1s +0%
shake128x4_absorb_once 1s 3s -67%
sk_s2hat_get_poly 1s 2s -50%

@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-44)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 1613s 1514s +6.5%
polyvecl_pointwise_acc_montgomery_c 155s 131s +18%
poly_pointwise_montgomery_c 136s 114s +19%
sign_verify_internal 128s 114s +12%
mld_invntt_layer 117s 107s +9%
mld_attempt_signature_generation 61s 58s +5%
compute_pack_t0_t1 53s 50s +6%
fqmul 43s 39s +10%
mld_ntt_layer 43s 42s +2%
polyvec_matrix_expand 28s 28s +0%
mld_ntt_butterfly_block 24s 23s +4%
keccakf1600x4_permute_native 23s 22s +5%
sign_signature_internal 23s 26s -12%
poly_ntt_c 20s 19s +5%
polyt0_unpack 18s 15s +20%
rej_uniform 18s 18s +0%
poly_chknorm_c 17s 17s +0%
polyvec_matrix_pointwise_montgomery_yvec 17s 15s +13%
polyeta_unpack 16s 14s +14%
mld_check_pct 15s 14s +7%
rej_uniform_c 15s 15s +0%
keccak_absorb_once_x4 13s 9s +44%
poly_uniform_4x 13s 14s -7%
poly_uniform_eta_4x 13s 11s +18%
poly_invntt_tomont_c 12s 11s +9%
polyz_unpack_c 11s 11s +0%
polyvecl_chknorm 10s 10s +0%
mld_compute_pack_z 8s 7s +14%
pointwise_acc_native_aarch64 7s 4s +75%
pointwise_acc_native_x86_64 7s 7s +0%
polyvec_matrix_expand_serial 7s 8s -12%
polyvecl_ntt 7s 2s +250%
mld_ct_memcmp 6s 3s +100%
mld_keccakf1600_permute_c 6s 8s -25%
ntt_native_aarch64 6s 3s +100%
poly_add 6s 7s -14%
polyt1_unpack 6s 5s +20%
polyveck_caddq 6s 3s +100%
sig_unpack_hints 6s 2s +200%
sign_keypair_internal 6s 4s +50%
sign_verify 6s 4s +50%
mld_sample_s1_s2 5s 4s +25%
ntt_native_x86_64 5s 3s +67%
poly_challenge 5s 3s +67%
poly_decompose_32_native_aarch64 5s 2s +150%
poly_decompose_c 5s 4s +25%
poly_reduce 5s 3s +67%
polyveck_chknorm 5s 5s +0%
polyveck_decompose 5s 4s +25%
polyveck_unpack_eta 5s 2s +150%
polyvecl_unpack_eta 5s 2s +150%
rej_uniform_native 5s 4s +25%
sign_keypair 5s 4s +25%
sign_pk_from_sk 5s 5s +0%
sign_signature_pre_hash_shake256 5s 3s +67%
sign_verify_pre_hash_internal 5s 3s +67%
decompose 4s 2s +100%
intt_native_aarch64 4s 9s -56%
keccak_absorb 4s 5s -20%
keccakf1600_permute 4s 2s +100%
mld_ct_abs_i32 4s 2s +100%
mld_ct_cmask_nonzero_u8 4s 2s +100%
mld_h 4s 4s +0%
mld_keccakf1600x4_extract_bytes_c 4s 2s +100%
mld_prepare_domain_separation_prefix 4s 4s +0%
nttunpack_native_x86_64 4s 1s +300%
pack_sk_rho_key_tr_s2 4s 3s +33%
pointwise_native_x86_64 4s 4s +0%
poly_caddq 4s 2s +100%
poly_caddq_native 4s 5s -20%
poly_decompose 4s 3s +33%
poly_decompose_native 4s 3s +33%
poly_decompose_native_x86_64 4s 3s +33%
poly_ntt 4s 3s +33%
poly_ntt_native 4s 5s -20%
poly_shiftl 4s 3s +33%
poly_sub 4s 3s +33%
poly_uniform_eta 4s 5s -20%
poly_uniform_gamma1_4x 4s 5s -20%
poly_use_hint_native_x86_64 4s - new
polyveck_invntt_tomont 4s 5s -20%
polyvecl_pack_eta 4s 3s +33%
polyw1_pack 4s 3s +33%
polyw1_pack_88 4s 1s +300%
reduce32 4s 2s +100%
shake128_absorb 4s 2s +100%
shake128_release 4s 1s +300%
sign_signature_extmu 4s 4s +0%
sign_signature_pre_hash_internal 4s 6s -33%
sign_verify_extmu 4s 3s +33%
sk_t0hat_get_poly 4s 2s +100%
unpack_sk 4s 3s +33%
yvec_init 4s 3s +33%
caddq 3s 2s +50%
intt_native_x86_64 3s 4s -25%
keccak_f1600_x1_native_aarch64_v84a 3s 3s +0%
keccak_f1600_x4_native_avx2 3s 3s +0%
keccak_finalize 3s 3s +0%
keccak_squeezeblocks_x4 3s 4s -25%
keccakf1600_permute_native 3s 3s +0%
keccakf1600_xor_bytes (big endian) 3s 4s -25%
mld_ct_cmask_nonzero_u32 3s 2s +50%
mld_keccakf1600_extract_bytes 3s 2s +50%
montgomery_reduce 3s 3s +0%
pack_sig_c 3s 2s +50%
pack_sig_h 3s 3s +0%
pack_sk_s1 3s 2s +50%
pointwise_native_aarch64 3s 5s -40%
poly_caddq_c 3s 2s +50%
poly_chknorm_native_aarch64 3s 4s -25%
poly_chknorm_native_x86_64 3s 2s +50%
poly_decompose_88_native_aarch64 3s 4s -25%
poly_permute_bitrev_to_custom_optional_native 3s 4s -25%
poly_pointwise_montgomery 3s 3s +0%
poly_uniform_gamma1 3s 4s -25%
poly_use_hint_c 3s 3s +0%
poly_use_hint_native 3s 4s -25%
poly_use_hint_native_aarch64 3s 2s +50%
polyt0_pack 3s 2s +50%
polyveck_ntt 3s 5s -40%
polyveck_pack_eta 3s 2s +50%
polyveck_pack_w1 3s 1s +200%
polyveck_reduce 3s 5s -40%
polyvecl_uniform_gamma1_serial 3s 2s +50%
polyz_unpack_19_native_aarch64 3s 5s -40%
polyz_unpack_native 3s 2s +50%
power2round 3s 3s +0%
rej_eta 3s 3s +0%
rej_eta_c 3s 4s -25%
rej_eta_native 3s 6s -50%
rej_uniform_eta_native_aarch64 3s 2s +50%
shake128_init 3s 3s +0%
shake128x4_squeezeblocks 3s 1s +200%
shake256 3s 1s +200%
shake256_finalize 3s 2s +50%
shake256_init 3s 3s +0%
shake256x4_absorb_once 3s 3s +0%
shake256x4_squeezeblocks 3s 4s -25%
sign_signature 3s 3s +0%
sk_s1hat_get_poly 3s 3s +0%
unpack_sk_s2hat 3s 4s -25%
unpack_sk_t0hat 3s 3s +0%
use_hint 3s 2s +50%
fqscale 2s 3s -33%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 2s 1s +100%
keccak_init 2s 3s -33%
keccakf1600x4_permute 2s 4s -50%
keccakf1600x4_xor_bytes 2s 2s +0%
keccakf1600x4_xor_bytes_native 2s 3s -33%
mld_ct_get_optblocker_u32 2s 1s +100%
mld_ct_sel_int32 2s 2s +0%
mld_keccakf1600x4_xor_bytes_c 2s 2s +0%
mld_polymat_expand_entry 2s 3s -33%
mld_sample_s1_s2_serial 2s 3s -33%
mld_value_barrier_i64 2s 2s +0%
mld_value_barrier_u32 2s 2s +0%
mld_value_barrier_u8 2s 3s -33%
pack_sig_z 2s 4s -50%
poly_caddq_native_aarch64 2s 4s -50%
poly_caddq_native_x86_64 2s 4s -50%
poly_chknorm 2s 4s -50%
poly_chknorm_native 2s 4s -50%
poly_invntt_tomont 2s 4s -50%
poly_invntt_tomont_native 2s 4s -50%
poly_permute_bitrev_to_custom_optional 2s 2s +0%
poly_pointwise_montgomery_native 2s 2s +0%
poly_power2round 2s 4s -50%
poly_uniform 2s 6s -67%
poly_use_hint 2s 4s -50%
polyeta_pack 2s 3s -33%
polyvec_matrix_pointwise_montgomery_row 2s 2s +0%
polyvecl_pointwise_acc_montgomery 2s 4s -50%
polyvecl_pointwise_acc_montgomery_native 2s 2s +0%
polyvecl_uniform_gamma1 2s 3s -33%
polyvecl_unpack_z 2s 2s +0%
polyw1_pack_32 2s 2s +0%
polyz_pack 2s 2s +0%
polyz_unpack 2s 3s -33%
polyz_unpack_17_native_aarch64 2s 5s -60%
polyz_unpack_native_x86_64 2s 3s -33%
shake128_finalize 2s 2s +0%
shake128_squeeze 2s 1s +100%
shake128x4_absorb_once 2s 3s -33%
shake256_squeeze 2s 2s +0%
sign_verify_pre_hash_shake256 2s 5s -60%
sk_s2hat_get_poly 2s 2s +0%
sys_check_capability 2s 4s -50%
unpack_sk_s1hat 2s 1s +100%
keccak_f1600_x1_native_aarch64 1s 2s -50%
keccak_f1600_x4_native_aarch64_v84a 1s 2s -50%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 1s 3s -67%
keccak_squeeze 1s 1s +0%
keccakf1600_extract_bytes (big endian) 1s 2s -50%
keccakf1600_xor_bytes 1s 1s +0%
keccakf1600x4_extract_bytes 1s 2s -50%
keccakf1600x4_extract_bytes_native 1s 3s -67%
make_hint 1s 3s -67%
mld_ct_cmask_neg_i32 1s 3s -67%
mld_ct_get_optblocker_i64 1s 4s -75%
mld_ct_get_optblocker_u8 1s 1s +0%
polyt1_pack 1s 4s -75%
rej_uniform_native_aarch64 1s 5s -80%
shake256_absorb 1s 3s -67%
shake256_release 1s 2s -50%
unpack_pk_t1 1s 5s -80%
yvec_get_poly 1s 3s -67%

@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-65, REDUCE-RAM)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 1480s 1482s -0.1%
polyvec_matrix_pointwise_montgomery_yvec 198s 201s -1%
poly_pointwise_montgomery_c 122s 116s +5%
mld_invntt_layer 119s 108s +10%
sign_verify_internal 72s 71s +1%
mld_ntt_layer 44s 43s +2%
polyvecl_chknorm 44s 43s +2%
fqmul 43s 40s +7%
polyveck_chknorm 33s 36s -8%
mld_attempt_signature_generation 32s 31s +3%
keccakf1600x4_permute_native 23s 22s +5%
mld_ntt_butterfly_block 23s 25s -8%
poly_ntt_c 19s 22s -14%
rej_uniform_c 15s 16s -6%
mld_check_pct 14s 12s +17%
poly_chknorm_c 13s 13s +0%
poly_invntt_tomont_c 13s 10s +30%
polyt0_unpack 12s 13s -8%
poly_uniform_eta_4x 11s 13s -15%
polyveck_decompose 10s 14s -29%
compute_pack_t0_t1 9s 7s +29%
keccak_absorb_once_x4 8s 10s -20%
polyveck_reduce 8s 6s +33%
polyz_unpack_c 8s 9s -11%
rej_uniform 8s 7s +14%
sign_pk_from_sk 8s 5s +60%
mld_h 7s 3s +133%
polyvec_matrix_pointwise_montgomery_row 7s 8s -12%
polyvecl_ntt 7s 7s +0%
sign_verify_pre_hash_internal 7s 5s +40%
mld_compute_pack_z 6s 5s +20%
mld_keccakf1600_permute_c 6s 7s -14%
nttunpack_native_x86_64 6s 3s +100%
poly_add 6s 7s -14%
poly_decompose_c 6s 8s -25%
poly_pointwise_montgomery 6s 2s +200%
poly_uniform_eta 6s 5s +20%
polyt0_pack 6s 5s +20%
polyveck_caddq 6s 7s -14%
polyveck_invntt_tomont 6s 7s -14%
polyz_unpack_native_x86_64 6s 3s +100%
sign_keypair 6s 4s +50%
mld_polymat_expand_entry 5s 3s +67%
pointwise_acc_native_aarch64 5s 6s -17%
pointwise_acc_native_x86_64 5s 5s +0%
poly_caddq_c 5s 5s +0%
poly_decompose 5s 2s +150%
poly_power2round 5s 7s -29%
poly_reduce 5s 4s +25%
poly_uniform 5s 2s +150%
polyvec_matrix_expand 5s 6s -17%
reduce32 5s 2s +150%
rej_eta_native 5s 3s +67%
rej_uniform_native 5s 4s +25%
sign_signature_pre_hash_shake256 5s 7s -29%
keccakf1600x4_permute 4s 1s +300%
mld_ct_cmask_nonzero_u32 4s 3s +33%
mld_ct_cmask_nonzero_u8 4s 2s +100%
mld_ct_get_optblocker_i64 4s 1s +300%
mld_prepare_domain_separation_prefix 4s 4s +0%
mld_sample_s1_s2 4s 6s -33%
mld_sample_s1_s2_serial 4s 3s +33%
mld_value_barrier_i64 4s 2s +100%
pack_sig_h 4s 2s +100%
pointwise_native_aarch64 4s 3s +33%
pointwise_native_x86_64 4s 2s +100%
poly_decompose_88_native_aarch64 4s 2s +100%
poly_decompose_native 4s 5s -20%
poly_uniform_4x 4s 4s +0%
poly_use_hint_c 4s 2s +100%
poly_use_hint_native 4s 7s -43%
poly_use_hint_native_aarch64 4s 4s +0%
polyveck_unpack_eta 4s 3s +33%
polyvecl_pointwise_acc_montgomery_native 4s 3s +33%
rej_uniform_native_aarch64 4s 5s -20%
shake256 4s 2s +100%
shake256_absorb 4s 4s +0%
sign_signature 4s 5s -20%
sign_signature_extmu 4s 4s +0%
sign_signature_pre_hash_internal 4s 3s +33%
sign_verify 4s 6s -33%
sign_verify_extmu 4s 2s +100%
sys_check_capability 4s 1s +300%
decompose 3s 4s -25%
intt_native_aarch64 3s 2s +50%
keccak_absorb 3s 3s +0%
keccak_f1600_x4_native_aarch64_v84a 3s 2s +50%
keccak_f1600_x4_native_avx2 3s 2s +50%
keccak_squeeze 3s 2s +50%
keccak_squeezeblocks_x4 3s 4s -25%
keccakf1600x4_extract_bytes 3s 4s -25%
keccakf1600x4_extract_bytes_native 3s 1s +200%
keccakf1600x4_xor_bytes_native 3s 2s +50%
make_hint 3s 3s +0%
mld_ct_get_optblocker_u8 3s 4s -25%
mld_ct_memcmp 3s 4s -25%
mld_ct_sel_int32 3s 2s +50%
mld_keccakf1600x4_extract_bytes_c 3s 2s +50%
mld_value_barrier_u32 3s 4s -25%
mld_value_barrier_u8 3s 1s +200%
pack_sig_c 3s 3s +0%
pack_sk_rho_key_tr_s2 3s 2s +50%
poly_caddq_native 3s 4s -25%
poly_caddq_native_aarch64 3s 2s +50%
poly_caddq_native_x86_64 3s 1s +200%
poly_challenge 3s 5s -40%
poly_chknorm_native_x86_64 3s 4s -25%
poly_decompose_32_native_aarch64 3s 4s -25%
poly_decompose_native_x86_64 3s 2s +50%
poly_invntt_tomont_native 3s 5s -40%
poly_ntt_native 3s 2s +50%
poly_permute_bitrev_to_custom_optional_native 3s 3s +0%
poly_pointwise_montgomery_native 3s 4s -25%
poly_shiftl 3s 3s +0%
polyt1_unpack 3s 3s +0%
polyveck_ntt 3s 4s -25%
polyveck_pack_eta 3s 3s +0%
polyveck_pack_w1 3s 4s -25%
polyvecl_pointwise_acc_montgomery 3s 3s +0%
polyvecl_pointwise_acc_montgomery_c 3s 3s +0%
polyvecl_uniform_gamma1 3s 4s -25%
polyvecl_uniform_gamma1_serial 3s 1s +200%
polyvecl_unpack_z 3s 1s +200%
polyw1_pack_88 3s 3s +0%
polyz_unpack 3s 3s +0%
polyz_unpack_19_native_aarch64 3s 5s -40%
polyz_unpack_native 3s 3s +0%
power2round 3s 2s +50%
rej_eta_c 3s 4s -25%
rej_uniform_eta_native_aarch64 3s 5s -40%
shake128_release 3s 2s +50%
shake128x4_squeezeblocks 3s 2s +50%
shake256_release 3s 3s +0%
shake256_squeeze 3s 4s -25%
sign_keypair_internal 3s 3s +0%
sign_signature_internal 3s 6s -50%
sk_s1hat_get_poly 3s 3s +0%
unpack_pk_t1 3s 2s +50%
unpack_sk 3s 3s +0%
unpack_sk_s1hat 3s 1s +200%
unpack_sk_s2hat 3s 3s +0%
yvec_init 3s 5s -40%
caddq 2s 2s +0%
fqscale 2s 3s -33%
intt_native_x86_64 2s 4s -50%
keccak_f1600_x1_native_aarch64 2s 2s +0%
keccak_f1600_x1_native_aarch64_v84a 2s 2s +0%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 2s 3s -33%
keccak_init 2s 4s -50%
keccakf1600_extract_bytes (big endian) 2s 3s -33%
keccakf1600x4_xor_bytes 2s 2s +0%
mld_ct_abs_i32 2s 6s -67%
mld_ct_get_optblocker_u32 2s 3s -33%
mld_keccakf1600_extract_bytes 2s 2s +0%
montgomery_reduce 2s 1s +100%
ntt_native_aarch64 2s 3s -33%
ntt_native_x86_64 2s 5s -60%
pack_sig_z 2s 1s +100%
pack_sk_s1 2s 3s -33%
poly_caddq 2s 3s -33%
poly_chknorm 2s 3s -33%
poly_chknorm_native 2s 4s -50%
poly_chknorm_native_aarch64 2s 2s +0%
poly_invntt_tomont 2s 5s -60%
poly_ntt 2s 2s +0%
poly_permute_bitrev_to_custom_optional 2s 3s -33%
poly_sub 2s 4s -50%
poly_uniform_gamma1 2s 3s -33%
poly_uniform_gamma1_4x 2s 3s -33%
poly_use_hint_native_x86_64 2s - new
polyeta_pack 2s 1s +100%
polyeta_unpack 2s 4s -50%
polyt1_pack 2s 3s -33%
polyvec_matrix_expand_serial 2s 3s -33%
polyvecl_pack_eta 2s 2s +0%
polyvecl_unpack_eta 2s 2s +0%
polyw1_pack 2s 3s -33%
polyw1_pack_32 2s 2s +0%
polyz_pack 2s 3s -33%
polyz_unpack_17_native_aarch64 2s 2s +0%
rej_eta 2s 5s -60%
shake128_absorb 2s 2s +0%
shake128_finalize 2s 2s +0%
shake128_init 2s 6s -67%
shake128_squeeze 2s 3s -33%
shake128x4_absorb_once 2s 2s +0%
shake256_finalize 2s 1s +100%
shake256_init 2s 4s -50%
shake256x4_absorb_once 2s 2s +0%
shake256x4_squeezeblocks 2s 2s +0%
sig_unpack_hints 2s 1s +100%
sign_verify_pre_hash_shake256 2s 6s -67%
sk_t0hat_get_poly 2s 1s +100%
unpack_sk_t0hat 2s 4s -50%
use_hint 2s 2s +0%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 1s 3s -67%
keccak_finalize 1s 2s -50%
keccakf1600_permute 1s 4s -75%
keccakf1600_permute_native 1s 2s -50%
keccakf1600_xor_bytes 1s 4s -75%
keccakf1600_xor_bytes (big endian) 1s 2s -50%
mld_ct_cmask_neg_i32 1s 3s -67%
mld_keccakf1600x4_xor_bytes_c 1s 2s -50%
poly_use_hint 1s 3s -67%
sk_s2hat_get_poly 1s 1s +0%
yvec_get_poly 1s 3s -67%

@oqs-bot

oqs-bot commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

CBMC Results (ML-DSA-87)

Full Results (205 proofs)
Proof Status Current Previous Change
**TOTAL** 2102s 2151s -2.3%
polyvecl_pointwise_acc_montgomery_c 361s 353s +2%
polyvec_matrix_expand 312s 324s -4%
poly_pointwise_montgomery_c 126s 144s -12%
mld_invntt_layer 114s 115s -1%
sign_verify_internal 96s 97s -1%
mld_attempt_signature_generation 54s 55s -2%
mld_ntt_layer 43s 45s -4%
fqmul 41s 43s -5%
sign_signature_internal 39s 42s -7%
polyvec_matrix_expand_serial 38s 38s +0%
keccakf1600x4_permute_native 22s 23s -4%
mld_ntt_butterfly_block 22s 24s -8%
compute_pack_t0_t1 19s 19s +0%
poly_ntt_c 18s 21s -14%
polyvec_matrix_pointwise_montgomery_yvec 18s 18s +0%
mld_check_pct 17s 16s +6%
poly_chknorm_c 16s 15s +7%
polyeta_unpack 16s 17s -6%
polyt0_unpack 16s 14s +14%
rej_uniform_c 16s 19s -16%
poly_uniform_eta_4x 14s 11s +27%
rej_uniform 14s 15s -7%
poly_invntt_tomont_c 12s 12s +0%
poly_uniform_4x 12s 13s -8%
keccak_absorb_once_x4 10s 9s +11%
mld_compute_pack_z 10s 8s +25%
polyveck_decompose 10s 13s -23%
polyveck_ntt 10s 11s -9%
pointwise_acc_native_aarch64 9s 6s +50%
pointwise_acc_native_x86_64 9s 6s +50%
polyveck_invntt_tomont 9s 9s +0%
poly_add 8s 6s +33%
polyvecl_ntt 8s 7s +14%
mld_keccakf1600_permute_c 7s 7s +0%
mld_sample_s1_s2 7s 6s +17%
mld_sample_s1_s2_serial 6s 8s -25%
poly_uniform 6s 4s +50%
poly_use_hint_native_x86_64 6s - new
polyveck_caddq 6s 8s -25%
polyvecl_uniform_gamma1 6s 2s +200%
sign_pk_from_sk 6s 6s +0%
sign_signature_extmu 6s 4s +50%
sign_signature_pre_hash_internal 6s 5s +20%
sign_verify_extmu 6s 3s +100%
sign_verify_pre_hash_internal 6s 3s +100%
ntt_native_x86_64 5s 2s +150%
pointwise_native_x86_64 5s 2s +150%
poly_challenge 5s 5s +0%
poly_decompose_c 5s 5s +0%
poly_ntt 5s 3s +67%
poly_pointwise_montgomery 5s 4s +25%
polyt1_unpack 5s 4s +25%
polyveck_pack_w1 5s 3s +67%
polyveck_unpack_eta 5s 4s +25%
polyvecl_chknorm 5s 7s -29%
polyz_unpack_native 5s 4s +25%
sign_signature 5s 5s +0%
sign_verify_pre_hash_shake256 5s 3s +67%
unpack_sk_t0hat 5s 7s -29%
caddq 4s 4s +0%
decompose 4s 3s +33%
intt_native_aarch64 4s 3s +33%
keccak_squeeze 4s 2s +100%
mld_ct_cmask_nonzero_u8 4s 3s +33%
mld_ct_get_optblocker_u8 4s 3s +33%
mld_h 4s 3s +33%
mld_value_barrier_u8 4s 3s +33%
montgomery_reduce 4s 3s +33%
pack_sig_c 4s 4s +0%
pack_sig_h 4s 4s +0%
poly_caddq_native_aarch64 4s 3s +33%
poly_chknorm_native_x86_64 4s 2s +100%
poly_decompose_32_native_aarch64 4s 5s -20%
poly_invntt_tomont_native 4s 5s -20%
poly_ntt_native 4s 3s +33%
poly_shiftl 4s 4s +0%
poly_uniform_eta 4s 4s +0%
poly_use_hint_c 4s 2s +100%
poly_use_hint_native 4s 3s +33%
poly_use_hint_native_aarch64 4s 2s +100%
polyeta_pack 4s 4s +0%
polyt0_pack 4s 4s +0%
polyveck_chknorm 4s 3s +33%
polyveck_pack_eta 4s 6s -33%
polyvecl_pack_eta 4s 3s +33%
polyvecl_uniform_gamma1_serial 4s 4s +0%
polyvecl_unpack_eta 4s 5s -20%
polyw1_pack 4s 4s +0%
polyz_unpack_native_x86_64 4s 3s +33%
power2round 4s 4s +0%
reduce32 4s 3s +33%
rej_uniform_native 4s 8s -50%
sign_keypair 4s 4s +0%
sign_keypair_internal 4s 6s -33%
sign_signature_pre_hash_shake256 4s 6s -33%
sk_s2hat_get_poly 4s 3s +33%
sk_t0hat_get_poly 4s 4s +0%
sys_check_capability 4s 3s +33%
unpack_sk 4s 5s -20%
intt_native_x86_64 3s 3s +0%
keccak_init 3s 3s +0%
keccak_squeezeblocks_x4 3s 4s -25%
keccakf1600_extract_bytes (big endian) 3s 3s +0%
keccakf1600_permute 3s 3s +0%
keccakf1600_xor_bytes 3s 3s +0%
keccakf1600_xor_bytes (big endian) 3s 2s +50%
keccakf1600x4_xor_bytes 3s 3s +0%
make_hint 3s 3s +0%
mld_ct_cmask_neg_i32 3s 4s -25%
mld_ct_get_optblocker_i64 3s 3s +0%
mld_ct_sel_int32 3s 3s +0%
mld_keccakf1600_extract_bytes 3s 4s -25%
mld_keccakf1600x4_extract_bytes_c 3s 2s +50%
mld_keccakf1600x4_xor_bytes_c 3s 4s -25%
mld_value_barrier_u32 3s 2s +50%
nttunpack_native_x86_64 3s 3s +0%
pack_sig_z 3s 5s -40%
pointwise_native_aarch64 3s 5s -40%
poly_caddq 3s 2s +50%
poly_caddq_native 3s 4s -25%
poly_caddq_native_x86_64 3s 2s +50%
poly_chknorm 3s 3s +0%
poly_chknorm_native 3s 4s -25%
poly_decompose_native 3s 2s +50%
poly_decompose_native_x86_64 3s 2s +50%
poly_invntt_tomont 3s 1s +200%
poly_permute_bitrev_to_custom_optional 3s 3s +0%
poly_permute_bitrev_to_custom_optional_native 3s 5s -40%
poly_reduce 3s 2s +50%
poly_sub 3s 3s +0%
poly_uniform_gamma1_4x 3s 3s +0%
polyveck_reduce 3s 3s +0%
polyz_unpack_17_native_aarch64 3s 3s +0%
polyz_unpack_19_native_aarch64 3s 4s -25%
rej_eta 3s 4s -25%
rej_eta_native 3s 6s -50%
rej_uniform_eta_native_aarch64 3s 5s -40%
shake128_absorb 3s 4s -25%
shake128_finalize 3s 2s +50%
shake128x4_absorb_once 3s 5s -40%
shake128x4_squeezeblocks 3s 3s +0%
shake256 3s 2s +50%
shake256_absorb 3s 2s +50%
shake256_finalize 3s 2s +50%
shake256_release 3s 3s +0%
shake256x4_squeezeblocks 3s 1s +200%
sig_unpack_hints 3s 3s +0%
sign_verify 3s 5s -40%
sk_s1hat_get_poly 3s 3s +0%
unpack_pk_t1 3s 1s +200%
unpack_sk_s1hat 3s 2s +50%
fqscale 2s 3s -33%
keccak_absorb 2s 3s -33%
keccak_f1600_x1_native_aarch64 2s 1s +100%
keccak_f1600_x1_native_aarch64_v84a 2s 1s +100%
keccak_f1600_x4_native_aarch64_v84a 2s 4s -50%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid 2s 3s -33%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid 2s 4s -50%
keccak_f1600_x4_native_avx2 2s 2s +0%
keccak_finalize 2s 1s +100%
keccakf1600x4_extract_bytes 2s 2s +0%
keccakf1600x4_extract_bytes_native 2s 2s +0%
keccakf1600x4_permute 2s 3s -33%
keccakf1600x4_xor_bytes_native 2s 3s -33%
mld_ct_abs_i32 2s 3s -33%
mld_ct_cmask_nonzero_u32 2s 2s +0%
mld_ct_get_optblocker_u32 2s 2s +0%
mld_ct_memcmp 2s 3s -33%
mld_polymat_expand_entry 2s 3s -33%
mld_prepare_domain_separation_prefix 2s 4s -50%
mld_value_barrier_i64 2s 1s +100%
ntt_native_aarch64 2s 6s -67%
pack_sk_rho_key_tr_s2 2s 3s -33%
pack_sk_s1 2s 1s +100%
poly_caddq_c 2s 3s -33%
poly_chknorm_native_aarch64 2s 4s -50%
poly_decompose 2s 3s -33%
poly_pointwise_montgomery_native 2s 5s -60%
poly_power2round 2s 3s -33%
poly_uniform_gamma1 2s 4s -50%
poly_use_hint 2s 1s +100%
polyt1_pack 2s 3s -33%
polyvec_matrix_pointwise_montgomery_row 2s 3s -33%
polyvecl_pointwise_acc_montgomery 2s 5s -60%
polyvecl_pointwise_acc_montgomery_native 2s 3s -33%
polyvecl_unpack_z 2s 4s -50%
polyw1_pack_32 2s 4s -50%
polyw1_pack_88 2s 3s -33%
polyz_pack 2s 5s -60%
polyz_unpack 2s 2s +0%
polyz_unpack_c 2s 3s -33%
rej_uniform_native_aarch64 2s 2s +0%
shake128_init 2s 1s +100%
shake128_release 2s 4s -50%
shake128_squeeze 2s 2s +0%
shake256_squeeze 2s 2s +0%
shake256x4_absorb_once 2s 2s +0%
unpack_sk_s2hat 2s 3s -33%
yvec_get_poly 2s 4s -50%
yvec_init 2s 4s -50%
keccakf1600_permute_native 1s 4s -75%
poly_decompose_88_native_aarch64 1s 2s -50%
rej_eta_c 1s 5s -80%
shake256_init 1s 2s -50%
use_hint 1s 3s -67%

@bremoran bremoran marked this pull request as draft July 9, 2026 07:19
@bremoran

bremoran commented Jul 9, 2026

Copy link
Copy Markdown
Contributor Author

I've marked this PR as a draft because while MVE memset/memcpy/zeroize did have a positive impact on reducing key pair generation, it had the opposite effect on signature generation and verification. This should not be the case and was not the case when I added it in local testing. However, I added it after other assembly optimisations, not before. Therefore, I'll defer this one until it makes an improvement in all benchmarks.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants