x86_64: 32-byte align Keccak x4 AVX2 stack frame

[hanno-becker]

For better performance, align stack to 32-byte in the AVX2 x4 Keccak backend implementation.

Updates HOL-Light proofs accordingly. Unfortunately, no existing tactic for the extension from the 'core' to the 'subroutine' proofs can handle the pattern we use, so we fall back to some ad-hoc tactics. As and when s2n-bignum adds support for stack alignment to its automation, this can hopefully be removed.

We also extend scripts/cfify to track the CFA register. A mov rsp, %REG re-anchors the CFA on REG, and subsequent modifications to the RSP do not require CFI directives. We handle this by conditioning the rules subq/addq->cfi_adjust_cfa_offset on the operand being the current CFA reg.

[oqs-bot]

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

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	1393s	1412s	-1.3%
poly_pointwise_montgomery_c	✅	170s	164s	+4%
rej_uniform_native	✅	103s	107s	-4%
mld_invntt_layer	✅	99s	98s	+1%
polyvec_matrix_pointwise_montgomery_yvec	✅	89s	90s	-1%
mld_ct_memcmp	✅	67s	65s	+3%
mld_ntt_layer	✅	42s	41s	+2%
fqmul	✅	29s	27s	+7%
mld_attempt_signature_generation	✅	27s	26s	+4%
sign_verify_internal	✅	24s	23s	+4%
keccakf1600x4_permute_native	✅	21s	22s	-5%
rej_uniform	✅	19s	19s	+0%
rej_uniform_c	✅	19s	19s	+0%
polyeta_unpack	✅	16s	15s	+7%
mld_ntt_butterfly_block	✅	15s	14s	+7%
poly_chknorm_c	✅	14s	15s	-7%
mld_check_pct	✅	13s	16s	-19%
poly_add	✅	13s	12s	+8%
polyz_unpack_c	✅	13s	12s	+8%
poly_uniform_eta_4x	✅	11s	10s	+10%
polyt0_unpack	✅	10s	12s	-17%
polyveck_chknorm	✅	10s	11s	-9%
keccak_absorb_once_x4	✅	9s	10s	-10%
poly_caddq_c	✅	9s	8s	+12%
poly_decompose_c	✅	8s	8s	+0%
poly_power2round	✅	8s	6s	+33%
polyvec_matrix_pointwise_montgomery_row	✅	8s	7s	+14%
keccak_absorb	✅	7s	5s	+40%
keccak_squeezeblocks_x4	✅	7s	4s	+75%
sign	✅	7s	8s	-12%
compute_pack_t0_t1	✅	6s	6s	+0%
keccakf1600x4_extract_bytes_native	✅	6s	4s	+50%
mld_compute_pack_z	✅	6s	6s	+0%
mld_keccakf1600_permute_c	✅	6s	6s	+0%
poly_invntt_tomont_c	✅	6s	8s	-25%
poly_uniform	✅	6s	3s	+100%
polyt0_pack	✅	6s	3s	+100%
sign_pk_from_sk	✅	6s	4s	+50%
sign_verify_pre_hash_internal	✅	6s	3s	+100%
mld_h	✅	5s	6s	-17%
pointwise_acc_native_x86_64	✅	5s	5s	+0%
poly_chknorm	✅	5s	1s	+400%
poly_decompose_32_native_aarch64	✅	5s	3s	+67%
poly_invntt_tomont	✅	5s	3s	+67%
poly_shiftl	✅	5s	5s	+0%
polyveck_invntt_tomont	✅	5s	4s	+25%
polyvecl_ntt	✅	5s	4s	+25%
polyz_unpack_17_native_aarch64	✅	5s	3s	+67%
sign_keypair	✅	5s	4s	+25%
sign_open	✅	5s	6s	-17%
sign_verify_extmu	✅	5s	5s	+0%
decompose	✅	4s	5s	-20%
keccakf1600_xor_bytes (big endian)	✅	4s	2s	+100%
keccakf1600x4_extract_bytes	✅	4s	3s	+33%
keccakf1600x4_permute	✅	4s	3s	+33%
mld_keccakf1600x4_extract_bytes_c	✅	4s	4s	+0%
mld_sample_s1_s2_serial	✅	4s	4s	+0%
pointwise_acc_native_aarch64	✅	4s	4s	+0%
pointwise_native_aarch64	✅	4s	2s	+100%
pointwise_native_x86_64	✅	4s	4s	+0%
poly_caddq	✅	4s	3s	+33%
poly_caddq_native	✅	4s	3s	+33%
poly_challenge	✅	4s	3s	+33%
poly_ntt	✅	4s	3s	+33%
poly_reduce	✅	4s	1s	+300%
poly_uniform_eta	✅	4s	5s	-20%
poly_uniform_gamma1	✅	4s	2s	+100%
poly_use_hint_native	✅	4s	2s	+100%
polyt1_unpack	✅	4s	3s	+33%
polyveck_reduce	✅	4s	7s	-43%
polyvecl_chknorm	✅	4s	3s	+33%
sign_keypair_internal	✅	4s	5s	-20%
sign_signature	✅	4s	7s	-43%
sign_signature_internal	✅	4s	5s	-20%
sign_signature_pre_hash_internal	✅	4s	6s	-33%
sign_signature_pre_hash_shake256	✅	4s	2s	+100%
sign_verify_pre_hash_shake256	✅	4s	2s	+100%
sk_s2hat_get_poly	✅	4s	4s	+0%
sys_check_capability	✅	4s	3s	+33%
intt_native_aarch64	✅	3s	4s	-25%
intt_native_x86_64	✅	3s	6s	-50%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	3s	2s	+50%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	3s	4s	-25%
keccak_finalize	✅	3s	2s	+50%
keccak_init	✅	3s	2s	+50%
make_hint	✅	3s	4s	-25%
mld_ct_get_optblocker_u32	✅	3s	2s	+50%
mld_polymat_expand_entry	✅	3s	2s	+50%
mld_sample_s1_s2	✅	3s	3s	+0%
montgomery_reduce	✅	3s	3s	+0%
ntt_native_x86_64	✅	3s	4s	-25%
nttunpack_native_x86_64	✅	3s	2s	+50%
pack_sig_h	✅	3s	5s	-40%
poly_chknorm_native_aarch64	✅	3s	3s	+0%
poly_invntt_tomont_native	✅	3s	4s	-25%
poly_ntt_native	✅	3s	2s	+50%
poly_permute_bitrev_to_custom_optional_native	✅	3s	2s	+50%
poly_sub	✅	3s	2s	+50%
poly_uniform_4x	✅	3s	2s	+50%
poly_uniform_gamma1_4x	✅	3s	3s	+0%
poly_use_hint_c	✅	3s	3s	+0%
polyvec_matrix_expand_serial	✅	3s	3s	+0%
polyveck_caddq	✅	3s	6s	-50%
polyveck_decompose	✅	3s	8s	-62%
polyveck_pack_eta	✅	3s	4s	-25%
polyveck_unpack_eta	✅	3s	2s	+50%
polyvecl_pointwise_acc_montgomery	✅	3s	3s	+0%
polyvecl_uniform_gamma1_serial	✅	3s	2s	+50%
polyvecl_unpack_eta	✅	3s	2s	+50%
polyw1_pack	✅	3s	2s	+50%
polyz_pack	✅	3s	4s	-25%
reduce32	✅	3s	3s	+0%
rej_eta	✅	3s	3s	+0%
rej_eta_c	✅	3s	3s	+0%
shake128_absorb	✅	3s	4s	-25%
shake128_init	✅	3s	1s	+200%
shake128_release	✅	3s	2s	+50%
shake128x4_squeezeblocks	✅	3s	2s	+50%
shake256	✅	3s	2s	+50%
shake256_finalize	✅	3s	3s	+0%
shake256_release	✅	3s	2s	+50%
shake256_squeeze	✅	3s	2s	+50%
shake256x4_absorb_once	✅	3s	1s	+200%
sig_unpack_hints	✅	3s	3s	+0%
sign_signature_extmu	✅	3s	5s	-40%
sign_verify	✅	3s	3s	+0%
sk_s1hat_get_poly	✅	3s	2s	+50%
sk_t0hat_get_poly	✅	3s	3s	+0%
unpack_sk_s1hat	✅	3s	3s	+0%
yvec_init	✅	3s	3s	+0%
caddq	✅	2s	2s	+0%
fqscale	✅	2s	4s	-50%
keccak_f1600_x1_native_aarch64	✅	2s	3s	-33%
keccak_f1600_x4_native_aarch64_v84a	✅	2s	5s	-60%
keccak_f1600_x4_native_avx2	✅	2s	2s	+0%
keccak_squeeze	✅	2s	3s	-33%
keccakf1600_permute	✅	2s	2s	+0%
keccakf1600_permute_native	✅	2s	2s	+0%
keccakf1600x4_xor_bytes	✅	2s	4s	-50%
keccakf1600x4_xor_bytes_native	✅	2s	3s	-33%
mld_ct_abs_i32	✅	2s	4s	-50%
mld_ct_cmask_neg_i32	✅	2s	1s	+100%
mld_ct_cmask_nonzero_u32	✅	2s	2s	+0%
mld_ct_cmask_nonzero_u8	✅	2s	3s	-33%
mld_ct_get_optblocker_i64	✅	2s	4s	-50%
mld_ct_get_optblocker_u8	✅	2s	2s	+0%
mld_keccakf1600_extract_bytes	✅	2s	4s	-50%
mld_prepare_domain_separation_prefix	✅	2s	7s	-71%
mld_value_barrier_i64	✅	2s	2s	+0%
mld_value_barrier_u32	✅	2s	2s	+0%
mld_value_barrier_u8	✅	2s	2s	+0%
ntt_native_aarch64	✅	2s	2s	+0%
pack_sig_c	✅	2s	4s	-50%
pack_sig_z	✅	2s	3s	-33%
pack_sk_rho_key_tr_s2	✅	2s	2s	+0%
pack_sk_s1	✅	2s	3s	-33%
poly_caddq_native_aarch64	✅	2s	2s	+0%
poly_decompose	✅	2s	4s	-50%
poly_decompose_88_native_aarch64	✅	2s	5s	-60%
poly_decompose_native	✅	2s	3s	-33%
poly_ntt_c	✅	2s	3s	-33%
poly_permute_bitrev_to_custom_optional	✅	2s	2s	+0%
poly_pointwise_montgomery_native	✅	2s	2s	+0%
poly_use_hint	✅	2s	3s	-33%
poly_use_hint_native_aarch64	✅	2s	3s	-33%
polyeta_pack	✅	2s	5s	-60%
polyt1_pack	✅	2s	2s	+0%
polyvec_matrix_expand	✅	2s	4s	-50%
polyveck_pack_w1	✅	2s	3s	-33%
polyvecl_pack_eta	✅	2s	4s	-50%
polyvecl_pointwise_acc_montgomery_c	✅	2s	3s	-33%
polyvecl_uniform_gamma1	✅	2s	2s	+0%
polyvecl_unpack_z	✅	2s	2s	+0%
polyz_unpack_19_native_aarch64	✅	2s	6s	-67%
polyz_unpack_native	✅	2s	2s	+0%
power2round	✅	2s	3s	-33%
rej_eta_native	✅	2s	3s	-33%
shake128_finalize	✅	2s	1s	+100%
shake128_squeeze	✅	2s	3s	-33%
shake128x4_absorb_once	✅	2s	2s	+0%
shake256_absorb	✅	2s	2s	+0%
shake256x4_squeezeblocks	✅	2s	1s	+100%
unpack_pk_t1	✅	2s	2s	+0%
unpack_sk	✅	2s	3s	-33%
unpack_sk_t0hat	✅	2s	2s	+0%
use_hint	✅	2s	3s	-33%
yvec_get_poly	✅	2s	4s	-50%
keccak_f1600_x1_native_aarch64_v84a	✅	1s	2s	-50%
keccakf1600_extract_bytes (big endian)	✅	1s	2s	-50%
keccakf1600_xor_bytes	✅	1s	3s	-67%
mld_ct_sel_int32	✅	1s	1s	+0%
mld_keccakf1600x4_xor_bytes_c	✅	1s	3s	-67%
poly_chknorm_native	✅	1s	3s	-67%
poly_pointwise_montgomery	✅	1s	4s	-75%
polyveck_ntt	✅	1s	2s	-50%
polyvecl_pointwise_acc_montgomery_native	✅	1s	2s	-50%
polyz_unpack	✅	1s	2s	-50%
rej_uniform_native_aarch64	✅	1s	-	new
shake256_init	✅	1s	2s	-50%
unpack_sk_s2hat	✅	1s	2s	-50%

[oqs-bot]

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

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	1557s	1563s	-0.4%
poly_pointwise_montgomery_c	✅	189s	198s	-5%
polyvec_matrix_pointwise_montgomery_yvec	✅	135s	135s	+0%
mld_invntt_layer	✅	112s	113s	-1%
rej_uniform_native	✅	109s	116s	-6%
mld_ct_memcmp	✅	72s	70s	+3%
mld_ntt_layer	✅	45s	46s	-2%
sign_verify_internal	✅	38s	37s	+3%
fqmul	✅	31s	27s	+15%
mld_attempt_signature_generation	✅	26s	27s	-4%
keccakf1600x4_permute_native	✅	23s	24s	-4%
rej_uniform	✅	21s	23s	-9%
rej_uniform_c	✅	21s	19s	+11%
mld_ntt_butterfly_block	✅	16s	15s	+7%
polyeta_unpack	✅	16s	15s	+7%
polyveck_decompose	✅	16s	15s	+7%
mld_check_pct	✅	13s	12s	+8%
poly_chknorm_c	✅	13s	15s	-13%
poly_uniform_eta_4x	✅	12s	11s	+9%
polyt0_unpack	✅	11s	12s	-8%
poly_add	✅	10s	14s	-29%
keccak_absorb_once_x4	✅	9s	10s	-10%
pointwise_acc_native_x86_64	✅	9s	6s	+50%
poly_caddq_c	✅	9s	8s	+12%
polyvec_matrix_pointwise_montgomery_row	✅	9s	10s	-10%
sign_pk_from_sk	✅	9s	7s	+29%
compute_pack_t0_t1	✅	8s	6s	+33%
mld_keccakf1600_permute_c	✅	8s	6s	+33%
pointwise_acc_native_aarch64	✅	8s	9s	-11%
keccak_absorb	✅	7s	6s	+17%
mld_sample_s1_s2	✅	7s	6s	+17%
mld_sample_s1_s2_serial	✅	7s	6s	+17%
poly_power2round	✅	7s	9s	-22%
polyz_unpack_c	✅	7s	7s	+0%
rej_eta_native	✅	7s	4s	+75%
ntt_native_aarch64	✅	6s	2s	+200%
poly_decompose_c	✅	6s	4s	+50%
poly_invntt_tomont_c	✅	6s	8s	-25%
poly_ntt	✅	6s	5s	+20%
poly_pointwise_montgomery	✅	6s	2s	+200%
polyveck_caddq	✅	6s	6s	+0%
polyveck_chknorm	✅	6s	7s	-14%
polyveck_reduce	✅	6s	7s	-14%
polyvecl_ntt	✅	6s	9s	-33%
rej_uniform_native_aarch64	✅	6s	-	new
sign	✅	6s	10s	-40%
sign_keypair_internal	✅	6s	5s	+20%
sign_open	✅	6s	3s	+100%
intt_native_aarch64	✅	5s	2s	+150%
keccak_squeezeblocks_x4	✅	5s	4s	+25%
mld_compute_pack_z	✅	5s	5s	+0%
pack_sk_s1	✅	5s	2s	+150%
poly_ntt_c	✅	5s	4s	+25%
poly_permute_bitrev_to_custom_optional_native	✅	5s	3s	+67%
poly_shiftl	✅	5s	6s	-17%
polyt1_unpack	✅	5s	3s	+67%
polyveck_invntt_tomont	✅	5s	5s	+0%
rej_eta	✅	5s	2s	+150%
rej_eta_c	✅	5s	4s	+25%
sign_keypair	✅	5s	3s	+67%
sign_signature_internal	✅	5s	4s	+25%
sign_verify_pre_hash_internal	✅	5s	4s	+25%
sign_verify_pre_hash_shake256	✅	5s	6s	-17%
sk_t0hat_get_poly	✅	5s	3s	+67%
unpack_pk_t1	✅	5s	2s	+150%
keccak_f1600_x1_native_aarch64	✅	4s	2s	+100%
keccakf1600x4_extract_bytes_native	✅	4s	1s	+300%
make_hint	✅	4s	2s	+100%
mld_ct_cmask_nonzero_u8	✅	4s	4s	+0%
mld_value_barrier_i64	✅	4s	1s	+300%
ntt_native_x86_64	✅	4s	3s	+33%
pointwise_native_aarch64	✅	4s	2s	+100%
poly_caddq	✅	4s	5s	-20%
poly_chknorm_native	✅	4s	4s	+0%
poly_ntt_native	✅	4s	2s	+100%
poly_permute_bitrev_to_custom_optional	✅	4s	3s	+33%
poly_uniform_4x	✅	4s	4s	+0%
poly_uniform_gamma1	✅	4s	3s	+33%
poly_uniform_gamma1_4x	✅	4s	3s	+33%
poly_use_hint	✅	4s	3s	+33%
polyveck_ntt	✅	4s	5s	-20%
polyveck_unpack_eta	✅	4s	4s	+0%
polyvecl_chknorm	✅	4s	5s	-20%
polyz_unpack	✅	4s	1s	+300%
polyz_unpack_19_native_aarch64	✅	4s	3s	+33%
shake256_absorb	✅	4s	4s	+0%
sig_unpack_hints	✅	4s	2s	+100%
sign_signature	✅	4s	4s	+0%
sign_signature_pre_hash_internal	✅	4s	4s	+0%
sk_s1hat_get_poly	✅	4s	3s	+33%
yvec_get_poly	✅	4s	3s	+33%
caddq	✅	3s	2s	+50%
decompose	✅	3s	3s	+0%
fqscale	✅	3s	3s	+0%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	3s	3s	+0%
keccak_f1600_x4_native_avx2	✅	3s	2s	+50%
keccak_finalize	✅	3s	2s	+50%
keccak_squeeze	✅	3s	5s	-40%
keccakf1600_extract_bytes (big endian)	✅	3s	2s	+50%
keccakf1600_permute	✅	3s	2s	+50%
mld_ct_get_optblocker_u32	✅	3s	1s	+200%
mld_prepare_domain_separation_prefix	✅	3s	5s	-40%
pack_sig_h	✅	3s	2s	+50%
pack_sk_rho_key_tr_s2	✅	3s	1s	+200%
pointwise_native_x86_64	✅	3s	3s	+0%
poly_caddq_native_aarch64	✅	3s	4s	-25%
poly_challenge	✅	3s	5s	-40%
poly_chknorm_native_aarch64	✅	3s	2s	+50%
poly_invntt_tomont	✅	3s	3s	+0%
poly_invntt_tomont_native	✅	3s	4s	-25%
poly_pointwise_montgomery_native	✅	3s	4s	-25%
poly_reduce	✅	3s	2s	+50%
poly_uniform	✅	3s	2s	+50%
poly_uniform_eta	✅	3s	5s	-40%
poly_use_hint_native	✅	3s	2s	+50%
polyvec_matrix_expand_serial	✅	3s	3s	+0%
polyvecl_pointwise_acc_montgomery_c	✅	3s	2s	+50%
polyvecl_uniform_gamma1_serial	✅	3s	3s	+0%
polyvecl_unpack_z	✅	3s	2s	+50%
polyz_pack	✅	3s	3s	+0%
polyz_unpack_17_native_aarch64	✅	3s	4s	-25%
polyz_unpack_native	✅	3s	4s	-25%
power2round	✅	3s	1s	+200%
reduce32	✅	3s	3s	+0%
shake128_absorb	✅	3s	3s	+0%
shake128_finalize	✅	3s	2s	+50%
shake128_release	✅	3s	4s	-25%
shake256_release	✅	3s	4s	-25%
sign_signature_pre_hash_shake256	✅	3s	3s	+0%
sign_verify_extmu	✅	3s	2s	+50%
sys_check_capability	✅	3s	3s	+0%
unpack_sk	✅	3s	2s	+50%
unpack_sk_s2hat	✅	3s	5s	-40%
intt_native_x86_64	✅	2s	5s	-60%
keccak_f1600_x1_native_aarch64_v84a	✅	2s	1s	+100%
keccak_f1600_x4_native_aarch64_v84a	✅	2s	3s	-33%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	2s	1s	+100%
keccak_init	✅	2s	3s	-33%
keccakf1600_xor_bytes (big endian)	✅	2s	3s	-33%
keccakf1600x4_extract_bytes	✅	2s	2s	+0%
keccakf1600x4_permute	✅	2s	2s	+0%
keccakf1600x4_xor_bytes	✅	2s	2s	+0%
keccakf1600x4_xor_bytes_native	✅	2s	2s	+0%
mld_ct_abs_i32	✅	2s	2s	+0%
mld_ct_cmask_neg_i32	✅	2s	1s	+100%
mld_ct_cmask_nonzero_u32	✅	2s	4s	-50%
mld_ct_get_optblocker_i64	✅	2s	1s	+100%
mld_ct_get_optblocker_u8	✅	2s	3s	-33%
mld_ct_sel_int32	✅	2s	2s	+0%
mld_h	✅	2s	4s	-50%
mld_keccakf1600_extract_bytes	✅	2s	5s	-60%
mld_keccakf1600x4_extract_bytes_c	✅	2s	3s	-33%
mld_keccakf1600x4_xor_bytes_c	✅	2s	3s	-33%
mld_polymat_expand_entry	✅	2s	3s	-33%
mld_value_barrier_u8	✅	2s	2s	+0%
montgomery_reduce	✅	2s	4s	-50%
nttunpack_native_x86_64	✅	2s	4s	-50%
pack_sig_c	✅	2s	2s	+0%
poly_caddq_native	✅	2s	4s	-50%
poly_chknorm	✅	2s	3s	-33%
poly_decompose_32_native_aarch64	✅	2s	2s	+0%
poly_decompose_native	✅	2s	1s	+100%
poly_sub	✅	2s	5s	-60%
poly_use_hint_c	✅	2s	4s	-50%
poly_use_hint_native_aarch64	✅	2s	2s	+0%
polyeta_pack	✅	2s	3s	-33%
polyt0_pack	✅	2s	3s	-33%
polyt1_pack	✅	2s	1s	+100%
polyvec_matrix_expand	✅	2s	3s	-33%
polyveck_pack_eta	✅	2s	3s	-33%
polyveck_pack_w1	✅	2s	3s	-33%
polyvecl_pack_eta	✅	2s	4s	-50%
polyvecl_pointwise_acc_montgomery_native	✅	2s	3s	-33%
polyvecl_uniform_gamma1	✅	2s	2s	+0%
polyvecl_unpack_eta	✅	2s	2s	+0%
polyw1_pack	✅	2s	2s	+0%
shake128_init	✅	2s	5s	-60%
shake128_squeeze	✅	2s	3s	-33%
shake256	✅	2s	4s	-50%
shake256_init	✅	2s	2s	+0%
shake256_squeeze	✅	2s	4s	-50%
shake256x4_absorb_once	✅	2s	1s	+100%
shake256x4_squeezeblocks	✅	2s	2s	+0%
sign_signature_extmu	✅	2s	4s	-50%
sign_verify	✅	2s	4s	-50%
sk_s2hat_get_poly	✅	2s	4s	-50%
unpack_sk_s1hat	✅	2s	3s	-33%
unpack_sk_t0hat	✅	2s	2s	+0%
use_hint	✅	2s	5s	-60%
yvec_init	✅	2s	4s	-50%
keccakf1600_permute_native	✅	1s	2s	-50%
keccakf1600_xor_bytes	✅	1s	2s	-50%
mld_value_barrier_u32	✅	1s	2s	-50%
pack_sig_z	✅	1s	2s	-50%
poly_decompose	✅	1s	3s	-67%
poly_decompose_88_native_aarch64	✅	1s	2s	-50%
polyvecl_pointwise_acc_montgomery	✅	1s	2s	-50%
shake128x4_absorb_once	✅	1s	4s	-75%
shake128x4_squeezeblocks	✅	1s	1s	+0%
shake256_finalize	✅	1s	3s	-67%

[oqs-bot]

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

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	1596s	1497s	+6.6%
poly_pointwise_montgomery_c	✅	186s	175s	+6%
polyvec_matrix_pointwise_montgomery_yvec	✅	160s	150s	+7%
rej_uniform_native	✅	112s	98s	+14%
mld_invntt_layer	✅	109s	102s	+7%
mld_ct_memcmp	✅	69s	66s	+5%
mld_ntt_layer	✅	44s	43s	+2%
fqmul	✅	29s	28s	+4%
mld_attempt_signature_generation	✅	28s	27s	+4%
sign_verify_internal	✅	26s	28s	-7%
keccakf1600x4_permute_native	✅	22s	21s	+5%
rej_uniform	✅	21s	20s	+5%
rej_uniform_c	✅	21s	18s	+17%
polyvecl_chknorm	✅	19s	18s	+6%
mld_check_pct	✅	18s	15s	+20%
mld_ntt_butterfly_block	✅	15s	17s	-12%
poly_chknorm_c	✅	14s	13s	+8%
poly_uniform_eta_4x	✅	13s	11s	+18%
polyveck_decompose	✅	13s	12s	+8%
poly_add	✅	11s	12s	-8%
polyt0_unpack	✅	11s	12s	-8%
compute_pack_t0_t1	✅	9s	7s	+29%
keccak_absorb	✅	9s	6s	+50%
poly_invntt_tomont_c	✅	9s	8s	+12%
polyvec_matrix_pointwise_montgomery_row	✅	9s	9s	+0%
polyveck_caddq	✅	9s	10s	-10%
polyz_unpack_c	✅	9s	6s	+50%
mld_prepare_domain_separation_prefix	✅	8s	5s	+60%
polyvecl_ntt	✅	8s	8s	+0%
intt_native_x86_64	✅	7s	3s	+133%
keccak_absorb_once_x4	✅	7s	10s	-30%
mld_keccakf1600_permute_c	✅	7s	7s	+0%
poly_caddq_c	✅	7s	9s	-22%
poly_power2round	✅	7s	7s	+0%
sign	✅	7s	6s	+17%
mld_compute_pack_z	✅	6s	6s	+0%
nttunpack_native_x86_64	✅	6s	4s	+50%
pointwise_acc_native_aarch64	✅	6s	5s	+20%
pointwise_native_x86_64	✅	6s	5s	+20%
poly_decompose_c	✅	6s	5s	+20%
poly_shiftl	✅	6s	5s	+20%
poly_uniform	✅	6s	5s	+20%
polyveck_chknorm	✅	6s	2s	+200%
polyveck_reduce	✅	6s	7s	-14%
sign_keypair_internal	✅	6s	6s	+0%
sign_signature_extmu	✅	6s	6s	+0%
sign_signature_internal	✅	6s	5s	+20%
sign_signature_pre_hash_internal	✅	6s	3s	+100%
sign_signature_pre_hash_shake256	✅	6s	5s	+20%
keccak_squeezeblocks_x4	✅	5s	3s	+67%
keccakf1600_xor_bytes	✅	5s	3s	+67%
keccakf1600x4_xor_bytes	✅	5s	3s	+67%
mld_ct_get_optblocker_u32	✅	5s	2s	+150%
ntt_native_aarch64	✅	5s	4s	+25%
poly_challenge	✅	5s	4s	+25%
poly_chknorm_native	✅	5s	3s	+67%
poly_invntt_tomont_native	✅	5s	2s	+150%
poly_ntt	✅	5s	2s	+150%
poly_ntt_c	✅	5s	2s	+150%
poly_ntt_native	✅	5s	3s	+67%
poly_permute_bitrev_to_custom_optional	✅	5s	3s	+67%
polyeta_unpack	✅	5s	3s	+67%
polyt0_pack	✅	5s	5s	+0%
polyw1_pack	✅	5s	4s	+25%
polyz_unpack_17_native_aarch64	✅	5s	2s	+150%
rej_eta_c	✅	5s	3s	+67%
rej_eta_native	✅	5s	7s	-29%
shake128_absorb	✅	5s	3s	+67%
shake128_finalize	✅	5s	2s	+150%
sign_pk_from_sk	✅	5s	5s	+0%
use_hint	✅	5s	2s	+150%
caddq	✅	4s	3s	+33%
intt_native_aarch64	✅	4s	4s	+0%
keccakf1600_permute	✅	4s	1s	+300%
keccakf1600_xor_bytes (big endian)	✅	4s	2s	+100%
mld_sample_s1_s2	✅	4s	5s	-20%
mld_sample_s1_s2_serial	✅	4s	5s	-20%
pack_sig_c	✅	4s	2s	+100%
pack_sk_s1	✅	4s	5s	-20%
pointwise_acc_native_x86_64	✅	4s	5s	-20%
poly_decompose_native	✅	4s	3s	+33%
poly_sub	✅	4s	3s	+33%
poly_uniform_eta	✅	4s	3s	+33%
poly_use_hint	✅	4s	3s	+33%
polyeta_pack	✅	4s	3s	+33%
polyt1_unpack	✅	4s	2s	+100%
polyveck_invntt_tomont	✅	4s	7s	-43%
polyveck_pack_eta	✅	4s	3s	+33%
polyvecl_uniform_gamma1_serial	✅	4s	3s	+33%
polyvecl_unpack_eta	✅	4s	3s	+33%
polyvecl_unpack_z	✅	4s	3s	+33%
rej_eta	✅	4s	3s	+33%
rej_uniform_native_aarch64	✅	4s	-	new
shake128x4_absorb_once	✅	4s	2s	+100%
shake256_finalize	✅	4s	2s	+100%
shake256_init	✅	4s	4s	+0%
sig_unpack_hints	✅	4s	3s	+33%
sign_signature	✅	4s	5s	-20%
sign_verify_pre_hash_internal	✅	4s	3s	+33%
sign_verify_pre_hash_shake256	✅	4s	4s	+0%
unpack_pk_t1	✅	4s	3s	+33%
unpack_sk_t0hat	✅	4s	3s	+33%
keccak_f1600_x1_native_aarch64_v84a	✅	3s	1s	+200%
keccak_f1600_x4_native_aarch64_v84a	✅	3s	3s	+0%
keccak_f1600_x4_native_avx2	✅	3s	2s	+50%
keccak_finalize	✅	3s	3s	+0%
keccak_squeeze	✅	3s	2s	+50%
keccakf1600x4_permute	✅	3s	2s	+50%
mld_ct_cmask_neg_i32	✅	3s	2s	+50%
mld_ct_cmask_nonzero_u8	✅	3s	2s	+50%
mld_ct_sel_int32	✅	3s	2s	+50%
mld_keccakf1600x4_xor_bytes_c	✅	3s	1s	+200%
ntt_native_x86_64	✅	3s	3s	+0%
pack_sig_h	✅	3s	3s	+0%
pack_sig_z	✅	3s	2s	+50%
pack_sk_rho_key_tr_s2	✅	3s	2s	+50%
pointwise_native_aarch64	✅	3s	5s	-40%
poly_caddq	✅	3s	3s	+0%
poly_caddq_native	✅	3s	3s	+0%
poly_caddq_native_aarch64	✅	3s	3s	+0%
poly_chknorm_native_aarch64	✅	3s	4s	-25%
poly_decompose_32_native_aarch64	✅	3s	3s	+0%
poly_decompose_88_native_aarch64	✅	3s	3s	+0%
poly_pointwise_montgomery	✅	3s	3s	+0%
poly_reduce	✅	3s	2s	+50%
poly_uniform_gamma1	✅	3s	4s	-25%
poly_use_hint_c	✅	3s	2s	+50%
poly_use_hint_native	✅	3s	3s	+0%
poly_use_hint_native_aarch64	✅	3s	4s	-25%
polyveck_ntt	✅	3s	3s	+0%
polyveck_unpack_eta	✅	3s	2s	+50%
polyvecl_pack_eta	✅	3s	3s	+0%
polyvecl_uniform_gamma1	✅	3s	1s	+200%
polyz_unpack	✅	3s	2s	+50%
shake128_init	✅	3s	2s	+50%
shake128_squeeze	✅	3s	3s	+0%
shake256	✅	3s	3s	+0%
sign_open	✅	3s	4s	-25%
sign_verify_extmu	✅	3s	4s	-25%
sk_s1hat_get_poly	✅	3s	3s	+0%
sk_t0hat_get_poly	✅	3s	3s	+0%
unpack_sk_s2hat	✅	3s	1s	+200%
decompose	✅	2s	3s	-33%
fqscale	✅	2s	4s	-50%
keccak_f1600_x1_native_aarch64	✅	2s	4s	-50%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	2s	1s	+100%
keccakf1600_permute_native	✅	2s	2s	+0%
keccakf1600x4_extract_bytes	✅	2s	2s	+0%
keccakf1600x4_extract_bytes_native	✅	2s	2s	+0%
keccakf1600x4_xor_bytes_native	✅	2s	3s	-33%
make_hint	✅	2s	3s	-33%
mld_ct_abs_i32	✅	2s	2s	+0%
mld_ct_cmask_nonzero_u32	✅	2s	1s	+100%
mld_ct_get_optblocker_i64	✅	2s	2s	+0%
mld_h	✅	2s	4s	-50%
mld_keccakf1600x4_extract_bytes_c	✅	2s	2s	+0%
mld_polymat_expand_entry	✅	2s	6s	-67%
mld_value_barrier_i64	✅	2s	3s	-33%
mld_value_barrier_u8	✅	2s	3s	-33%
montgomery_reduce	✅	2s	3s	-33%
poly_chknorm	✅	2s	1s	+100%
poly_decompose	✅	2s	3s	-33%
poly_permute_bitrev_to_custom_optional_native	✅	2s	4s	-50%
poly_pointwise_montgomery_native	✅	2s	5s	-60%
poly_uniform_4x	✅	2s	3s	-33%
poly_uniform_gamma1_4x	✅	2s	4s	-50%
polyt1_pack	✅	2s	4s	-50%
polyvec_matrix_expand	✅	2s	3s	-33%
polyvec_matrix_expand_serial	✅	2s	2s	+0%
polyveck_pack_w1	✅	2s	1s	+100%
polyvecl_pointwise_acc_montgomery	✅	2s	4s	-50%
polyvecl_pointwise_acc_montgomery_c	✅	2s	3s	-33%
polyvecl_pointwise_acc_montgomery_native	✅	2s	2s	+0%
polyz_pack	✅	2s	3s	-33%
polyz_unpack_19_native_aarch64	✅	2s	2s	+0%
polyz_unpack_native	✅	2s	3s	-33%
power2round	✅	2s	5s	-60%
reduce32	✅	2s	4s	-50%
shake128x4_squeezeblocks	✅	2s	1s	+100%
shake256_squeeze	✅	2s	3s	-33%
shake256x4_absorb_once	✅	2s	3s	-33%
shake256x4_squeezeblocks	✅	2s	2s	+0%
sign_keypair	✅	2s	4s	-50%
sign_verify	✅	2s	3s	-33%
sys_check_capability	✅	2s	5s	-60%
unpack_sk	✅	2s	3s	-33%
unpack_sk_s1hat	✅	2s	2s	+0%
yvec_get_poly	✅	2s	5s	-60%
yvec_init	✅	2s	3s	-33%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	1s	2s	-50%
keccak_init	✅	1s	2s	-50%
keccakf1600_extract_bytes (big endian)	✅	1s	3s	-67%
mld_ct_get_optblocker_u8	✅	1s	3s	-67%
mld_keccakf1600_extract_bytes	✅	1s	3s	-67%
mld_value_barrier_u32	✅	1s	2s	-50%
poly_invntt_tomont	✅	1s	2s	-50%
shake128_release	✅	1s	1s	+0%
shake256_absorb	✅	1s	2s	-50%
shake256_release	✅	1s	3s	-67%
sk_s2hat_get_poly	✅	1s	2s	-50%

[oqs-bot]

CBMC Results (ML-DSA-87)

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	2149s	1987s	+8.2%
polyvecl_pointwise_acc_montgomery_c	✅	300s	250s	+20%
polyvec_matrix_expand	✅	183s	169s	+8%
rej_uniform_native	✅	130s	124s	+5%
mld_attempt_signature_generation	✅	105s	102s	+3%
poly_pointwise_montgomery_c	✅	104s	92s	+13%
mld_invntt_layer	✅	99s	93s	+6%
sign_verify_internal	✅	91s	88s	+3%
mld_ct_memcmp	✅	75s	65s	+15%
sign_signature_internal	✅	55s	54s	+2%
mld_ntt_layer	✅	44s	41s	+7%
polyvec_matrix_expand_serial	✅	44s	37s	+19%
fqmul	✅	32s	26s	+23%
compute_pack_t0_t1	✅	26s	26s	+0%
keccakf1600x4_permute_native	✅	25s	24s	+4%
polyvec_matrix_pointwise_montgomery_yvec	✅	22s	21s	+5%
poly_chknorm_c	✅	19s	15s	+27%
rej_uniform_c	✅	19s	19s	+0%
mld_ntt_butterfly_block	✅	18s	17s	+6%
rej_uniform	✅	18s	15s	+20%
poly_uniform_eta_4x	✅	13s	13s	+0%
polyeta_unpack	✅	13s	11s	+18%
polyt0_unpack	✅	13s	13s	+0%
keccak_absorb_once_x4	✅	12s	9s	+33%
polyveck_decompose	✅	12s	12s	+0%
poly_add	✅	11s	11s	+0%
poly_uniform_4x	✅	11s	11s	+0%
poly_invntt_tomont_c	✅	10s	7s	+43%
poly_ntt	✅	10s	4s	+150%
polyveck_ntt	✅	10s	10s	+0%
mld_check_pct	✅	9s	11s	-18%
mld_sample_s1_s2_serial	✅	9s	9s	+0%
poly_power2round	✅	9s	7s	+29%
polyz_unpack_c	✅	9s	7s	+29%
sign	✅	9s	8s	+12%
mld_compute_pack_z	✅	8s	7s	+14%
poly_caddq_c	✅	8s	4s	+100%
polyveck_caddq	✅	8s	7s	+14%
polyveck_invntt_tomont	✅	8s	9s	-11%
mld_keccakf1600_permute_c	✅	7s	7s	+0%
pointwise_acc_native_aarch64	✅	7s	8s	-12%
polyvecl_chknorm	✅	7s	5s	+40%
sign_keypair	✅	7s	4s	+75%
sign_signature_extmu	✅	7s	4s	+75%
keccak_absorb	✅	6s	5s	+20%
keccak_init	✅	6s	3s	+100%
pointwise_acc_native_x86_64	✅	6s	8s	-25%
poly_challenge	✅	6s	2s	+200%
polyt1_pack	✅	6s	2s	+200%
polyveck_chknorm	✅	6s	6s	+0%
polyvecl_ntt	✅	6s	7s	-14%
sign_open	✅	6s	5s	+20%
sign_pk_from_sk	✅	6s	6s	+0%
sign_signature	✅	6s	4s	+50%
fqscale	✅	5s	2s	+150%
intt_native_aarch64	✅	5s	3s	+67%
mld_sample_s1_s2	✅	5s	6s	-17%
ntt_native_x86_64	✅	5s	4s	+25%
pack_sig_h	✅	5s	4s	+25%
poly_sub	✅	5s	5s	+0%
poly_uniform_eta	✅	5s	4s	+25%
poly_uniform_gamma1_4x	✅	5s	3s	+67%
poly_use_hint_c	✅	5s	4s	+25%
polyveck_pack_eta	✅	5s	4s	+25%
polyvecl_uniform_gamma1	✅	5s	2s	+150%
power2round	✅	5s	3s	+67%
rej_eta_native	✅	5s	3s	+67%
shake256x4_absorb_once	✅	5s	3s	+67%
shake256x4_squeezeblocks	✅	5s	5s	+0%
sign_signature_pre_hash_internal	✅	5s	3s	+67%
caddq	✅	4s	2s	+100%
intt_native_x86_64	✅	4s	3s	+33%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	4s	4s	+0%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	4s	3s	+33%
keccak_squeezeblocks_x4	✅	4s	4s	+0%
keccakf1600x4_permute	✅	4s	4s	+0%
mld_ct_get_optblocker_u8	✅	4s	3s	+33%
mld_keccakf1600_extract_bytes	✅	4s	2s	+100%
mld_keccakf1600x4_extract_bytes_c	✅	4s	3s	+33%
mld_polymat_expand_entry	✅	4s	3s	+33%
mld_prepare_domain_separation_prefix	✅	4s	5s	-20%
pointwise_native_x86_64	✅	4s	4s	+0%
poly_caddq	✅	4s	3s	+33%
poly_caddq_native	✅	4s	3s	+33%
poly_chknorm_native_aarch64	✅	4s	4s	+0%
poly_decompose_88_native_aarch64	✅	4s	2s	+100%
poly_decompose_c	✅	4s	3s	+33%
poly_permute_bitrev_to_custom_optional	✅	4s	3s	+33%
poly_pointwise_montgomery_native	✅	4s	3s	+33%
poly_shiftl	✅	4s	5s	-20%
poly_uniform	✅	4s	2s	+100%
poly_use_hint_native_aarch64	✅	4s	2s	+100%
polyeta_pack	✅	4s	4s	+0%
polyt0_pack	✅	4s	4s	+0%
polyt1_unpack	✅	4s	4s	+0%
polyvec_matrix_pointwise_montgomery_row	✅	4s	2s	+100%
polyveck_unpack_eta	✅	4s	3s	+33%
polyvecl_pointwise_acc_montgomery_native	✅	4s	4s	+0%
polyz_unpack_19_native_aarch64	✅	4s	3s	+33%
shake128_squeeze	✅	4s	2s	+100%
shake256	✅	4s	2s	+100%
shake256_release	✅	4s	1s	+300%
sign_verify	✅	4s	5s	-20%
sk_s1hat_get_poly	✅	4s	4s	+0%
sys_check_capability	✅	4s	1s	+300%
unpack_sk	✅	4s	3s	+33%
unpack_sk_s1hat	✅	4s	5s	-20%
unpack_sk_t0hat	✅	4s	5s	-20%
use_hint	✅	4s	3s	+33%
yvec_get_poly	✅	4s	2s	+100%
yvec_init	✅	4s	3s	+33%
decompose	✅	3s	5s	-40%
keccak_f1600_x1_native_aarch64_v84a	✅	3s	2s	+50%
keccak_squeeze	✅	3s	1s	+200%
keccakf1600_extract_bytes (big endian)	✅	3s	3s	+0%
keccakf1600x4_xor_bytes	✅	3s	3s	+0%
mld_h	✅	3s	5s	-40%
ntt_native_aarch64	✅	3s	4s	-25%
pack_sk_rho_key_tr_s2	✅	3s	2s	+50%
pointwise_native_aarch64	✅	3s	3s	+0%
poly_caddq_native_aarch64	✅	3s	3s	+0%
poly_chknorm_native	✅	3s	4s	-25%
poly_decompose	✅	3s	3s	+0%
poly_decompose_32_native_aarch64	✅	3s	3s	+0%
poly_decompose_native	✅	3s	3s	+0%
poly_invntt_tomont_native	✅	3s	4s	-25%
poly_ntt_c	✅	3s	4s	-25%
poly_permute_bitrev_to_custom_optional_native	✅	3s	3s	+0%
poly_uniform_gamma1	✅	3s	3s	+0%
poly_use_hint_native	✅	3s	5s	-40%
polyveck_pack_w1	✅	3s	2s	+50%
polyvecl_pack_eta	✅	3s	2s	+50%
polyvecl_pointwise_acc_montgomery	✅	3s	4s	-25%
polyvecl_unpack_z	✅	3s	1s	+200%
rej_eta	✅	3s	2s	+50%
rej_eta_c	✅	3s	6s	-50%
shake128_absorb	✅	3s	4s	-25%
shake128_init	✅	3s	4s	-25%
shake128x4_absorb_once	✅	3s	4s	-25%
shake256_absorb	✅	3s	3s	+0%
shake256_init	✅	3s	2s	+50%
shake256_squeeze	✅	3s	2s	+50%
sig_unpack_hints	✅	3s	3s	+0%
sign_keypair_internal	✅	3s	6s	-50%
sign_signature_pre_hash_shake256	✅	3s	2s	+50%
sign_verify_extmu	✅	3s	6s	-50%
sign_verify_pre_hash_internal	✅	3s	5s	-40%
sign_verify_pre_hash_shake256	✅	3s	2s	+50%
sk_s2hat_get_poly	✅	3s	2s	+50%
unpack_sk_s2hat	✅	3s	4s	-25%
keccak_f1600_x1_native_aarch64	✅	2s	2s	+0%
keccak_f1600_x4_native_aarch64_v84a	✅	2s	3s	-33%
keccak_f1600_x4_native_avx2	✅	2s	2s	+0%
keccak_finalize	✅	2s	2s	+0%
keccakf1600_permute_native	✅	2s	3s	-33%
keccakf1600_xor_bytes	✅	2s	2s	+0%
keccakf1600_xor_bytes (big endian)	✅	2s	1s	+100%
keccakf1600x4_extract_bytes	✅	2s	3s	-33%
keccakf1600x4_extract_bytes_native	✅	2s	4s	-50%
keccakf1600x4_xor_bytes_native	✅	2s	5s	-60%
make_hint	✅	2s	4s	-50%
mld_ct_cmask_neg_i32	✅	2s	1s	+100%
mld_ct_cmask_nonzero_u32	✅	2s	4s	-50%
mld_ct_cmask_nonzero_u8	✅	2s	3s	-33%
mld_ct_get_optblocker_i64	✅	2s	5s	-60%
mld_ct_get_optblocker_u32	✅	2s	4s	-50%
mld_keccakf1600x4_xor_bytes_c	✅	2s	3s	-33%
mld_value_barrier_u32	✅	2s	4s	-50%
mld_value_barrier_u8	✅	2s	3s	-33%
montgomery_reduce	✅	2s	3s	-33%
nttunpack_native_x86_64	✅	2s	3s	-33%
pack_sig_c	✅	2s	3s	-33%
pack_sig_z	✅	2s	2s	+0%
pack_sk_s1	✅	2s	3s	-33%
poly_chknorm	✅	2s	3s	-33%
poly_invntt_tomont	✅	2s	3s	-33%
poly_ntt_native	✅	2s	3s	-33%
poly_pointwise_montgomery	✅	2s	2s	+0%
poly_reduce	✅	2s	4s	-50%
poly_use_hint	✅	2s	3s	-33%
polyveck_reduce	✅	2s	2s	+0%
polyvecl_uniform_gamma1_serial	✅	2s	4s	-50%
polyw1_pack	✅	2s	2s	+0%
polyz_pack	✅	2s	3s	-33%
polyz_unpack	✅	2s	2s	+0%
polyz_unpack_17_native_aarch64	✅	2s	4s	-50%
polyz_unpack_native	✅	2s	3s	-33%
reduce32	✅	2s	3s	-33%
rej_uniform_native_aarch64	✅	2s	-	new
shake128x4_squeezeblocks	✅	2s	3s	-33%
shake256_finalize	✅	2s	3s	-33%
sk_t0hat_get_poly	✅	2s	4s	-50%
keccakf1600_permute	✅	1s	3s	-67%
mld_ct_abs_i32	✅	1s	4s	-75%
mld_ct_sel_int32	✅	1s	4s	-75%
mld_value_barrier_i64	✅	1s	2s	-50%
polyvecl_unpack_eta	✅	1s	3s	-67%
shake128_finalize	✅	1s	2s	-50%
shake128_release	✅	1s	2s	-50%
unpack_pk_t1	✅	1s	3s	-67%

[oqs-bot]

CBMC Results (ML-DSA-44)

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	1818s	1672s	+8.7%
polyvecl_pointwise_acc_montgomery_c	✅	300s	255s	+18%
rej_uniform_native	✅	130s	117s	+11%
poly_pointwise_montgomery_c	✅	115s	97s	+19%
mld_invntt_layer	✅	103s	93s	+11%
mld_ct_memcmp	✅	81s	69s	+17%
mld_attempt_signature_generation	✅	59s	54s	+9%
mld_ntt_layer	✅	46s	44s	+5%
polyvec_matrix_expand	✅	32s	30s	+7%
sign_signature_internal	✅	32s	28s	+14%
fqmul	✅	31s	28s	+11%
sign_verify_internal	✅	27s	28s	-4%
keccakf1600x4_permute_native	✅	22s	22s	+0%
polyvecl_chknorm	✅	21s	16s	+31%
mld_ntt_butterfly_block	✅	20s	15s	+33%
rej_uniform_c	✅	19s	16s	+19%
rej_uniform	✅	18s	16s	+12%
mld_check_pct	✅	17s	15s	+13%
poly_chknorm_c	✅	17s	17s	+0%
polyvec_matrix_pointwise_montgomery_yvec	✅	16s	15s	+7%
polyt0_unpack	✅	15s	16s	-6%
poly_uniform_eta_4x	✅	14s	14s	+0%
polyz_unpack_c	✅	14s	12s	+17%
compute_pack_t0_t1	✅	13s	15s	-13%
keccak_absorb_once_x4	✅	13s	8s	+62%
polyeta_unpack	✅	13s	14s	-7%
poly_uniform_4x	✅	12s	13s	-8%
polyvec_matrix_expand_serial	✅	12s	11s	+9%
poly_add	✅	11s	10s	+10%
poly_invntt_tomont_c	✅	10s	8s	+25%
poly_power2round	✅	10s	10s	+0%
mld_compute_pack_z	✅	9s	9s	+0%
sign	✅	8s	6s	+33%
keccak_absorb	✅	7s	7s	+0%
poly_decompose_c	✅	7s	9s	-22%
sign_keypair_internal	✅	7s	6s	+17%
sign_pk_from_sk	✅	7s	6s	+17%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	6s	3s	+100%
mld_keccakf1600_permute_c	✅	6s	7s	-14%
poly_caddq_c	✅	6s	3s	+100%
polyveck_chknorm	✅	6s	6s	+0%
polyveck_decompose	✅	6s	8s	-25%
sign_open	✅	6s	3s	+100%
sign_signature_pre_hash_internal	✅	6s	5s	+20%
sk_s2hat_get_poly	✅	6s	2s	+200%
intt_native_x86_64	✅	5s	3s	+67%
keccakf1600_permute_native	✅	5s	4s	+25%
mld_h	✅	5s	7s	-29%
mld_keccakf1600_extract_bytes	✅	5s	3s	+67%
mld_keccakf1600x4_extract_bytes_c	✅	5s	3s	+67%
ntt_native_aarch64	✅	5s	4s	+25%
pack_sk_s1	✅	5s	2s	+150%
pointwise_acc_native_aarch64	✅	5s	6s	-17%
pointwise_acc_native_x86_64	✅	5s	6s	-17%
poly_challenge	✅	5s	6s	-17%
poly_invntt_tomont_native	✅	5s	4s	+25%
poly_permute_bitrev_to_custom_optional	✅	5s	2s	+150%
poly_sub	✅	5s	2s	+150%
polyvec_matrix_pointwise_montgomery_row	✅	5s	3s	+67%
polyveck_pack_w1	✅	5s	3s	+67%
polyvecl_unpack_z	✅	5s	2s	+150%
polyz_unpack	✅	5s	2s	+150%
rej_eta_c	✅	5s	4s	+25%
sig_unpack_hints	✅	5s	2s	+150%
sign_signature	✅	5s	5s	+0%
sign_verify_pre_hash_shake256	✅	5s	6s	-17%
unpack_sk_t0hat	✅	5s	5s	+0%
fqscale	✅	4s	4s	+0%
keccak_f1600_x4_native_avx2	✅	4s	2s	+100%
keccak_squeezeblocks_x4	✅	4s	4s	+0%
keccakf1600_xor_bytes	✅	4s	3s	+33%
keccakf1600_xor_bytes (big endian)	✅	4s	3s	+33%
keccakf1600x4_xor_bytes	✅	4s	4s	+0%
mld_ct_cmask_nonzero_u32	✅	4s	2s	+100%
mld_ct_get_optblocker_u32	✅	4s	2s	+100%
mld_sample_s1_s2_serial	✅	4s	3s	+33%
pack_sig_c	✅	4s	4s	+0%
pack_sk_rho_key_tr_s2	✅	4s	3s	+33%
poly_caddq_native_aarch64	✅	4s	2s	+100%
poly_chknorm_native	✅	4s	4s	+0%
poly_chknorm_native_aarch64	✅	4s	2s	+100%
poly_decompose_88_native_aarch64	✅	4s	4s	+0%
poly_decompose_native	✅	4s	3s	+33%
poly_ntt	✅	4s	3s	+33%
poly_pointwise_montgomery	✅	4s	5s	-20%
poly_shiftl	✅	4s	5s	-20%
poly_uniform	✅	4s	4s	+0%
poly_use_hint_native	✅	4s	4s	+0%
polyveck_invntt_tomont	✅	4s	7s	-43%
polyveck_pack_eta	✅	4s	2s	+100%
polyveck_unpack_eta	✅	4s	3s	+33%
polyvecl_ntt	✅	4s	4s	+0%
polyvecl_pointwise_acc_montgomery_native	✅	4s	2s	+100%
polyvecl_uniform_gamma1_serial	✅	4s	2s	+100%
polyz_unpack_17_native_aarch64	✅	4s	6s	-33%
power2round	✅	4s	5s	-20%
rej_eta_native	✅	4s	4s	+0%
shake256_squeeze	✅	4s	1s	+300%
sign_signature_pre_hash_shake256	✅	4s	3s	+33%
unpack_sk	✅	4s	4s	+0%
yvec_get_poly	✅	4s	4s	+0%
decompose	✅	3s	4s	-25%
intt_native_aarch64	✅	3s	3s	+0%
keccak_f1600_x1_native_aarch64	✅	3s	3s	+0%
keccak_f1600_x4_native_aarch64_v84a	✅	3s	4s	-25%
keccak_squeeze	✅	3s	3s	+0%
keccakf1600x4_permute	✅	3s	3s	+0%
keccakf1600x4_xor_bytes_native	✅	3s	2s	+50%
make_hint	✅	3s	2s	+50%
mld_ct_cmask_nonzero_u8	✅	3s	1s	+200%
mld_ct_get_optblocker_i64	✅	3s	2s	+50%
mld_polymat_expand_entry	✅	3s	3s	+0%
mld_prepare_domain_separation_prefix	✅	3s	5s	-40%
mld_sample_s1_s2	✅	3s	3s	+0%
nttunpack_native_x86_64	✅	3s	5s	-40%
pack_sig_h	✅	3s	2s	+50%
pack_sig_z	✅	3s	2s	+50%
pointwise_native_aarch64	✅	3s	2s	+50%
pointwise_native_x86_64	✅	3s	2s	+50%
poly_decompose	✅	3s	3s	+0%
poly_invntt_tomont	✅	3s	2s	+50%
poly_ntt_native	✅	3s	3s	+0%
poly_permute_bitrev_to_custom_optional_native	✅	3s	3s	+0%
poly_pointwise_montgomery_native	✅	3s	3s	+0%
poly_reduce	✅	3s	3s	+0%
poly_uniform_eta	✅	3s	5s	-40%
poly_uniform_gamma1	✅	3s	5s	-40%
poly_uniform_gamma1_4x	✅	3s	3s	+0%
poly_use_hint_c	✅	3s	3s	+0%
poly_use_hint_native_aarch64	✅	3s	2s	+50%
polyt0_pack	✅	3s	5s	-40%
polyt1_unpack	✅	3s	3s	+0%
polyveck_caddq	✅	3s	6s	-50%
polyvecl_pack_eta	✅	3s	3s	+0%
polyw1_pack	✅	3s	1s	+200%
polyz_pack	✅	3s	2s	+50%
polyz_unpack_19_native_aarch64	✅	3s	1s	+200%
polyz_unpack_native	✅	3s	3s	+0%
rej_eta	✅	3s	2s	+50%
shake128_release	✅	3s	3s	+0%
shake256	✅	3s	2s	+50%
shake256_absorb	✅	3s	1s	+200%
shake256_init	✅	3s	1s	+200%
sign_verify	✅	3s	6s	-50%
sign_verify_extmu	✅	3s	4s	-25%
unpack_pk_t1	✅	3s	3s	+0%
caddq	✅	2s	3s	-33%
keccak_f1600_x1_native_aarch64_v84a	✅	2s	3s	-33%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	2s	3s	-33%
keccak_finalize	✅	2s	1s	+100%
keccak_init	✅	2s	2s	+0%
keccakf1600_extract_bytes (big endian)	✅	2s	2s	+0%
keccakf1600_permute	✅	2s	3s	-33%
keccakf1600x4_extract_bytes	✅	2s	3s	-33%
mld_ct_abs_i32	✅	2s	4s	-50%
mld_ct_cmask_neg_i32	✅	2s	1s	+100%
mld_ct_get_optblocker_u8	✅	2s	3s	-33%
mld_ct_sel_int32	✅	2s	3s	-33%
mld_keccakf1600x4_xor_bytes_c	✅	2s	4s	-50%
mld_value_barrier_i64	✅	2s	2s	+0%
mld_value_barrier_u32	✅	2s	2s	+0%
montgomery_reduce	✅	2s	3s	-33%
ntt_native_x86_64	✅	2s	2s	+0%
poly_caddq	✅	2s	3s	-33%
poly_chknorm	✅	2s	3s	-33%
poly_decompose_32_native_aarch64	✅	2s	3s	-33%
poly_ntt_c	✅	2s	4s	-50%
poly_use_hint	✅	2s	4s	-50%
polyeta_pack	✅	2s	4s	-50%
polyt1_pack	✅	2s	3s	-33%
polyveck_ntt	✅	2s	4s	-50%
polyveck_reduce	✅	2s	1s	+100%
polyvecl_pointwise_acc_montgomery	✅	2s	2s	+0%
polyvecl_uniform_gamma1	✅	2s	3s	-33%
reduce32	✅	2s	2s	+0%
rej_uniform_native_aarch64	✅	2s	-	new
shake128_absorb	✅	2s	2s	+0%
shake128_finalize	✅	2s	2s	+0%
shake128_init	✅	2s	3s	-33%
shake128x4_absorb_once	✅	2s	3s	-33%
shake256_finalize	✅	2s	3s	-33%
shake256_release	✅	2s	1s	+100%
shake256x4_absorb_once	✅	2s	5s	-60%
shake256x4_squeezeblocks	✅	2s	3s	-33%
sign_keypair	✅	2s	6s	-67%
sign_signature_extmu	✅	2s	3s	-33%
sign_verify_pre_hash_internal	✅	2s	4s	-50%
sk_s1hat_get_poly	✅	2s	3s	-33%
sk_t0hat_get_poly	✅	2s	5s	-60%
sys_check_capability	✅	2s	4s	-50%
unpack_sk_s1hat	✅	2s	4s	-50%
use_hint	✅	2s	4s	-50%
yvec_init	✅	2s	2s	+0%
keccakf1600x4_extract_bytes_native	✅	1s	2s	-50%
mld_value_barrier_u8	✅	1s	1s	+0%
poly_caddq_native	✅	1s	2s	-50%
polyvecl_unpack_eta	✅	1s	3s	-67%
shake128_squeeze	✅	1s	2s	-50%
shake128x4_squeezeblocks	✅	1s	3s	-67%
unpack_sk_s2hat	✅	1s	3s	-67%

[oqs-bot]

CBMC Results (ML-DSA-65)

Full Results (199 proofs)

Proof	Status	Current	Previous	Change
**TOTAL**	✅	2060s	1914s	+7.6%
polyvecl_pointwise_acc_montgomery_c	✅	333s	284s	+17%
polyvec_matrix_expand	✅	154s	149s	+3%
rej_uniform_native	✅	132s	124s	+6%
poly_pointwise_montgomery_c	✅	110s	94s	+17%
mld_invntt_layer	✅	99s	92s	+8%
mld_ct_memcmp	✅	79s	69s	+14%
sign_verify_internal	✅	72s	71s	+1%
mld_attempt_signature_generation	✅	70s	67s	+4%
sign_signature_internal	✅	46s	45s	+2%
mld_ntt_layer	✅	44s	45s	-2%
fqmul	✅	30s	31s	-3%
polyvec_matrix_pointwise_montgomery_yvec	✅	29s	29s	+0%
keccakf1600x4_permute_native	✅	24s	23s	+4%
polyvec_matrix_expand_serial	✅	24s	24s	+0%
rej_uniform_c	✅	21s	17s	+24%
mld_ntt_butterfly_block	✅	18s	16s	+12%
poly_chknorm_c	✅	17s	15s	+13%
rej_uniform	✅	17s	16s	+6%
polyt0_unpack	✅	16s	17s	-6%
polyveck_decompose	✅	14s	16s	-12%
poly_power2round	✅	13s	10s	+30%
poly_uniform_eta_4x	✅	13s	13s	+0%
compute_pack_t0_t1	✅	12s	15s	-20%
keccak_absorb_once_x4	✅	12s	9s	+33%
mld_check_pct	✅	12s	13s	-8%
poly_uniform_4x	✅	12s	12s	+0%
poly_add	✅	11s	11s	+0%
polyveck_caddq	✅	10s	8s	+25%
polyveck_chknorm	✅	10s	10s	+0%
polyvecl_ntt	✅	9s	6s	+50%
poly_invntt_tomont_c	✅	8s	7s	+14%
polyveck_invntt_tomont	✅	8s	6s	+33%
sign	✅	8s	8s	+0%
intt_native_aarch64	✅	7s	2s	+250%
mld_keccakf1600_permute_c	✅	7s	8s	-12%
mld_sample_s1_s2	✅	7s	4s	+75%
poly_decompose_c	✅	7s	8s	-12%
poly_shiftl	✅	7s	5s	+40%
polyveck_ntt	✅	7s	10s	-30%
keccak_absorb	✅	6s	7s	-14%
mld_compute_pack_z	✅	6s	10s	-40%
poly_use_hint	✅	6s	6s	+0%
polyvecl_unpack_z	✅	6s	4s	+50%
rej_eta	✅	6s	3s	+100%
rej_eta_native	✅	6s	4s	+50%
sign_keypair_internal	✅	6s	6s	+0%
sign_open	✅	6s	4s	+50%
sign_pk_from_sk	✅	6s	6s	+0%
unpack_sk_t0hat	✅	6s	5s	+20%
keccak_squeezeblocks_x4	✅	5s	6s	-17%
keccakf1600x4_xor_bytes_native	✅	5s	1s	+400%
mld_prepare_domain_separation_prefix	✅	5s	4s	+25%
mld_sample_s1_s2_serial	✅	5s	3s	+67%
pointwise_acc_native_aarch64	✅	5s	8s	-38%
pointwise_acc_native_x86_64	✅	5s	5s	+0%
poly_caddq_native	✅	5s	2s	+150%
poly_ntt_native	✅	5s	3s	+67%
poly_use_hint_native_aarch64	✅	5s	3s	+67%
polyvecl_chknorm	✅	5s	6s	-17%
polyvecl_pack_eta	✅	5s	4s	+25%
polyvecl_pointwise_acc_montgomery_native	✅	5s	5s	+0%
rej_eta_c	✅	5s	5s	+0%
sign_keypair	✅	5s	4s	+25%
sign_signature_extmu	✅	5s	3s	+67%
sign_signature_pre_hash_internal	✅	5s	3s	+67%
sign_signature_pre_hash_shake256	✅	5s	3s	+67%
sign_verify	✅	5s	3s	+67%
sys_check_capability	✅	5s	1s	+400%
unpack_sk	✅	5s	4s	+25%
caddq	✅	4s	3s	+33%
decompose	✅	4s	5s	-20%
keccak_finalize	✅	4s	4s	+0%
mld_keccakf1600x4_extract_bytes_c	✅	4s	2s	+100%
ntt_native_aarch64	✅	4s	2s	+100%
pack_sig_h	✅	4s	2s	+100%
pack_sk_rho_key_tr_s2	✅	4s	2s	+100%
poly_caddq_c	✅	4s	4s	+0%
poly_challenge	✅	4s	7s	-43%
poly_decompose_32_native_aarch64	✅	4s	5s	-20%
poly_decompose_native	✅	4s	4s	+0%
poly_invntt_tomont	✅	4s	5s	-20%
poly_invntt_tomont_native	✅	4s	3s	+33%
poly_pointwise_montgomery	✅	4s	2s	+100%
poly_uniform	✅	4s	3s	+33%
poly_uniform_eta	✅	4s	4s	+0%
poly_uniform_gamma1	✅	4s	4s	+0%
poly_use_hint_native	✅	4s	3s	+33%
polyeta_pack	✅	4s	4s	+0%
polyeta_unpack	✅	4s	3s	+33%
polyt1_unpack	✅	4s	5s	-20%
polyveck_pack_w1	✅	4s	2s	+100%
polyvecl_pointwise_acc_montgomery	✅	4s	1s	+300%
polyvecl_uniform_gamma1	✅	4s	4s	+0%
polyz_pack	✅	4s	2s	+100%
polyz_unpack_c	✅	4s	5s	-20%
polyz_unpack_native	✅	4s	2s	+100%
reduce32	✅	4s	2s	+100%
shake256	✅	4s	3s	+33%
shake256x4_absorb_once	✅	4s	3s	+33%
sign_verify_pre_hash_internal	✅	4s	3s	+33%
sk_s1hat_get_poly	✅	4s	2s	+100%
unpack_sk_s2hat	✅	4s	2s	+100%
use_hint	✅	4s	2s	+100%
intt_native_x86_64	✅	3s	2s	+50%
keccak_f1600_x1_native_aarch64	✅	3s	2s	+50%
keccak_f1600_x4_native_aarch64_v84a	✅	3s	2s	+50%
keccak_f1600_x4_native_aarch64_v8a_v84a_scalar_hybrid	✅	3s	2s	+50%
keccak_f1600_x4_native_avx2	✅	3s	5s	-40%
keccakf1600_permute_native	✅	3s	4s	-25%
keccakf1600_xor_bytes (big endian)	✅	3s	4s	-25%
keccakf1600x4_extract_bytes	✅	3s	1s	+200%
keccakf1600x4_extract_bytes_native	✅	3s	1s	+200%
keccakf1600x4_xor_bytes	✅	3s	3s	+0%
make_hint	✅	3s	3s	+0%
mld_ct_cmask_nonzero_u32	✅	3s	4s	-25%
mld_ct_cmask_nonzero_u8	✅	3s	4s	-25%
mld_ct_get_optblocker_u8	✅	3s	2s	+50%
mld_h	✅	3s	7s	-57%
mld_keccakf1600_extract_bytes	✅	3s	3s	+0%
mld_keccakf1600x4_xor_bytes_c	✅	3s	3s	+0%
mld_value_barrier_i64	✅	3s	3s	+0%
montgomery_reduce	✅	3s	4s	-25%
ntt_native_x86_64	✅	3s	5s	-40%
pack_sig_z	✅	3s	3s	+0%
pointwise_native_aarch64	✅	3s	3s	+0%
pointwise_native_x86_64	✅	3s	2s	+50%
poly_caddq	✅	3s	3s	+0%
poly_caddq_native_aarch64	✅	3s	2s	+50%
poly_chknorm_native	✅	3s	3s	+0%
poly_chknorm_native_aarch64	✅	3s	3s	+0%
poly_decompose	✅	3s	5s	-40%
poly_ntt	✅	3s	3s	+0%
poly_ntt_c	✅	3s	2s	+50%
poly_permute_bitrev_to_custom_optional_native	✅	3s	3s	+0%
poly_pointwise_montgomery_native	✅	3s	3s	+0%
poly_uniform_gamma1_4x	✅	3s	4s	-25%
poly_use_hint_c	✅	3s	3s	+0%
polyt0_pack	✅	3s	6s	-50%
polyveck_unpack_eta	✅	3s	4s	-25%
polyz_unpack	✅	3s	3s	+0%
power2round	✅	3s	1s	+200%
rej_uniform_native_aarch64	✅	3s	-	new
shake128_absorb	✅	3s	2s	+50%
shake128_squeeze	✅	3s	2s	+50%
shake128x4_squeezeblocks	✅	3s	2s	+50%
shake256_release	✅	3s	2s	+50%
shake256_squeeze	✅	3s	3s	+0%
shake256x4_squeezeblocks	✅	3s	2s	+50%
sig_unpack_hints	✅	3s	3s	+0%
sign_signature	✅	3s	5s	-40%
sign_verify_extmu	✅	3s	3s	+0%
sk_s2hat_get_poly	✅	3s	2s	+50%
unpack_sk_s1hat	✅	3s	2s	+50%
yvec_get_poly	✅	3s	5s	-40%
yvec_init	✅	3s	3s	+0%
fqscale	✅	2s	3s	-33%
keccak_f1600_x4_native_aarch64_v8a_scalar_hybrid	✅	2s	3s	-33%
keccak_squeeze	✅	2s	2s	+0%
keccakf1600_extract_bytes (big endian)	✅	2s	4s	-50%
keccakf1600x4_permute	✅	2s	3s	-33%
mld_ct_abs_i32	✅	2s	1s	+100%
mld_ct_cmask_neg_i32	✅	2s	2s	+0%
mld_ct_get_optblocker_i64	✅	2s	1s	+100%
mld_ct_sel_int32	✅	2s	3s	-33%
mld_value_barrier_u32	✅	2s	3s	-33%
mld_value_barrier_u8	✅	2s	1s	+100%
nttunpack_native_x86_64	✅	2s	2s	+0%
pack_sig_c	✅	2s	3s	-33%
pack_sk_s1	✅	2s	2s	+0%
poly_chknorm	✅	2s	3s	-33%
poly_permute_bitrev_to_custom_optional	✅	2s	3s	-33%
poly_reduce	✅	2s	1s	+100%
poly_sub	✅	2s	1s	+100%
polyt1_pack	✅	2s	2s	+0%
polyvec_matrix_pointwise_montgomery_row	✅	2s	2s	+0%
polyveck_pack_eta	✅	2s	1s	+100%
polyveck_reduce	✅	2s	2s	+0%
polyvecl_uniform_gamma1_serial	✅	2s	4s	-50%
polyvecl_unpack_eta	✅	2s	2s	+0%
polyw1_pack	✅	2s	1s	+100%
polyz_unpack_19_native_aarch64	✅	2s	3s	-33%
shake128_finalize	✅	2s	4s	-50%
shake128_init	✅	2s	3s	-33%
shake128_release	✅	2s	2s	+0%
shake128x4_absorb_once	✅	2s	4s	-50%
shake256_absorb	✅	2s	2s	+0%
shake256_init	✅	2s	3s	-33%
sign_verify_pre_hash_shake256	✅	2s	2s	+0%
sk_t0hat_get_poly	✅	2s	2s	+0%
unpack_pk_t1	✅	2s	2s	+0%
keccak_f1600_x1_native_aarch64_v84a	✅	1s	1s	+0%
keccak_init	✅	1s	4s	-75%
keccakf1600_permute	✅	1s	3s	-67%
keccakf1600_xor_bytes	✅	1s	2s	-50%
mld_ct_get_optblocker_u32	✅	1s	4s	-75%
mld_polymat_expand_entry	✅	1s	4s	-75%
poly_decompose_88_native_aarch64	✅	1s	2s	-50%
polyz_unpack_17_native_aarch64	✅	1s	6s	-83%
shake256_finalize	✅	1s	1s	+0%

[github-actions]

Mac Mini (M1, 2020) benchmarks (opt)

Details

Benchmark suite	Current: 6c13542	Previous: ec0cdd4	Ratio
ML-DSA-44 keypair	46535 cycles	46506 cycles	1.00
ML-DSA-44 sign	131058 cycles	131078 cycles	1.00
ML-DSA-44 verify	47345 cycles	47320 cycles	1.00
ML-DSA-65 keypair	81706 cycles	81693 cycles	1.00
ML-DSA-65 sign	215431 cycles	215418 cycles	1.00
ML-DSA-65 verify	79324 cycles	79309 cycles	1.00
ML-DSA-87 keypair	132411 cycles	132409 cycles	1.00
ML-DSA-87 sign	277428 cycles	277534 cycles	1.00
ML-DSA-87 verify	134236 cycles	134235 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Mac Mini (M1, 2020) benchmarks (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	112746 cycles	112740 cycles	1.00
ML-DSA-44 sign	400901 cycles	400842 cycles	1.00
ML-DSA-44 verify	120128 cycles	120086 cycles	1.00
ML-DSA-65 keypair	192883 cycles	192877 cycles	1.00
ML-DSA-65 sign	649925 cycles	649964 cycles	1.00
ML-DSA-65 verify	192956 cycles	192956 cycles	1
ML-DSA-87 keypair	318782 cycles	318775 cycles	1.00
ML-DSA-87 sign	828588 cycles	828851 cycles	1.00
ML-DSA-87 verify	326650 cycles	326654 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 4th gen (c7i)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	43768 cycles	45391 cycles	0.96
ML-DSA-44 sign	133272 cycles	136216 cycles	0.98
ML-DSA-44 verify	45772 cycles	47321 cycles	0.97
ML-DSA-65 keypair	76387 cycles	78853 cycles	0.97
ML-DSA-65 sign	218619 cycles	223148 cycles	0.98
ML-DSA-65 verify	76486 cycles	77818 cycles	0.98
ML-DSA-87 keypair	124993 cycles	126383 cycles	0.99
ML-DSA-87 sign	277386 cycles	280003 cycles	0.99
ML-DSA-87 verify	122348 cycles	124086 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 4th gen (c7i) (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	94221 cycles	94250 cycles	1.00
ML-DSA-44 sign	329262 cycles	329671 cycles	1.00
ML-DSA-44 verify	98725 cycles	98848 cycles	1.00
ML-DSA-65 keypair	161876 cycles	161842 cycles	1.00
ML-DSA-65 sign	539009 cycles	538466 cycles	1.00
ML-DSA-65 verify	160676 cycles	160405 cycles	1.00
ML-DSA-87 keypair	264143 cycles	264153 cycles	1.00
ML-DSA-87 sign	694078 cycles	694626 cycles	1.00
ML-DSA-87 verify	265819 cycles	265814 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

SpacemiT K1 8 (Banana Pi F3) benchmarks (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	820432 cycles	820764 cycles	1.00
ML-DSA-44 sign	3222145 cycles	3222715 cycles	1.00
ML-DSA-44 verify	917121 cycles	917496 cycles	1.00
ML-DSA-65 keypair	1391448 cycles	1391037 cycles	1.00
ML-DSA-65 sign	5243597 cycles	5232579 cycles	1.00
ML-DSA-65 verify	1466874 cycles	1464573 cycles	1.00
ML-DSA-87 keypair	2298784 cycles	2299791 cycles	1.00
ML-DSA-87 sign	6610495 cycles	6616416 cycles	1.00
ML-DSA-87 verify	2406162 cycles	2407836 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 3rd gen (c6a)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	55563 cycles	58246 cycles	0.95
ML-DSA-44 sign	165532 cycles	168182 cycles	0.98
ML-DSA-44 verify	58065 cycles	58487 cycles	0.99
ML-DSA-65 keypair	96320 cycles	96874 cycles	0.99
ML-DSA-65 sign	267696 cycles	271854 cycles	0.98
ML-DSA-65 verify	96597 cycles	97497 cycles	0.99
ML-DSA-87 keypair	155692 cycles	164997 cycles	0.94
ML-DSA-87 sign	328179 cycles	339783 cycles	0.97
ML-DSA-87 verify	151858 cycles	154373 cycles	0.98

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton2

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	112606 cycles	112584 cycles	1.00
ML-DSA-44 sign	355233 cycles	355058 cycles	1.00
ML-DSA-44 verify	117577 cycles	117447 cycles	1.00
ML-DSA-65 keypair	194491 cycles	194602 cycles	1.00
ML-DSA-65 sign	585379 cycles	585206 cycles	1.00
ML-DSA-65 verify	193298 cycles	193231 cycles	1.00
ML-DSA-87 keypair	321166 cycles	321492 cycles	1.00
ML-DSA-87 sign	749549 cycles	750302 cycles	1.00
ML-DSA-87 verify	318315 cycles	318520 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 3rd gen (c6a) (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	133850 cycles	133824 cycles	1.00
ML-DSA-44 sign	522666 cycles	523429 cycles	1.00
ML-DSA-44 verify	146999 cycles	147203 cycles	1.00
ML-DSA-65 keypair	223918 cycles	224049 cycles	1.00
ML-DSA-65 sign	853033 cycles	850408 cycles	1.00
ML-DSA-65 verify	233445 cycles	233150 cycles	1.00
ML-DSA-87 keypair	371837 cycles	373095 cycles	1.00
ML-DSA-87 sign	1073791 cycles	1075287 cycles	1.00
ML-DSA-87 verify	384334 cycles	385379 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 4th gen (c7a)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	46880 cycles	47240 cycles	0.99
ML-DSA-44 sign	144149 cycles	146136 cycles	0.99
ML-DSA-44 verify	49896 cycles	50648 cycles	0.99
ML-DSA-65 keypair	82602 cycles	83469 cycles	0.99
ML-DSA-65 sign	229918 cycles	230072 cycles	1.00
ML-DSA-65 verify	83172 cycles	83481 cycles	1.00
ML-DSA-87 keypair	130909 cycles	132078 cycles	0.99
ML-DSA-87 sign	280817 cycles	283164 cycles	0.99
ML-DSA-87 verify	128828 cycles	130195 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton4

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	67437 cycles	67230 cycles	1.00
ML-DSA-44 sign	201387 cycles	201509 cycles	1.00
ML-DSA-44 verify	70315 cycles	70229 cycles	1.00
ML-DSA-65 keypair	119444 cycles	119440 cycles	1.00
ML-DSA-65 sign	328182 cycles	328213 cycles	1.00
ML-DSA-65 verify	116781 cycles	116941 cycles	1.00
ML-DSA-87 keypair	196729 cycles	196651 cycles	1.00
ML-DSA-87 sign	425010 cycles	424774 cycles	1.00
ML-DSA-87 verify	193266 cycles	193028 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 3rd gen (c6i)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	61922 cycles	62711 cycles	0.99
ML-DSA-44 sign	191461 cycles	193467 cycles	0.99
ML-DSA-44 verify	66255 cycles	67225 cycles	0.99
ML-DSA-65 keypair	108162 cycles	112590 cycles	0.96
ML-DSA-65 sign	314656 cycles	319856 cycles	0.98
ML-DSA-65 verify	109273 cycles	112272 cycles	0.97
ML-DSA-87 keypair	172432 cycles	172667 cycles	1.00
ML-DSA-87 sign	383790 cycles	385139 cycles	1.00
ML-DSA-87 verify	172188 cycles	172209 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 4th gen (c7a) (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	118781 cycles	119396 cycles	0.99
ML-DSA-44 sign	448947 cycles	446583 cycles	1.01
ML-DSA-44 verify	128855 cycles	128844 cycles	1.00
ML-DSA-65 keypair	201858 cycles	202970 cycles	0.99
ML-DSA-65 sign	719584 cycles	719324 cycles	1.00
ML-DSA-65 verify	208524 cycles	207674 cycles	1.00
ML-DSA-87 keypair	333642 cycles	335008 cycles	1.00
ML-DSA-87 sign	914941 cycles	918169 cycles	1.00
ML-DSA-87 verify	341970 cycles	342415 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Intel Xeon 3rd gen (c6i)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-87 verify	178158 cycles	172209 cycles	1.03

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton2 (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	213751 cycles	212528 cycles	1.01
ML-DSA-44 sign	758285 cycles	758331 cycles	1.00
ML-DSA-44 verify	230133 cycles	229988 cycles	1.00
ML-DSA-65 keypair	378479 cycles	378899 cycles	1.00
ML-DSA-65 sign	1241045 cycles	1241831 cycles	1.00
ML-DSA-65 verify	372957 cycles	372984 cycles	1.00
ML-DSA-87 keypair	604331 cycles	603666 cycles	1.00
ML-DSA-87 sign	1582990 cycles	1581558 cycles	1.00
ML-DSA-87 verify	618690 cycles	618334 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton4 (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	128404 cycles	128472 cycles	1.00
ML-DSA-44 sign	445324 cycles	444913 cycles	1.00
ML-DSA-44 verify	136666 cycles	136570 cycles	1.00
ML-DSA-65 keypair	220459 cycles	220085 cycles	1.00
ML-DSA-65 sign	718170 cycles	718725 cycles	1.00
ML-DSA-65 verify	220838 cycles	221154 cycles	1.00
ML-DSA-87 keypair	365445 cycles	365468 cycles	1.00
ML-DSA-87 sign	918949 cycles	917811 cycles	1.00
ML-DSA-87 verify	371017 cycles	371454 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 3rd gen (c6i) (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	150916 cycles	153976 cycles	0.98
ML-DSA-44 sign	545488 cycles	559057 cycles	0.98
ML-DSA-44 verify	163644 cycles	166793 cycles	0.98
ML-DSA-65 keypair	255567 cycles	256142 cycles	1.00
ML-DSA-65 sign	887481 cycles	889069 cycles	1.00
ML-DSA-65 verify	262294 cycles	263111 cycles	1.00
ML-DSA-87 keypair	425948 cycles	426566 cycles	1.00
ML-DSA-87 sign	1144091 cycles	1150462 cycles	0.99
ML-DSA-87 verify	440785 cycles	439448 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A76 (Raspberry Pi 5) benchmarks (opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	112466 cycles	112471 cycles	1.00
ML-DSA-44 sign	354625 cycles	354319 cycles	1.00
ML-DSA-44 verify	117059 cycles	117101 cycles	1.00
ML-DSA-65 keypair	194532 cycles	194670 cycles	1.00
ML-DSA-65 sign	584264 cycles	584352 cycles	1.00
ML-DSA-65 verify	193237 cycles	193010 cycles	1.00
ML-DSA-87 keypair	320621 cycles	321273 cycles	1.00
ML-DSA-87 sign	748906 cycles	749948 cycles	1.00
ML-DSA-87 verify	317880 cycles	318693 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton3

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	71572 cycles	71489 cycles	1.00
ML-DSA-44 sign	211568 cycles	211342 cycles	1.00
ML-DSA-44 verify	74829 cycles	74924 cycles	1.00
ML-DSA-65 keypair	125984 cycles	125905 cycles	1.00
ML-DSA-65 sign	347604 cycles	347998 cycles	1.00
ML-DSA-65 verify	123873 cycles	124044 cycles	1.00
ML-DSA-87 keypair	206240 cycles	206671 cycles	1.00
ML-DSA-87 sign	443131 cycles	447427 cycles	0.99
ML-DSA-87 verify	204465 cycles	204120 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton3 (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	137889 cycles	137948 cycles	1.00
ML-DSA-44 sign	482110 cycles	481676 cycles	1.00
ML-DSA-44 verify	148803 cycles	148659 cycles	1.00
ML-DSA-65 keypair	241031 cycles	240730 cycles	1.00
ML-DSA-65 sign	785016 cycles	784965 cycles	1.00
ML-DSA-65 verify	240613 cycles	241049 cycles	1.00
ML-DSA-87 keypair	395048 cycles	395084 cycles	1.00
ML-DSA-87 sign	1005956 cycles	1004845 cycles	1.00
ML-DSA-87 verify	402645 cycles	403184 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A76 (Raspberry Pi 5) benchmarks (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	212371 cycles	212425 cycles	1.00
ML-DSA-44 sign	756804 cycles	756359 cycles	1.00
ML-DSA-44 verify	229234 cycles	229083 cycles	1.00
ML-DSA-65 keypair	378769 cycles	378500 cycles	1.00
ML-DSA-65 sign	1240394 cycles	1240209 cycles	1.00
ML-DSA-65 verify	371908 cycles	371886 cycles	1.00
ML-DSA-87 keypair	602950 cycles	602448 cycles	1.00
ML-DSA-87 sign	1580764 cycles	1580047 cycles	1.00
ML-DSA-87 verify	619634 cycles	618603 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A55 (Snapdragon 888) benchmarks (opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	271362 cycles	266927 cycles	1.02
ML-DSA-44 sign	803267 cycles	797012 cycles	1.01
ML-DSA-44 verify	272085 cycles	268934 cycles	1.01
ML-DSA-65 keypair	465548 cycles	462006 cycles	1.01
ML-DSA-65 sign	1346356 cycles	1325140 cycles	1.02
ML-DSA-65 verify	452908 cycles	447051 cycles	1.01
ML-DSA-87 keypair	796067 cycles	789145 cycles	1.01
ML-DSA-87 sign	1814243 cycles	1808930 cycles	1.00
ML-DSA-87 verify	774654 cycles	768055 cycles	1.01

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A55 (Snapdragon 888) benchmarks (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	458869 cycles	456127 cycles	1.01
ML-DSA-44 sign	2126957 cycles	2116401 cycles	1.00
ML-DSA-44 verify	552019 cycles	548507 cycles	1.01
ML-DSA-65 keypair	770502 cycles	766953 cycles	1.00
ML-DSA-65 sign	3470118 cycles	3454812 cycles	1.00
ML-DSA-65 verify	855533 cycles	851822 cycles	1.00
ML-DSA-87 keypair	1257950 cycles	1239858 cycles	1.01
ML-DSA-87 sign	4350714 cycles	4301107 cycles	1.01
ML-DSA-87 verify	1376864 cycles	1364841 cycles	1.01

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A72 (Raspberry Pi 4) benchmarks (opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	220320 cycles	225607 cycles	0.98
ML-DSA-44 sign	629787 cycles	613159 cycles	1.03
ML-DSA-44 verify	218806 cycles	221594 cycles	0.99
ML-DSA-65 keypair	381297 cycles	390520 cycles	0.98
ML-DSA-65 sign	981110 cycles	1011825 cycles	0.97
ML-DSA-65 verify	362378 cycles	366404 cycles	0.99
ML-DSA-87 keypair	643194 cycles	647780 cycles	0.99
ML-DSA-87 sign	1333643 cycles	1330441 cycles	1.00
ML-DSA-87 verify	622584 cycles	623332 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Arm Cortex-A72 (Raspberry Pi 4) benchmarks (opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-87 keypair	672194 cycles	647780 cycles	1.04
ML-DSA-87 sign	1388591 cycles	1330441 cycles	1.04

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A72 (Raspberry Pi 4) benchmarks (no-opt)

Details

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 keypair	311539 cycles	313248 cycles	0.99
ML-DSA-44 sign	1218975 cycles	1165859 cycles	1.05
ML-DSA-44 verify	357865 cycles	340574 cycles	1.05
ML-DSA-65 keypair	577066 cycles	577106 cycles	1.00
ML-DSA-65 sign	1946955 cycles	1997418 cycles	0.97
ML-DSA-65 verify	545442 cycles	555863 cycles	0.98
ML-DSA-87 keypair	865804 cycles	881765 cycles	0.98
ML-DSA-87 sign	2425492 cycles	2508825 cycles	0.97
ML-DSA-87 verify	893414 cycles	921818 cycles	0.97

This comment was automatically generated by workflow using github-action-benchmark.

[mkannwischer]

Thanks @hanno-becker. LGTM.

[github-actions]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Arm Cortex-A72 (Raspberry Pi 4) benchmarks (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 6c13542	Previous: cbc80f6	Ratio
ML-DSA-44 sign	1218975 cycles	1165859 cycles	1.05
ML-DSA-44 verify	357865 cycles	340574 cycles	1.05

This comment was automatically generated by workflow using github-action-benchmark.