Eliminate use_hint 32/88 intrinsics by willieyz · Pull Request #940 · pq-code-package/mldsa-native

willieyz · 2026-02-03T07:41:03Z

Resolves: AVX2: Replace intrinsics implementation of poly_use_hint with assembly #484
In this PR, we replace the AVX2 intrinsics implementation of poly_use_hint_32 and poly_use_hint_88 with a x86_64 assembly version, this is part of the effort to enable HOL-Light proofs.

We also tried unrolling the loops: mld_poly_use_hint_88_avx2_loop and mld_poly_use_hint_32_avx2_loop
in both files. However, the benchmark results showed that this did not provide any performance benefit, so we decided to keep the current version.

bench components
- Δ (%) = (asm − AVX2) / AVX2 × 100

Component	Implementation	Build	ML-DSA-44	ML-DSA-65	ML-DSA-87	Notes
mld_poly_caddq (avg)	AVX2 intrinsics	no-opt	821	781	789
	x86_64 asm	no-opt	847	786	787
	Δ (%)	no-opt	+3.17%	+0.64%	-0.25%
mld_poly_caddq (avg)	AVX2 intrinsics	opt	210	147	143
	x86_64 asm	opt	220	153	155
	x86_64 asm (unroll)	opt	273	154	156	unroll by 4
	Δ (%)	opt	+4.76%	+4.08%	+8.39%
	Δ (%) (unroll)	opt	+30.00%	+4.76%	+9.09%	unroll by 4

bench
- Δ (%) = (asm − AVX2) / AVX2 × 100

Component	Implementation	Build	ML-DSA-44	ML-DSA-65	ML-DSA-87	Notes
keypair cycles (avg)	AVX2 intrinsics	no-opt	127436	218610	360739	baseline (main)
	x86_64 asm	no-opt	127459	217604	367118
	Δ (%)	no-opt	+0.02%	-0.46%	+1.77%
	AVX2 intrinsics	opt	56955	98362	157869	baseline (main)
	x86_64 asm	opt	59747	102961	165706
	x86_64 asm (unroll)	opt	59483	104732	166654
	Δ (%)	opt	+4.90%	+4.68%	+4.96%
	Δ (%) (unroll)	opt	+4.44%	+6.48%	+5.56%	unroll by 4
sign cycles (avg)	AVX2 intrinsics	no-opt	451922	756003	958151	baseline (main)
	x86_64 asm	no-opt	452833	752512	974497
	Δ (%)	no-opt	+0.20%	-0.46%	+1.71%
	AVX2 intrinsics	opt	170370	281545	347924	baseline (main)
	x86_64 asm	opt	178564	294843	362677
	x86_64 asm (unroll)	opt	177251	300667	366158
	Δ (%)	opt	+4.81%	+4.72%	+4.24%
	Δ (%) (unroll)	opt	+4.04%	+6.79%	+5.24%	unroll by 4
verify cycles (avg)	AVX2 intrinsics	no-opt	134113	220671	363234	baseline (main)
	x86_64 asm	no-opt	134633	220015	369763
	Δ (%)	no-opt	+0.39%	-0.30%	+1.80%
	AVX2 intrinsics	opt	60234	98904	156281	baseline (main)
	x86_64 asm	opt	63140	103682	164376
	x86_64 asm (unroll)	opt	62822	105719	164028
	Δ (%)	opt	+4.82%	+4.83%	+5.18%
	Δ (%) (unroll)	opt	+4.30%	+6.89%	+4.96%	unroll by 4

oqs-bot · 2026-02-03T07:58:29Z

CBMC Results (ML-DSA-87)

Full Results (175 proofs)

Proof	Status	Current	Previous	Change
`TOTAL`	✅	2433s	2484s	-2.1%
`sign_verify_internal`	✅	301s	313s	-4%
`mld_attempt_signature_generation`	✅	210s	218s	-4%
`polyvecl_pointwise_acc_montgomery_c`	✅	174s	183s	-5%
`polyvec_matrix_expand`	✅	158s	165s	-4%
`rej_uniform_native`	✅	137s	144s	-5%
`poly_pointwise_montgomery_c`	✅	128s	133s	-4%
`mld_invntt_layer`	✅	119s	122s	-2%
`polyvec_matrix_expand_serial`	✅	108s	108s	+0%
`mld_ct_memcmp`	✅	77s	81s	-5%
`sign_signature_internal`	✅	76s	73s	+4%
`mld_ntt_layer`	✅	44s	44s	+0%
`keccak_squeezeblocks_x4`	✅	42s	43s	-2%
`mld_compute_t0_t1_tr_from_sk_components`	✅	24s	25s	-4%
`polymat_permute_bitrev_to_custom`	✅	24s	27s	-11%
`rej_uniform`	✅	20s	20s	+0%
`fqmul`	✅	18s	18s	+0%
`poly_chknorm_c`	✅	16s	18s	-11%
`mld_ntt_butterfly_block`	✅	15s	13s	+15%
`poly_uniform_4x`	✅	15s	16s	-6%
`rej_uniform_c`	✅	15s	18s	-17%
`mld_check_pct`	✅	14s	11s	+27%
`poly_uniform_eta_4x`	✅	14s	14s	+0%
`polyeta_unpack`	✅	14s	12s	+17%
`polyveck_add`	✅	14s	15s	-7%
`polyveck_power2round`	✅	14s	13s	+8%
`keccakf1600x4_permute_native`	✅	13s	15s	-13%
`polyt0_unpack`	✅	13s	15s	-13%
`polyvec_matrix_pointwise_montgomery`	✅	13s	13s	+0%
`polyveck_use_hint`	✅	11s	10s	+10%
`polyveck_reduce`	✅	10s	9s	+11%
`keccak_absorb_once_x4`	✅	9s	11s	-18%
`poly_invntt_tomont_c`	✅	9s	7s	+29%
`polyveck_caddq`	✅	9s	8s	+12%
`polyvecl_ntt`	✅	9s	8s	+12%
`keccakf1600_permute_native`	✅	8s	9s	-11%
`mld_compute_pack_z`	✅	8s	11s	-27%
`mld_polyvecl_permute_bitrev_to_custom_native`	✅	8s	8s	+0%
`poly_decompose_c`	✅	8s	8s	+0%
`polyveck_chknorm`	✅	8s	11s	-27%
`polyveck_invntt_tomont`	✅	8s	7s	+14%
`polyveck_ntt`	✅	8s	6s	+33%
`polyveck_pointwise_poly_montgomery`	✅	8s	8s	+0%
`sign`	✅	8s	7s	+14%
`unpack_sk`	✅	8s	8s	+0%
`keccakf1600_permute`	✅	7s	5s	+40%
`mld_sample_s1_s2`	✅	7s	8s	-12%
`mld_sample_s1_s2_serial`	✅	7s	8s	-12%
`polyveck_sub`	✅	7s	7s	+0%
`polyz_unpack_native`	✅	7s	3s	+133%
`sign_pk_from_sk`	✅	7s	10s	-30%
`unpack_hints`	✅	7s	5s	+40%
`keccak_absorb`	✅	6s	6s	+0%
`polyveck_decompose`	✅	6s	8s	-25%
`polyveck_make_hint`	✅	6s	4s	+50%
`polyveck_shiftl`	✅	6s	6s	+0%
`polyvecl_uniform_gamma1_serial`	✅	6s	3s	+100%
`sign_signature`	✅	6s	6s	+0%
`unpack_pk`	✅	6s	5s	+20%
`unpack_sig`	✅	6s	5s	+20%
`mld_ct_get_optblocker_u32`	✅	5s	3s	+67%
`poly_caddq_c`	✅	5s	3s	+67%
`poly_caddq_native`	✅	5s	5s	+0%
`poly_ntt_native`	✅	5s	3s	+67%
`poly_shiftl`	✅	5s	5s	+0%
`poly_uniform_gamma1_4x`	✅	5s	2s	+150%
`poly_use_hint_c`	✅	5s	2s	+150%
`polyt0_pack`	✅	5s	4s	+25%
`polyvecl_chknorm`	✅	5s	4s	+25%
`rej_eta_native`	✅	5s	3s	+67%
`shake256x4_squeezeblocks`	✅	5s	4s	+25%
`sign_keypair`	✅	5s	4s	+25%
`sign_keypair_internal`	✅	5s	6s	-17%
`sign_signature_extmu`	✅	5s	6s	-17%
`sign_verify`	✅	5s	2s	+150%
`fqscale`	✅	4s	2s	+100%
`intt_native_x86_64`	✅	4s	3s	+33%
`make_hint`	✅	4s	3s	+33%
`mld_h`	✅	4s	4s	+0%
`mld_keccakf1600_extract_bytes`	✅	4s	2s	+100%
`mld_value_barrier_u32`	✅	4s	3s	+33%
`poly_add`	✅	4s	3s	+33%
`poly_chknorm_native`	✅	4s	3s	+33%
`poly_invntt_tomont_native`	✅	4s	2s	+100%
`poly_sub`	✅	4s	4s	+0%
`poly_use_hint_native`	✅	4s	3s	+33%
`polyveck_pack_t0`	✅	4s	3s	+33%
`polyveck_pack_w1`	✅	4s	3s	+33%
`polyveck_unpack_eta`	✅	4s	5s	-20%
`polyvecl_pointwise_acc_montgomery`	✅	4s	3s	+33%
`polyvecl_pointwise_acc_montgomery_native`	✅	4s	4s	+0%
`polyvecl_unpack_eta`	✅	4s	5s	-20%
`polyz_unpack`	✅	4s	3s	+33%
`polyz_unpack_c`	✅	4s	5s	-20%
`power2round`	✅	4s	2s	+100%
`rej_eta_c`	✅	4s	4s	+0%
`shake128_absorb`	✅	4s	4s	+0%
`shake128_squeeze`	✅	4s	3s	+33%
`shake128x4_squeezeblocks`	✅	4s	2s	+100%
`sign_open`	✅	4s	3s	+33%
`sign_verify_extmu`	✅	4s	4s	+0%
`sign_verify_pre_hash_shake256`	✅	4s	3s	+33%
`caddq`	✅	3s	4s	-25%
`keccak_finalize`	✅	3s	3s	+0%
`keccak_init`	✅	3s	2s	+50%
`keccak_squeeze`	✅	3s	4s	-25%
`keccakf1600_extract_bytes (big endian)`	✅	3s	3s	+0%
`keccakf1600_xor_bytes (big endian)`	✅	3s	2s	+50%
`keccakf1600x4_extract_bytes`	✅	3s	2s	+50%
`mld_ct_abs_i32`	✅	3s	3s	+0%
`mld_ct_cmask_neg_i32`	✅	3s	3s	+0%
`mld_ct_sel_int32`	✅	3s	1s	+200%
`mld_prepare_domain_separation_prefix`	✅	3s	5s	-40%
`montgomery_reduce`	✅	3s	4s	-25%
`pack_pk`	✅	3s	2s	+50%
`pack_sig_z`	✅	3s	2s	+50%
`pack_sk`	✅	3s	3s	+0%
`poly_caddq`	✅	3s	4s	-25%
`poly_challenge`	✅	3s	4s	-25%
`poly_chknorm`	✅	3s	2s	+50%
`poly_decompose`	✅	3s	3s	+0%
`poly_ntt`	✅	3s	2s	+50%
`poly_ntt_c`	✅	3s	3s	+0%
`poly_pointwise_montgomery_native`	✅	3s	3s	+0%
`poly_power2round`	✅	3s	1s	+200%
`poly_reduce`	✅	3s	2s	+50%
`poly_uniform_gamma1`	✅	3s	4s	-25%
`poly_use_hint`	✅	3s	4s	-25%
`polyeta_pack`	✅	3s	2s	+50%
`polyt1_unpack`	✅	3s	3s	+0%
`polyveck_pack_eta`	✅	3s	3s	+0%
`polyveck_unpack_t0`	✅	3s	4s	-25%
`polyvecl_pack_eta`	✅	3s	3s	+0%
`polyvecl_permute_bitrev_to_custom`	✅	3s	2s	+50%
`polyvecl_unpack_z`	✅	3s	6s	-50%
`polyw1_pack`	✅	3s	4s	-25%
`rej_eta`	✅	3s	2s	+50%
`shake128x4_absorb_once`	✅	3s	3s	+0%
`shake256_absorb`	✅	3s	2s	+50%
`shake256_finalize`	✅	3s	2s	+50%
`shake256_release`	✅	3s	2s	+50%
`shake256_squeeze`	✅	3s	4s	-25%
`sign_signature_pre_hash_internal`	✅	3s	6s	-50%
`sign_signature_pre_hash_shake256`	✅	3s	6s	-50%
`sys_check_capability`	✅	3s	2s	+50%
`decompose`	✅	2s	3s	-33%
`keccakf1600_xor_bytes`	✅	2s	3s	-33%
`keccakf1600x4_permute`	✅	2s	2s	+0%
`mld_ct_cmask_nonzero_u32`	✅	2s	3s	-33%
`mld_ct_cmask_nonzero_u8`	✅	2s	3s	-33%
`mld_ct_get_optblocker_i64`	✅	2s	2s	+0%
`mld_ct_get_optblocker_u8`	✅	2s	2s	+0%
`mld_value_barrier_i64`	✅	2s	2s	+0%
`ntt_native_x86_64`	✅	2s	5s	-60%
`pack_sig_c_h`	✅	2s	7s	-71%
`poly_decompose_native`	✅	2s	3s	-33%
`poly_invntt_tomont`	✅	2s	4s	-50%
`poly_make_hint`	✅	2s	2s	+0%
`poly_pointwise_montgomery`	✅	2s	2s	+0%
`poly_uniform`	✅	2s	2s	+0%
`poly_uniform_eta`	✅	2s	5s	-60%
`polyt1_pack`	✅	2s	4s	-50%
`polyvecl_uniform_gamma1`	✅	2s	3s	-33%
`polyz_pack`	✅	2s	2s	+0%
`shake128_finalize`	✅	2s	2s	+0%
`shake128_init`	✅	2s	2s	+0%
`shake128_release`	✅	2s	3s	-33%
`shake256`	✅	2s	3s	-33%
`shake256x4_absorb_once`	✅	2s	4s	-50%
`sign_verify_pre_hash_internal`	✅	2s	3s	-33%
`use_hint`	✅	2s	3s	-33%
`keccakf1600x4_xor_bytes`	✅	1s	4s	-75%
`mld_value_barrier_u8`	✅	1s	2s	-50%
`poly_caddq_native_aarch64`	✅	1s	4s	-75%
`reduce32`	✅	1s	2s	-50%
`shake256_init`	✅	1s	3s	-67%

oqs-bot · 2026-02-03T07:59:14Z

CBMC Results (ML-DSA-44)

Full Results (175 proofs)

Proof	Status	Current	Previous	Change
`TOTAL`	✅	2061s	2185s	-5.7%
`mld_attempt_signature_generation`	✅	304s	330s	-8%
`polyvecl_pointwise_acc_montgomery_c`	✅	200s	217s	-8%
`sign_verify_internal`	✅	190s	192s	-1%
`rej_uniform_native`	✅	142s	151s	-6%
`poly_pointwise_montgomery_c`	✅	131s	148s	-11%
`mld_invntt_layer`	✅	115s	124s	-7%
`mld_ct_memcmp`	✅	81s	88s	-8%
`keccak_squeezeblocks_x4`	✅	46s	43s	+7%
`mld_ntt_layer`	✅	42s	49s	-14%
`sign_signature_internal`	✅	22s	22s	+0%
`rej_uniform`	✅	20s	22s	-9%
`fqmul`	✅	18s	20s	-10%
`poly_uniform_eta_4x`	✅	18s	17s	+6%
`rej_uniform_c`	✅	16s	20s	-20%
`mld_compute_t0_t1_tr_from_sk_components`	✅	15s	15s	+0%
`mld_polyvecl_permute_bitrev_to_custom_native`	✅	15s	15s	+0%
`polymat_permute_bitrev_to_custom`	✅	15s	16s	-6%
`polyt0_unpack`	✅	15s	18s	-17%
`polyvec_matrix_expand`	✅	14s	16s	-12%
`keccakf1600x4_permute_native`	✅	13s	13s	+0%
`poly_uniform_4x`	✅	13s	13s	+0%
`polyeta_unpack`	✅	13s	15s	-13%
`polyz_unpack_c`	✅	13s	14s	-7%
`keccak_absorb_once_x4`	✅	12s	14s	-14%
`poly_chknorm_c`	✅	12s	14s	-14%
`mld_ntt_butterfly_block`	✅	11s	13s	-15%
`keccakf1600_permute`	✅	8s	7s	+14%
`keccakf1600_permute_native`	✅	8s	9s	-11%
`poly_invntt_tomont_c`	✅	8s	8s	+0%
`polyvec_matrix_pointwise_montgomery`	✅	8s	6s	+33%
`mld_check_pct`	✅	7s	8s	-12%
`polyveck_add`	✅	7s	9s	-22%
`polyveck_decompose`	✅	7s	5s	+40%
`sign_verify`	✅	7s	7s	+0%
`sign_verify_pre_hash_internal`	✅	7s	3s	+133%
`keccak_absorb`	✅	6s	6s	+0%
`mld_compute_pack_z`	✅	6s	7s	-14%
`mld_prepare_domain_separation_prefix`	✅	6s	3s	+100%
`mld_sample_s1_s2`	✅	6s	4s	+50%
`poly_decompose_native`	✅	6s	4s	+50%
`poly_uniform_eta`	✅	6s	4s	+50%
`polyveck_ntt`	✅	6s	7s	-14%
`polyveck_pointwise_poly_montgomery`	✅	6s	7s	-14%
`polyveck_power2round`	✅	6s	5s	+20%
`polyvecl_ntt`	✅	6s	7s	-14%
`polyvecl_uniform_gamma1`	✅	6s	4s	+50%
`sign_keypair_internal`	✅	6s	5s	+20%
`sign_open`	✅	6s	4s	+50%
`sign_pk_from_sk`	✅	6s	7s	-14%
`sign_signature_pre_hash_shake256`	✅	6s	6s	+0%
`make_hint`	✅	5s	3s	+67%
`mld_h`	✅	5s	7s	-29%
`mld_sample_s1_s2_serial`	✅	5s	4s	+25%
`montgomery_reduce`	✅	5s	3s	+67%
`ntt_native_x86_64`	✅	5s	4s	+25%
`poly_uniform_gamma1`	✅	5s	4s	+25%
`poly_uniform_gamma1_4x`	✅	5s	4s	+25%
`poly_use_hint_c`	✅	5s	5s	+0%
`polyt0_pack`	✅	5s	3s	+67%
`polyvec_matrix_expand_serial`	✅	5s	5s	+0%
`polyveck_caddq`	✅	5s	5s	+0%
`polyveck_reduce`	✅	5s	5s	+0%
`polyveck_sub`	✅	5s	5s	+0%
`polyveck_use_hint`	✅	5s	6s	-17%
`polyvecl_pack_eta`	✅	5s	3s	+67%
`rej_eta_c`	✅	5s	4s	+25%
`shake128_init`	✅	5s	2s	+150%
`sign`	✅	5s	9s	-44%
`sign_signature`	✅	5s	6s	-17%
`unpack_hints`	✅	5s	6s	-17%
`keccakf1600_extract_bytes (big endian)`	✅	4s	2s	+100%
`keccakf1600_xor_bytes (big endian)`	✅	4s	2s	+100%
`mld_ct_cmask_nonzero_u8`	✅	4s	3s	+33%
`poly_add`	✅	4s	6s	-33%
`poly_challenge`	✅	4s	4s	+0%
`poly_chknorm_native`	✅	4s	2s	+100%
`poly_decompose_c`	✅	4s	3s	+33%
`poly_pointwise_montgomery`	✅	4s	1s	+300%
`poly_power2round`	✅	4s	4s	+0%
`poly_uniform`	✅	4s	5s	-20%
`poly_use_hint_native`	✅	4s	4s	+0%
`polyeta_pack`	✅	4s	2s	+100%
`polyveck_invntt_tomont`	✅	4s	5s	-20%
`polyveck_pack_t0`	✅	4s	3s	+33%
`polyveck_shiftl`	✅	4s	5s	-20%
`polyvecl_chknorm`	✅	4s	5s	-20%
`polyvecl_pointwise_acc_montgomery_native`	✅	4s	3s	+33%
`polyw1_pack`	✅	4s	4s	+0%
`power2round`	✅	4s	2s	+100%
`rej_eta`	✅	4s	4s	+0%
`shake128_squeeze`	✅	4s	2s	+100%
`shake256x4_absorb_once`	✅	4s	3s	+33%
`sign_keypair`	✅	4s	5s	-20%
`sign_signature_extmu`	✅	4s	4s	+0%
`sign_signature_pre_hash_internal`	✅	4s	3s	+33%
`unpack_sk`	✅	4s	3s	+33%
`caddq`	✅	3s	3s	+0%
`intt_native_x86_64`	✅	3s	4s	-25%
`keccak_finalize`	✅	3s	5s	-40%
`keccak_init`	✅	3s	3s	+0%
`keccakf1600x4_extract_bytes`	✅	3s	2s	+50%
`keccakf1600x4_xor_bytes`	✅	3s	3s	+0%
`mld_ct_abs_i32`	✅	3s	2s	+50%
`mld_ct_cmask_nonzero_u32`	✅	3s	3s	+0%
`mld_ct_get_optblocker_u8`	✅	3s	2s	+50%
`mld_value_barrier_u32`	✅	3s	2s	+50%
`mld_value_barrier_u8`	✅	3s	3s	+0%
`pack_pk`	✅	3s	5s	-40%
`pack_sig_z`	✅	3s	4s	-25%
`pack_sk`	✅	3s	3s	+0%
`poly_caddq_c`	✅	3s	3s	+0%
`poly_caddq_native_aarch64`	✅	3s	4s	-25%
`poly_invntt_tomont`	✅	3s	5s	-40%
`poly_invntt_tomont_native`	✅	3s	2s	+50%
`poly_ntt`	✅	3s	3s	+0%
`poly_ntt_c`	✅	3s	1s	+200%
`poly_pointwise_montgomery_native`	✅	3s	4s	-25%
`poly_shiftl`	✅	3s	3s	+0%
`polyt1_pack`	✅	3s	3s	+0%
`polyt1_unpack`	✅	3s	4s	-25%
`polyveck_chknorm`	✅	3s	3s	+0%
`polyveck_make_hint`	✅	3s	5s	-40%
`polyveck_pack_eta`	✅	3s	5s	-40%
`polyveck_unpack_eta`	✅	3s	3s	+0%
`polyvecl_permute_bitrev_to_custom`	✅	3s	4s	-25%
`polyvecl_pointwise_acc_montgomery`	✅	3s	5s	-40%
`polyvecl_uniform_gamma1_serial`	✅	3s	4s	-25%
`polyvecl_unpack_eta`	✅	3s	2s	+50%
`polyvecl_unpack_z`	✅	3s	3s	+0%
`polyz_unpack`	✅	3s	4s	-25%
`polyz_unpack_native`	✅	3s	3s	+0%
`reduce32`	✅	3s	2s	+50%
`shake256_squeeze`	✅	3s	2s	+50%
`sign_verify_extmu`	✅	3s	3s	+0%
`sign_verify_pre_hash_shake256`	✅	3s	3s	+0%
`use_hint`	✅	3s	2s	+50%
`decompose`	✅	2s	3s	-33%
`fqscale`	✅	2s	4s	-50%
`keccakf1600_xor_bytes`	✅	2s	3s	-33%
`keccakf1600x4_permute`	✅	2s	2s	+0%
`mld_ct_cmask_neg_i32`	✅	2s	3s	-33%
`mld_ct_get_optblocker_i64`	✅	2s	4s	-50%
`mld_ct_get_optblocker_u32`	✅	2s	1s	+100%
`mld_ct_sel_int32`	✅	2s	2s	+0%
`pack_sig_c_h`	✅	2s	3s	-33%
`poly_caddq`	✅	2s	3s	-33%
`poly_caddq_native`	✅	2s	4s	-50%
`poly_decompose`	✅	2s	2s	+0%
`poly_make_hint`	✅	2s	3s	-33%
`poly_ntt_native`	✅	2s	3s	-33%
`poly_reduce`	✅	2s	2s	+0%
`poly_sub`	✅	2s	1s	+100%
`poly_use_hint`	✅	2s	5s	-60%
`polyveck_pack_w1`	✅	2s	2s	+0%
`polyveck_unpack_t0`	✅	2s	3s	-33%
`polyz_pack`	✅	2s	4s	-50%
`rej_eta_native`	✅	2s	4s	-50%
`shake128_absorb`	✅	2s	3s	-33%
`shake128_finalize`	✅	2s	2s	+0%
`shake128_release`	✅	2s	1s	+100%
`shake128x4_absorb_once`	✅	2s	3s	-33%
`shake128x4_squeezeblocks`	✅	2s	3s	-33%
`shake256`	✅	2s	3s	-33%
`shake256_absorb`	✅	2s	8s	-75%
`shake256_finalize`	✅	2s	2s	+0%
`shake256_init`	✅	2s	2s	+0%
`shake256_release`	✅	2s	3s	-33%
`shake256x4_squeezeblocks`	✅	2s	2s	+0%
`sys_check_capability`	✅	2s	3s	-33%
`unpack_pk`	✅	2s	3s	-33%
`unpack_sig`	✅	2s	2s	+0%
`keccak_squeeze`	✅	1s	2s	-50%
`mld_keccakf1600_extract_bytes`	✅	1s	3s	-67%
`mld_value_barrier_i64`	✅	1s	3s	-67%
`poly_chknorm`	✅	1s	4s	-75%

oqs-bot · 2026-02-03T08:00:03Z

CBMC Results (ML-DSA-65)

Full Results (175 proofs)

Proof	Status	Current	Previous	Change
`TOTAL`	✅	2402s	2317s	+3.7%
`mld_attempt_signature_generation`	✅	248s	231s	+7%
`polyvecl_pointwise_acc_montgomery_c`	✅	243s	221s	+10%
`sign_verify_internal`	✅	212s	200s	+6%
`poly_pointwise_montgomery_c`	✅	150s	140s	+7%
`rej_uniform_native`	✅	148s	140s	+6%
`mld_invntt_layer`	✅	125s	119s	+5%
`polyvec_matrix_expand`	✅	120s	114s	+5%
`mld_ct_memcmp`	✅	84s	81s	+4%
`polyvec_matrix_expand_serial`	✅	65s	66s	-2%
`mld_ntt_layer`	✅	46s	45s	+2%
`keccak_squeezeblocks_x4`	✅	45s	44s	+2%
`sign_signature_internal`	✅	43s	43s	+0%
`mld_compute_t0_t1_tr_from_sk_components`	✅	27s	25s	+8%
`fqmul`	✅	20s	20s	+0%
`polymat_permute_bitrev_to_custom`	✅	20s	19s	+5%
`poly_chknorm_c`	✅	19s	16s	+19%
`poly_uniform_eta_4x`	✅	19s	16s	+19%
`rej_uniform`	✅	19s	20s	-5%
`polyvec_matrix_pointwise_montgomery`	✅	18s	13s	+38%
`polyveck_decompose`	✅	18s	17s	+6%
`rej_uniform_c`	✅	18s	17s	+6%
`poly_uniform_4x`	✅	16s	14s	+14%
`mld_ntt_butterfly_block`	✅	15s	12s	+25%
`mld_polyvecl_permute_bitrev_to_custom_native`	✅	15s	13s	+15%
`polyt0_unpack`	✅	15s	17s	-12%
`polyveck_use_hint`	✅	14s	11s	+27%
`keccakf1600x4_permute_native`	✅	12s	12s	+0%
`keccak_absorb_once_x4`	✅	11s	12s	-8%
`keccakf1600_permute_native`	✅	10s	9s	+11%
`polyveck_power2round`	✅	10s	8s	+25%
`sign`	✅	10s	10s	+0%
`keccak_absorb`	✅	9s	6s	+50%
`polyveck_add`	✅	9s	11s	-18%
`polyveck_reduce`	✅	9s	8s	+12%
`keccakf1600_permute`	✅	8s	10s	-20%
`mld_check_pct`	✅	8s	8s	+0%
`mld_h`	✅	8s	5s	+60%
`poly_decompose_c`	✅	8s	7s	+14%
`polyeta_unpack`	✅	8s	6s	+33%
`polyveck_caddq`	✅	8s	6s	+33%
`polyveck_invntt_tomont`	✅	8s	9s	-11%
`polyveck_sub`	✅	8s	8s	+0%
`mld_compute_pack_z`	✅	7s	5s	+40%
`mld_sample_s1_s2_serial`	✅	7s	6s	+17%
`poly_invntt_tomont_c`	✅	7s	7s	+0%
`polyveck_ntt`	✅	7s	8s	-12%
`polyveck_shiftl`	✅	7s	6s	+17%
`polyvecl_unpack_z`	✅	7s	4s	+75%
`sign_pk_from_sk`	✅	7s	5s	+40%
`poly_caddq_native`	✅	6s	2s	+200%
`polyveck_pack_t0`	✅	6s	7s	-14%
`polyveck_pointwise_poly_montgomery`	✅	6s	6s	+0%
`polyvecl_ntt`	✅	6s	8s	-25%
`polyz_unpack_c`	✅	6s	7s	-14%
`sign_verify_pre_hash_shake256`	✅	6s	4s	+50%
`unpack_hints`	✅	6s	5s	+20%
`unpack_pk`	✅	6s	2s	+200%
`keccakf1600_extract_bytes (big endian)`	✅	5s	3s	+67%
`keccakf1600x4_xor_bytes`	✅	5s	3s	+67%
`mld_prepare_domain_separation_prefix`	✅	5s	2s	+150%
`mld_sample_s1_s2`	✅	5s	5s	+0%
`poly_make_hint`	✅	5s	4s	+25%
`poly_pointwise_montgomery`	✅	5s	6s	-17%
`poly_power2round`	✅	5s	6s	-17%
`poly_use_hint_c`	✅	5s	6s	-17%
`polyveck_chknorm`	✅	5s	5s	+0%
`polyveck_make_hint`	✅	5s	5s	+0%
`rej_eta_c`	✅	5s	5s	+0%
`rej_eta_native`	✅	5s	4s	+25%
`shake256_absorb`	✅	5s	3s	+67%
`sign_keypair_internal`	✅	5s	8s	-38%
`keccak_finalize`	✅	4s	2s	+100%
`keccak_squeeze`	✅	4s	5s	-20%
`mld_ct_cmask_nonzero_u32`	✅	4s	3s	+33%
`mld_ct_get_optblocker_u32`	✅	4s	2s	+100%
`mld_value_barrier_i64`	✅	4s	3s	+33%
`mld_value_barrier_u8`	✅	4s	1s	+300%
`montgomery_reduce`	✅	4s	2s	+100%
`pack_sk`	✅	4s	3s	+33%
`poly_caddq_c`	✅	4s	4s	+0%
`poly_challenge`	✅	4s	5s	-20%
`poly_invntt_tomont`	✅	4s	2s	+100%
`poly_pointwise_montgomery_native`	✅	4s	3s	+33%
`poly_reduce`	✅	4s	3s	+33%
`poly_uniform`	✅	4s	2s	+100%
`poly_uniform_eta`	✅	4s	6s	-33%
`poly_uniform_gamma1`	✅	4s	5s	-20%
`poly_uniform_gamma1_4x`	✅	4s	3s	+33%
`polyeta_pack`	✅	4s	4s	+0%
`polyt0_pack`	✅	4s	5s	-20%
`polyt1_pack`	✅	4s	3s	+33%
`polyveck_unpack_t0`	✅	4s	4s	+0%
`polyvecl_chknorm`	✅	4s	5s	-20%
`polyvecl_pointwise_acc_montgomery_native`	✅	4s	4s	+0%
`polyvecl_uniform_gamma1`	✅	4s	3s	+33%
`polyvecl_uniform_gamma1_serial`	✅	4s	3s	+33%
`polyvecl_unpack_eta`	✅	4s	3s	+33%
`polyz_unpack_native`	✅	4s	4s	+0%
`shake256`	✅	4s	4s	+0%
`sign_keypair`	✅	4s	3s	+33%
`sign_signature_extmu`	✅	4s	3s	+33%
`sign_signature_pre_hash_internal`	✅	4s	4s	+0%
`sign_signature_pre_hash_shake256`	✅	4s	3s	+33%
`sign_verify`	✅	4s	2s	+100%
`sys_check_capability`	✅	4s	2s	+100%
`unpack_sig`	✅	4s	3s	+33%
`unpack_sk`	✅	4s	6s	-33%
`use_hint`	✅	4s	1s	+300%
`fqscale`	✅	3s	2s	+50%
`keccak_init`	✅	3s	2s	+50%
`keccakf1600_xor_bytes (big endian)`	✅	3s	2s	+50%
`keccakf1600x4_permute`	✅	3s	3s	+0%
`mld_ct_abs_i32`	✅	3s	2s	+50%
`mld_ct_cmask_neg_i32`	✅	3s	2s	+50%
`mld_ct_cmask_nonzero_u8`	✅	3s	4s	-25%
`mld_keccakf1600_extract_bytes`	✅	3s	2s	+50%
`ntt_native_x86_64`	✅	3s	4s	-25%
`pack_sig_c_h`	✅	3s	4s	-25%
`poly_add`	✅	3s	4s	-25%
`poly_caddq`	✅	3s	4s	-25%
`poly_caddq_native_aarch64`	✅	3s	6s	-50%
`poly_chknorm`	✅	3s	5s	-40%
`poly_chknorm_native`	✅	3s	4s	-25%
`poly_ntt_c`	✅	3s	3s	+0%
`poly_shiftl`	✅	3s	5s	-40%
`poly_sub`	✅	3s	3s	+0%
`poly_use_hint`	✅	3s	6s	-50%
`poly_use_hint_native`	✅	3s	4s	-25%
`polyt1_unpack`	✅	3s	3s	+0%
`polyveck_pack_eta`	✅	3s	4s	-25%
`polyveck_unpack_eta`	✅	3s	4s	-25%
`polyvecl_permute_bitrev_to_custom`	✅	3s	4s	-25%
`polyw1_pack`	✅	3s	3s	+0%
`polyz_unpack`	✅	3s	6s	-50%
`rej_eta`	✅	3s	3s	+0%
`shake128_finalize`	✅	3s	4s	-25%
`shake128_squeeze`	✅	3s	2s	+50%
`shake256_init`	✅	3s	3s	+0%
`shake256x4_absorb_once`	✅	3s	4s	-25%
`sign_open`	✅	3s	4s	-25%
`sign_signature`	✅	3s	3s	+0%
`sign_verify_pre_hash_internal`	✅	3s	5s	-40%
`caddq`	✅	2s	2s	+0%
`decompose`	✅	2s	3s	-33%
`intt_native_x86_64`	✅	2s	4s	-50%
`keccakf1600x4_extract_bytes`	✅	2s	3s	-33%
`make_hint`	✅	2s	4s	-50%
`mld_ct_get_optblocker_i64`	✅	2s	3s	-33%
`mld_ct_get_optblocker_u8`	✅	2s	2s	+0%
`pack_pk`	✅	2s	3s	-33%
`pack_sig_z`	✅	2s	2s	+0%
`poly_decompose`	✅	2s	4s	-50%
`poly_decompose_native`	✅	2s	6s	-67%
`poly_invntt_tomont_native`	✅	2s	3s	-33%
`poly_ntt`	✅	2s	5s	-60%
`poly_ntt_native`	✅	2s	4s	-50%
`polyveck_pack_w1`	✅	2s	4s	-50%
`polyvecl_pack_eta`	✅	2s	5s	-60%
`polyvecl_pointwise_acc_montgomery`	✅	2s	6s	-67%
`polyz_pack`	✅	2s	3s	-33%
`power2round`	✅	2s	3s	-33%
`reduce32`	✅	2s	2s	+0%
`shake128_init`	✅	2s	4s	-50%
`shake128x4_absorb_once`	✅	2s	3s	-33%
`shake128x4_squeezeblocks`	✅	2s	3s	-33%
`shake256_release`	✅	2s	3s	-33%
`shake256_squeeze`	✅	2s	2s	+0%
`sign_verify_extmu`	✅	2s	6s	-67%
`keccakf1600_xor_bytes`	✅	1s	4s	-75%
`mld_ct_sel_int32`	✅	1s	4s	-75%
`mld_value_barrier_u32`	✅	1s	4s	-75%
`shake128_absorb`	✅	1s	3s	-67%
`shake128_release`	✅	1s	2s	-50%
`shake256_finalize`	✅	1s	4s	-75%
`shake256x4_squeezeblocks`	✅	1s	2s	-50%

github-actions

Mac Mini (M1, 2020) benchmarks (opt)

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`46205` cycles	`46203` cycles	`1.00`
`ML-DSA-44 sign`	`131278` cycles	`131278` cycles	`1`
`ML-DSA-44 verify`	`47765` cycles	`47768` cycles	`1.00`
`ML-DSA-65 keypair`	`81014` cycles	`81024` cycles	`1.00`
`ML-DSA-65 sign`	`215785` cycles	`215787` cycles	`1.00`
`ML-DSA-65 verify`	`80057` cycles	`80052` cycles	`1.00`
`ML-DSA-87 keypair`	`132158` cycles	`132151` cycles	`1.00`
`ML-DSA-87 sign`	`276862` cycles	`276816` cycles	`1.00`
`ML-DSA-87 verify`	`130418` cycles	`130384` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`114213` cycles	`114155` cycles	`1.00`
`ML-DSA-44 sign`	`418158` cycles	`417994` cycles	`1.00`
`ML-DSA-44 verify`	`122319` cycles	`122262` cycles	`1.00`
`ML-DSA-65 keypair`	`195508` cycles	`195499` cycles	`1.00`
`ML-DSA-65 sign`	`682497` cycles	`682470` cycles	`1.00`
`ML-DSA-65 verify`	`197760` cycles	`197741` cycles	`1.00`
`ML-DSA-87 keypair`	`322642` cycles	`322656` cycles	`1.00`
`ML-DSA-87 sign`	`864585` cycles	`864584` cycles	`1.00`
`ML-DSA-87 verify`	`328628` cycles	`328653` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`34677` cycles	`34696` cycles	`1.00`
`ML-DSA-44 sign`	`120151` cycles	`120195` cycles	`1.00`
`ML-DSA-44 verify`	`38151` cycles	`38145` cycles	`1.00`
`ML-DSA-65 keypair`	`61275` cycles	`60582` cycles	`1.01`
`ML-DSA-65 sign`	`202094` cycles	`200476` cycles	`1.01`
`ML-DSA-65 verify`	`62940` cycles	`62563` cycles	`1.01`
`ML-DSA-87 keypair`	`93525` cycles	`94602` cycles	`0.99`
`ML-DSA-87 sign`	`236210` cycles	`240494` cycles	`0.98`
`ML-DSA-87 verify`	`95587` cycles	`95761` cycles	`1.00`

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

oqs-bot

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

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`93726` cycles	`93889` cycles	`1.00`
`ML-DSA-44 sign`	`333512` cycles	`333450` cycles	`1.00`
`ML-DSA-44 verify`	`99955` cycles	`99851` cycles	`1.00`
`ML-DSA-65 keypair`	`160065` cycles	`160390` cycles	`1.00`
`ML-DSA-65 sign`	`545794` cycles	`545908` cycles	`1.00`
`ML-DSA-65 verify`	`160881` cycles	`160887` cycles	`1.00`
`ML-DSA-87 keypair`	`267728` cycles	`267405` cycles	`1.00`
`ML-DSA-87 sign`	`707504` cycles	`707235` cycles	`1.00`
`ML-DSA-87 verify`	`270918` cycles	`269967` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`276468` cycles	`277102` cycles	`1.00`
`ML-DSA-44 sign`	`818650` cycles	`810656` cycles	`1.01`
`ML-DSA-44 verify`	`276672` cycles	`278882` cycles	`0.99`
`ML-DSA-65 keypair`	`475323` cycles	`478906` cycles	`0.99`
`ML-DSA-65 sign`	`1367640` cycles	`1360800` cycles	`1.01`
`ML-DSA-65 verify`	`459822` cycles	`466415` cycles	`0.99`
`ML-DSA-87 keypair`	`825623` cycles	`818822` cycles	`1.01`
`ML-DSA-87 sign`	`1873209` cycles	`1878770` cycles	`1.00`
`ML-DSA-87 verify`	`800938` cycles	`794467` cycles	`1.01`

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

oqs-bot

AMD EPYC 3rd gen (c6a)

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`69035` cycles	`69134` cycles	`1.00`
`ML-DSA-44 sign`	`187364` cycles	`187688` cycles	`1.00`
`ML-DSA-44 verify`	`69341` cycles	`69282` cycles	`1.00`
`ML-DSA-65 keypair`	`119503` cycles	`119368` cycles	`1.00`
`ML-DSA-65 sign`	`303527` cycles	`300862` cycles	`1.01`
`ML-DSA-65 verify`	`115926` cycles	`115513` cycles	`1.00`
`ML-DSA-87 keypair`	`203793` cycles	`203546` cycles	`1.00`
`ML-DSA-87 sign`	`394456` cycles	`394636` cycles	`1.00`
`ML-DSA-87 verify`	`195809` cycles	`195483` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`57235` cycles	`56751` cycles	`1.01`
`ML-DSA-44 sign`	`181496` cycles	`181670` cycles	`1.00`
`ML-DSA-44 verify`	`61165` cycles	`61146` cycles	`1.00`
`ML-DSA-65 keypair`	`98680` cycles	`98647` cycles	`1.00`
`ML-DSA-65 sign`	`298309` cycles	`298480` cycles	`1.00`
`ML-DSA-65 verify`	`100528` cycles	`100288` cycles	`1.00`
`ML-DSA-87 keypair`	`152581` cycles	`152587` cycles	`1.00`
`ML-DSA-87 sign`	`355291` cycles	`355235` cycles	`1.00`
`ML-DSA-87 verify`	`153950` cycles	`153556` cycles	`1.00`

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

oqs-bot

Graviton4

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`68156` cycles	`68132` cycles	`1.00`
`ML-DSA-44 sign`	`202004` cycles	`201919` cycles	`1.00`
`ML-DSA-44 verify`	`70775` cycles	`70781` cycles	`1.00`
`ML-DSA-65 keypair`	`120970` cycles	`120914` cycles	`1.00`
`ML-DSA-65 sign`	`331183` cycles	`331101` cycles	`1.00`
`ML-DSA-65 verify`	`117884` cycles	`117908` cycles	`1.00`
`ML-DSA-87 keypair`	`198649` cycles	`198347` cycles	`1.00`
`ML-DSA-87 sign`	`427544` cycles	`427112` cycles	`1.00`
`ML-DSA-87 verify`	`194417` cycles	`194311` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`135070` cycles	`134705` cycles	`1.00`
`ML-DSA-44 sign`	`526006` cycles	`524023` cycles	`1.00`
`ML-DSA-44 verify`	`147853` cycles	`147704` cycles	`1.00`
`ML-DSA-65 keypair`	`226865` cycles	`226528` cycles	`1.00`
`ML-DSA-65 sign`	`860582` cycles	`861852` cycles	`1.00`
`ML-DSA-65 verify`	`235373` cycles	`235761` cycles	`1.00`
`ML-DSA-87 keypair`	`370367` cycles	`371080` cycles	`1.00`
`ML-DSA-87 sign`	`1079627` cycles	`1079785` cycles	`1.00`
`ML-DSA-87 verify`	`382615` cycles	`383268` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`41639` cycles	`42042` cycles	`0.99`
`ML-DSA-44 sign`	`134495` cycles	`135046` cycles	`1.00`
`ML-DSA-44 verify`	`44953` cycles	`45886` cycles	`0.98`
`ML-DSA-65 keypair`	`72877` cycles	`72408` cycles	`1.01`
`ML-DSA-65 sign`	`214749` cycles	`215490` cycles	`1.00`
`ML-DSA-65 verify`	`73910` cycles	`73252` cycles	`1.01`
`ML-DSA-87 keypair`	`107778` cycles	`107965` cycles	`1.00`
`ML-DSA-87 sign`	`252308` cycles	`254024` cycles	`0.99`
`ML-DSA-87 verify`	`109196` cycles	`111034` cycles	`0.98`

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

oqs-bot

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

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`157593` cycles	`157623` cycles	`1.00`
`ML-DSA-44 sign`	`550359` cycles	`549610` cycles	`1.00`
`ML-DSA-44 verify`	`169225` cycles	`169078` cycles	`1.00`
`ML-DSA-65 keypair`	`267977` cycles	`267943` cycles	`1.00`
`ML-DSA-65 sign`	`903637` cycles	`902493` cycles	`1.00`
`ML-DSA-65 verify`	`274125` cycles	`274108` cycles	`1.00`
`ML-DSA-87 keypair`	`450990` cycles	`447542` cycles	`1.01`
`ML-DSA-87 sign`	`1162617` cycles	`1156527` cycles	`1.01`
`ML-DSA-87 verify`	`460584` cycles	`457749` cycles	`1.01`

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

oqs-bot

Graviton3

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`72258` cycles	`72244` cycles	`1.00`
`ML-DSA-44 sign`	`211991` cycles	`212021` cycles	`1.00`
`ML-DSA-44 verify`	`75712` cycles	`75740` cycles	`1.00`
`ML-DSA-65 keypair`	`127432` cycles	`127429` cycles	`1.00`
`ML-DSA-65 sign`	`350175` cycles	`350138` cycles	`1.00`
`ML-DSA-65 verify`	`125364` cycles	`125365` cycles	`1.00`
`ML-DSA-87 keypair`	`208138` cycles	`208164` cycles	`1.00`
`ML-DSA-87 sign`	`448958` cycles	`448891` cycles	`1.00`
`ML-DSA-87 verify`	`205105` cycles	`205092` cycles	`1.00`

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

oqs-bot

Graviton4 (no-opt)

Details

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`128309` cycles	`128287` cycles	`1.00`
`ML-DSA-44 sign`	`447743` cycles	`447655` cycles	`1.00`
`ML-DSA-44 verify`	`138349` cycles	`144617` cycles	`0.96`
`ML-DSA-65 keypair`	`220300` cycles	`220134` cycles	`1.00`
`ML-DSA-65 sign`	`727626` cycles	`727309` cycles	`1.00`
`ML-DSA-65 verify`	`223200` cycles	`223042` cycles	`1.00`
`ML-DSA-87 keypair`	`365101` cycles	`365095` cycles	`1.00`
`ML-DSA-87 sign`	`926593` cycles	`926085` cycles	`1.00`
`ML-DSA-87 verify`	`372803` cycles	`372794` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`120283` cycles	`123215` cycles	`0.98`
`ML-DSA-44 sign`	`447117` cycles	`449447` cycles	`0.99`
`ML-DSA-44 verify`	`131120` cycles	`129997` cycles	`1.01`
`ML-DSA-65 keypair`	`205159` cycles	`204042` cycles	`1.01`
`ML-DSA-65 sign`	`729240` cycles	`726667` cycles	`1.00`
`ML-DSA-65 verify`	`210548` cycles	`209895` cycles	`1.00`
`ML-DSA-87 keypair`	`336772` cycles	`336983` cycles	`1.00`
`ML-DSA-87 sign`	`923968` cycles	`923345` cycles	`1.00`
`ML-DSA-87 verify`	`346738` cycles	`346079` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`212612` cycles	`212810` cycles	`1.00`
`ML-DSA-44 sign`	`759997` cycles	`759720` cycles	`1.00`
`ML-DSA-44 verify`	`228854` cycles	`229136` cycles	`1.00`
`ML-DSA-65 keypair`	`380708` cycles	`380820` cycles	`1.00`
`ML-DSA-65 sign`	`1252502` cycles	`1251840` cycles	`1.00`
`ML-DSA-65 verify`	`371854` cycles	`372231` cycles	`1.00`
`ML-DSA-87 keypair`	`605059` cycles	`605579` cycles	`1.00`
`ML-DSA-87 sign`	`1593982` cycles	`1591706` cycles	`1.00`
`ML-DSA-87 verify`	`618815` cycles	`617581` 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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`828493` cycles	`828629` cycles	`1.00`
`ML-DSA-44 sign`	`3237874` cycles	`3236899` cycles	`1.00`
`ML-DSA-44 verify`	`920036` cycles	`920218` cycles	`1.00`
`ML-DSA-65 keypair`	`1414978` cycles	`1413016` cycles	`1.00`
`ML-DSA-65 sign`	`5366078` cycles	`5357541` cycles	`1.00`
`ML-DSA-65 verify`	`1482925` cycles	`1480164` cycles	`1.00`
`ML-DSA-87 keypair`	`2312703` cycles	`2311040` cycles	`1.00`
`ML-DSA-87 sign`	`6669160` cycles	`6668340` cycles	`1.00`
`ML-DSA-87 verify`	`2416765` cycles	`2415856` cycles	`1.00`

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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`222746` cycles	`227029` cycles	`0.98`
`ML-DSA-44 sign`	`609985` cycles	`617875` cycles	`0.99`
`ML-DSA-44 verify`	`223898` cycles	`224701` cycles	`1.00`
`ML-DSA-65 keypair`	`396984` cycles	`412531` cycles	`0.96`
`ML-DSA-65 sign`	`1037227` cycles	`1061715` cycles	`0.98`
`ML-DSA-65 verify`	`375316` cycles	`387814` cycles	`0.97`
`ML-DSA-87 keypair`	`658105` cycles	`666611` cycles	`0.99`
`ML-DSA-87 sign`	`1352975` cycles	`1398456` cycles	`0.97`
`ML-DSA-87 verify`	`638484` cycles	`667131` cycles	`0.96`

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: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-44 keypair`	`314316` cycles	`322374` cycles	`0.98`
`ML-DSA-44 sign`	`1219077` cycles	`1200283` cycles	`1.02`
`ML-DSA-44 verify`	`347864` cycles	`342633` cycles	`1.02`
`ML-DSA-65 keypair`	`605825` cycles	`566673` cycles	`1.07`
`ML-DSA-65 sign`	`2034909` cycles	`1937222` cycles	`1.05`
`ML-DSA-65 verify`	`568560` cycles	`546998` cycles	`1.04`
`ML-DSA-87 keypair`	`877363` cycles	`869944` cycles	`1.01`
`ML-DSA-87 sign`	`2465004` cycles	`2468357` cycles	`1.00`
`ML-DSA-87 verify`	`897477` cycles	`906874` cycles	`0.99`

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 (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: `8a19e9a`	Previous: `41da557`	Ratio
`ML-DSA-65 keypair`	`605825` cycles	`566673` cycles	`1.07`
`ML-DSA-65 sign`	`2034909` cycles	`1937222` cycles	`1.05`
`ML-DSA-65 verify`	`568560` cycles	`546998` cycles	`1.04`

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

mkannwischer

Please apply the same changes as requested in #905

This commit adds poly_use_hint to bench --components for benchmarking the performance impact of the changes to: - poly_use_hint_32 - poly_use_hint_88 Signed-off-by: willieyz <willie.zhao@chelpis.com>

In this PR, we replace the AVX2 intrinsics implementation of poly_use_hint_32 and poly_use_hint_88 with a x86_64 assembly version, this is part of the effort to enable HOL-Light proofs. Signed-off-by: willieyz <willie.zhao@chelpis.com>

This commit extract the decompose 32/88 and use_hint 32/88 as a macro. Signed-off-by: willieyz <willie.zhao@chelpis.com>

willieyz · 2026-02-12T06:43:20Z

Please apply the same changes as requested in #905

Hello, @mkannwischer , I had apply same changes requested in #905, including:

Remove all usage # for comment, use // and /*...*/ instead
Remove all vzeroupper
Use 32-bit constant instead of 64 bit
Extract the decompose32/88 and use_hint32/88 macros (referencing the AArch64 versions), and add brief comments in the same style.

Thank you for your help!

willieyz force-pushed the eliminate-use_hint_32_88-intrinsics branch 9 times, most recently from 1ea9d5f to 8a19e9a Compare February 5, 2026 06:05

willieyz marked this pull request as ready for review February 5, 2026 06:39

willieyz requested a review from a team as a code owner February 5, 2026 06:39

willieyz added the benchmark label Feb 5, 2026

willieyz marked this pull request as draft February 5, 2026 07:19

github-actions bot reviewed Feb 5, 2026

View reviewed changes

oqs-bot reviewed Feb 5, 2026

View reviewed changes

github-actions bot reviewed Feb 5, 2026

View reviewed changes

oqs-bot reviewed Feb 5, 2026

View reviewed changes

github-actions bot reviewed Feb 5, 2026

View reviewed changes

willieyz marked this pull request as ready for review February 5, 2026 07:42

mkannwischer requested changes Feb 10, 2026

View reviewed changes

mkannwischer marked this pull request as draft February 10, 2026 02:46

willieyz force-pushed the eliminate-use_hint_32_88-intrinsics branch 15 times, most recently from 18a3b4d to 32689ac Compare February 12, 2026 06:23

willieyz added 2 commits February 12, 2026 14:25

Add components benchmark for poly_use_hint_32 and poly_use_hint_88

9613da2

This commit adds poly_use_hint to bench --components for benchmarking the performance impact of the changes to: - poly_use_hint_32 - poly_use_hint_88 Signed-off-by: willieyz <willie.zhao@chelpis.com>

willieyz force-pushed the eliminate-use_hint_32_88-intrinsics branch from 32689ac to 81d5192 Compare February 12, 2026 06:26

Extract Macro: decompose32/88 and use_hint32/88

377fdc8

This commit extract the decompose 32/88 and use_hint 32/88 as a macro. Signed-off-by: willieyz <willie.zhao@chelpis.com>

willieyz force-pushed the eliminate-use_hint_32_88-intrinsics branch from 81d5192 to 377fdc8 Compare February 12, 2026 06:26

willieyz marked this pull request as ready for review February 12, 2026 06:43

Conversation

willieyz commented Feb 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

oqs-bot commented Feb 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

CBMC Results (ML-DSA-87)

Uh oh!

oqs-bot commented Feb 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

CBMC Results (ML-DSA-44)

Uh oh!

oqs-bot commented Feb 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

CBMC Results (ML-DSA-65)

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

Mac Mini (M1, 2020) benchmarks (opt)

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Intel Xeon 4th gen (c7i)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

AMD EPYC 3rd gen (c6a)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Intel Xeon 3rd gen (c6i)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton4

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

AMD EPYC 4th gen (c7a)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton3

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton4 (no-opt)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

willieyz commented Feb 3, 2026 •

edited

Loading

oqs-bot commented Feb 3, 2026 •

edited

Loading

oqs-bot commented Feb 3, 2026 •

edited

Loading

oqs-bot commented Feb 3, 2026 •

edited

Loading