Skip to content

doc: zero-knowledge leaves - #619

Merged
tcoratger merged 1 commit into
riscv-explorationfrom
zk-stack/1-spec
Oct 13, 2026
Merged

tcoratger merged 1 commit into
riscv-explorationfrom
zk-stack/1-spec

Conversation

@tcoratger

@tcoratger tcoratger commented Oct 11, 2026 •

Copy link
Copy Markdown
Collaborator

Stack: #619 spec → #620 transcript → #621 pcs → #622 outer proof → #623 ZK leaves → #624 recursion. Replaces #532.

Part 1 of 6 of the zero-knowledge stack, which rebuilds #532 by @kevaundray with the hiding fixed.

The spec comes first, so the argument can be reviewed before the code.

What

  • Annex B, the hiding commitment. Every level-0 row is padded past its power of two. The stack ends with an aligned group of four uniform rows.
  • Annex F, zero knowledge (new). The full construction: one-time-pad keys, the hidden final clock, the record, the deferred claims, the outer Spartan, the key commitment, soundness, the zero-knowledge theorem, and recursion.

The fix over #532

Lanes are words of K, but the fold weights are in E, which is three-dimensional over K.

One uniform lane masks each folded coordinate only along a line.

A revealed value with coefficients in K then shows two K-coordinates of the witness: a level-0 corrected value, or any opened symbol of level 1.

Four lanes in one aligned group span E over K (Lemma pcs-zk-group), so the folded witness is uniform and VEIL's lemma applies as stated.

Review guide

  • Lemma pcs-zk-group and Theorem pcs-zk in Annex B.
  • The soundness ledger in Annex F: the second list factor, paid by 12 grinding bits.
  • Theorem zk in Annex F.

The PDF builds with no undefined reference.

Co-authored-by: Kevaundray Wedderburn kevtheappdev@gmail.com

🤖 Generated with Claude Code

@github-actions

github-actions Bot commented Oct 11, 2026 •

Copy link
Copy Markdown

Benchmarks: base against this PR, on one runner

c89680c merged into its base, against the base d0b0f82: each benchmark run in turns on one runner, base and PR 5 times each. A size is shown when it changed; a time or a peak memory when it moved the same way in every round and its median by at least 1% (the change is the median ratio, with the rounds' range).

Threads shows the named configuration; default means no thread count is encoded in the benchmark ID.

BLAKE2s

benchmark threads runner measure base this PR change
blake2s-batch 16 x86-64 Time per operation 1.12 ns 1.04 ns -7.30% (-14.39% to -0.91%)

Fibonacci

Prover stages
benchmark threads runner base this PR change
fibonacci-asm-2000000 16 x86-64 529.02 ms 526.87 ms -1.52% (-5.98% to +0.54%)
 ↳ build-witness 41.43 ms 40.54 ms -2.15% (-3.31% to -0.38%)
 ↳ commit 74.55 ms 70.21 ms -5.18% (-8.21% to -4.53%)
 ↳ execute-program 72.98 ms 75.93 ms +2.47% (-2.16% to +4.83%)
 ↳ flock-reductions 144.35 ms 143.27 ms -4.04% (-7.99% to +0.18%)
 ↳ pcs-open 143.03 ms 145.29 ms +3.60% (-5.97% to +6.52%)
 ↳ prove-bus 37.76 ms 37.18 ms -4.37% (-9.60% to +4.90%)
 ↳ prove-constraints 15.47 ms 15.42 ms -0.88% (-7.53% to +2.97%)

leanXMSS

benchmark threads runner measure base this PR change
aggregate-leanxmss-100-4to1-first 1 x86-64 Verifying time 4.61 ms 4.28 ms -3.91% (-10.15% to -1.10%)
Prover stages
benchmark threads runner base this PR change
aggregate-leanxmss-100-2to1-first 8 arm64 156.85 ms 156.57 ms -0.22% (-0.62% to +0.34%)
 ↳ build-circuit 10.20 ms 10.23 ms +0.46% (-1.18% to +0.54%)
 ↳ prove-recursion 134.91 ms 134.71 ms -0.11% (-0.30% to +0.38%)
 ↳ reduce-claims 4.35 ms 4.13 ms -5.04% (-7.29% to -1.38%)
 ↳ reduce-in-rows 1.44 ms 1.41 ms -1.60% (-3.58% to +2.81%)
 ↳ verify 5.89 ms 5.87 ms -0.18% (-1.65% to +0.61%)
aggregate-leanxmss-100-2to1-first 1 x86-64 575.22 ms 577.02 ms +0.33% (-0.44% to +0.88%)
 ↳ build-circuit 14.61 ms 15.07 ms +2.14% (-0.13% to +6.68%)
 ↳ prove-recursion 534.09 ms 534.64 ms +0.27% (-0.49% to +0.71%)
 ↳ reduce-claims 18.53 ms 18.70 ms +1.63% (+0.34% to +2.67%)
 ↳ reduce-in-rows 1.75 ms 1.85 ms +4.86% (-0.02% to +12.36%)
 ↳ verify 6.67 ms 6.69 ms -0.55% (-0.93% to +1.77%)
aggregate-leanxmss-100-2to1-node 4 arm64 283.39 ms 283.29 ms +0.04% (-0.37% to +0.66%)
 ↳ build-circuit 11.58 ms 11.57 ms -0.01% (-2.04% to +8.25%)
 ↳ prove-recursion 254.82 ms 254.92 ms +0.08% (-0.29% to +0.80%)
 ↳ reduce-claims 10.59 ms 10.44 ms -1.39% (-2.04% to -0.10%)
 ↳ reduce-in-rows 1.50 ms 1.51 ms +1.05% (-3.47% to +6.02%)
aggregate-leanxmss-100-2to1-node 8 x86-64 123.49 ms 125.15 ms +0.89% (+0.05% to +2.71%)
 ↳ build-circuit 15.46 ms 16.05 ms +2.06% (+0.01% to +15.91%)
 ↳ prove-recursion 91.36 ms 91.95 ms +0.51% (+0.01% to +2.19%)
 ↳ reduce-claims 9.56 ms 9.82 ms +0.15% (-0.86% to +2.74%)
 ↳ reduce-in-rows 1.95 ms 2.00 ms +4.80% (-6.62% to +6.54%)
aggregate-leanxmss-100-4to1-first 8 arm64 300.58 ms 300.28 ms -0.37% (-0.88% to +0.20%)
 ↳ build-circuit 21.02 ms 20.90 ms -1.16% (-2.56% to +0.58%)
 ↳ prove-recursion 260.08 ms 259.85 ms -0.39% (-0.80% to +0.15%)
 ↳ reduce-claims 5.07 ms 5.17 ms +1.95% (-2.00% to +2.90%)
 ↳ reduce-in-rows 2.83 ms 2.75 ms -3.02% (-4.13% to -1.16%)
 ↳ verify 11.55 ms 11.53 ms -0.18% (-2.29% to +0.49%)
aggregate-leanxmss-100-4to1-first 1 x86-64 1.13 s 1.14 s -0.06% (-0.32% to +0.68%)
 ↳ build-circuit 32.58 ms 33.15 ms +1.54% (+0.34% to +3.54%)
 ↳ prove-recursion 1.06 s 1.06 s -0.03% (-0.45% to +0.70%)
 ↳ reduce-claims 26.29 ms 26.21 ms -0.20% (-1.56% to +1.77%)
 ↳ reduce-in-rows 3.69 ms 3.73 ms +0.16% (-3.14% to +2.98%)
 ↳ verify 12.30 ms 12.28 ms -0.15% (-0.24% to +0.33%)
aggregate-leanxmss-100-4to1-first 8 x86-64 218.12 ms 217.28 ms +0.30% (-1.47% to +1.92%)
 ↳ build-circuit 31.35 ms 31.38 ms +0.09% (-5.21% to +1.58%)
 ↳ prove-recursion 161.96 ms 162.03 ms +0.07% (-1.13% to +1.35%)
 ↳ reduce-claims 7.11 ms 7.80 ms +8.18% (+6.26% to +21.69%)
 ↳ reduce-in-rows 3.80 ms 3.74 ms -0.32% (-6.73% to +2.42%)
 ↳ verify 12.28 ms 12.24 ms -0.28% (-1.95% to +1.08%)
aggregate-leanxmss-100-4to1-node 1 arm64 2.05 s 2.06 s +0.01% (-0.29% to +0.29%)
 ↳ build-circuit 29.41 ms 29.31 ms -0.50% (-1.17% to +0.33%)
 ↳ prove-recursion 1.95 s 1.95 s +0.00% (-0.33% to +0.27%)
 ↳ reduce-claims 55.73 ms 56.18 ms +0.77% (+0.49% to +1.40%)
 ↳ reduce-in-rows 2.91 ms 2.97 ms +1.92% (+0.05% to +3.58%)
leanxmss-100 16 x86-64 125.21 ms 121.19 ms -1.09% (-5.38% to +1.83%)
 ↳ build-witness 7.32 ms 7.11 ms -1.84% (-8.50% to +12.26%)
 ↳ commit 14.11 ms 13.51 ms -4.10% (-5.37% to +1.39%)
 ↳ execute-program 11.89 ms 11.96 ms +1.74% (-4.61% to +3.48%)
 ↳ flock-reductions 34.28 ms 33.22 ms -0.87% (-5.70% to +5.35%)
 ↳ pcs-open 41.45 ms 39.63 ms -2.24% (-7.81% to -0.88%)
 ↳ prove-bus 10.99 ms 10.79 ms +0.22% (-7.40% to +2.21%)
 ↳ prove-constraints 5.01 ms 4.92 ms +0.12% (-4.70% to +1.98%)
Every result

BLAKE2s

benchmark threads runner CPU measure base this PR change
hash-50000 16 arm64 Neoverse-V2 Proving time 529.52 ms 532.00 ms +0.80% (-2.05% to +1.39%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 343.19 ms 352.58 ms +3.00% (-4.68% to +8.39%)
hash-50000 16 arm64 Neoverse-V2 Verifying time 3.29 ms 3.29 ms -0.30% (-8.70% to +8.97%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.16 ms 3.15 ms +0.29% (-1.67% to +1.67%)
blake2s-batch 16 arm64 Neoverse-V2 Time per operation 2.91 ns 2.90 ns -0.31% (-0.82% to +0.69%)
blake2s-batch 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 1.12 ns 1.04 ns -7.30% (-14.39% to -0.91%)
hash-50000 16 arm64 Neoverse-V2 Proof size 322,698 B 322,698 B 0 B (+0.00%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 322,698 B 322,698 B 0 B (+0.00%)
hash-50000 16 arm64 Neoverse-V2 Peak memory 4982.52 MiB 4982.34 MiB -0.04% (-0.19% to +0.11%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 2019.75 MiB 2017.63 MiB -0.10% (-0.24% to +0.05%)
hash-50000 16 arm64 Neoverse-V2 Peak heap 4400.28 MiB 4400.35 MiB +0.00% (-0.00% to +0.01%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 1823.93 MiB 1823.99 MiB +0.00% (-0.00% to +0.01%)
hash-50000 16 arm64 Neoverse-V2 Allocations 16,662 16,662 +0.00% (-0.20% to +0.00%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 17,311 17,311 +0.00% (-0.02% to +0.02%)
Prover stages
benchmark threads runner CPU base this PR change
hash-50000 16 arm64 Neoverse-V2 529.52 ms 532.00 ms +0.80% (-2.05% to +1.39%)
 ↳ build-witness 20.66 ms 20.33 ms +0.02% (-3.32% to +8.04%)
 ↳ commit 82.69 ms 83.24 ms +1.75% (-4.04% to +5.58%)
 ↳ execute-program 24.28 ms 24.34 ms +0.54% (-4.31% to +6.52%)
 ↳ flock-reductions 172.14 ms 171.58 ms +0.18% (-0.56% to +3.39%)
 ↳ pcs-open 192.48 ms 190.08 ms -1.05% (-2.95% to +3.99%)
 ↳ prove-bus 30.57 ms 30.18 ms -0.98% (-2.87% to +0.43%)
 ↳ prove-constraints 7.31 ms 7.31 ms +0.05% (-4.50% to +2.17%)
hash-50000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 343.19 ms 352.58 ms +3.00% (-4.68% to +8.39%)
 ↳ build-witness 22.59 ms 23.62 ms +3.82% (-2.62% to +7.75%)
 ↳ commit 47.40 ms 50.11 ms +6.25% (-5.44% to +12.25%)
 ↳ execute-program 30.62 ms 29.42 ms -0.28% (-5.64% to +4.91%)
 ↳ flock-reductions 87.63 ms 90.46 ms +5.09% (-5.74% to +9.74%)
 ↳ pcs-open 125.52 ms 128.71 ms +2.63% (-4.55% to +8.04%)
 ↳ prove-bus 20.93 ms 21.74 ms +5.01% (-2.74% to +6.62%)
 ↳ prove-constraints 8.53 ms 8.88 ms +4.48% (-2.67% to +7.47%)

Fibonacci

benchmark threads runner CPU measure base this PR change
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Proving time 817.47 ms 818.52 ms +0.13% (-0.35% to +0.40%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 529.02 ms 526.87 ms -1.52% (-5.98% to +0.54%)
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Verifying time 3.23 ms 3.23 ms +0.02% (-0.60% to +0.81%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.26 ms 3.30 ms +0.87% (-0.95% to +1.18%)
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Proof size 364,138 B 364,138 B 0 B (+0.00%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 364,138 B 364,138 B 0 B (+0.00%)
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Peak memory 7452.69 MiB 7450.57 MiB -0.01% (-0.09% to +0.07%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 3253.25 MiB 3249.74 MiB -0.10% (-0.31% to -0.08%)
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Peak heap 7050.01 MiB 7050.00 MiB -0.00% (-0.00% to +0.00%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 2998.76 MiB 2998.71 MiB -0.00% (-0.00% to +0.00%)
fibonacci-asm-2000000 16 arm64 Neoverse-V2 Allocations 11,598 11,598 +0.00% (+0.00% to +0.00%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 12,235 12,235 +0.00% (-0.01% to +0.00%)
Prover stages
benchmark threads runner CPU base this PR change
fibonacci-asm-2000000 16 arm64 Neoverse-V2 817.47 ms 818.52 ms +0.13% (-0.35% to +0.40%)
 ↳ build-witness 29.33 ms 29.36 ms +0.40% (-1.33% to +0.99%)
 ↳ commit 126.23 ms 126.19 ms +0.02% (-0.50% to +0.76%)
 ↳ execute-program 63.22 ms 62.82 ms -3.27% (-4.93% to +5.26%)
 ↳ flock-reductions 294.26 ms 293.62 ms -0.39% (-0.46% to +1.74%)
 ↳ pcs-open 233.04 ms 233.68 ms +0.27% (-0.16% to +1.52%)
 ↳ prove-bus 59.66 ms 59.69 ms +0.18% (-0.05% to +1.02%)
 ↳ prove-constraints 10.85 ms 10.90 ms -0.08% (-8.18% to +0.41%)
fibonacci-asm-2000000 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 529.02 ms 526.87 ms -1.52% (-5.98% to +0.54%)
 ↳ build-witness 41.43 ms 40.54 ms -2.15% (-3.31% to -0.38%)
 ↳ commit 74.55 ms 70.21 ms -5.18% (-8.21% to -4.53%)
 ↳ execute-program 72.98 ms 75.93 ms +2.47% (-2.16% to +4.83%)
 ↳ flock-reductions 144.35 ms 143.27 ms -4.04% (-7.99% to +0.18%)
 ↳ pcs-open 143.03 ms 145.29 ms +3.60% (-5.97% to +6.52%)
 ↳ prove-bus 37.76 ms 37.18 ms -4.37% (-9.60% to +4.90%)
 ↳ prove-constraints 15.47 ms 15.42 ms -0.88% (-7.53% to +2.97%)

Field and transpose kernels

benchmark threads runner CPU measure base this PR change
f192-inv default arm64 Neoverse-V2 Time per operation 244.93 ns 245.04 ns +0.01% (-0.00% to +0.66%)
f192-inv default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 265.54 ns 265.53 ns -0.01% (-0.04% to +0.05%)
f192-mul-latency default arm64 Neoverse-V2 Time per operation 8.03 ns 8.02 ns +0.16% (-0.07% to +0.25%)
f192-mul-latency default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 7.57 ns 7.54 ns -0.15% (-1.01% to +0.36%)
f192-mul-throughput default arm64 Neoverse-V2 Time per operation 2.94 ns 2.94 ns -0.03% (-0.17% to +0.03%)
f192-mul-throughput default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 4.44 ns 4.44 ns -0.05% (-0.23% to +0.88%)
f192-mul4-latency default arm64 Neoverse-V2 Time per operation 13.06 ns 12.76 ns -0.67% (-3.07% to +3.26%)
f192-mul4-latency default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 10.10 ns 10.10 ns +0.00% (-0.74% to +0.09%)
f192-mul4-throughput default arm64 Neoverse-V2 Time per operation 10.76 ns 10.76 ns -0.05% (-0.07% to +0.15%)
f192-mul4-throughput default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 15.60 ns 15.61 ns +0.00% (-0.02% to +0.07%)
f192-square default arm64 Neoverse-V2 Time per operation 1.70 ns 1.70 ns +0.12% (+0.00% to +0.29%)
f192-square default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 3.32 ns 3.32 ns -0.06% (-0.30% to +0.30%)
f64-inv default arm64 Neoverse-V2 Time per operation 211.49 ns 211.45 ns -0.04% (-0.18% to +0.06%)
f64-inv default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 237.19 ns 237.25 ns +0.00% (-0.04% to +0.03%)
f64-mul default arm64 Neoverse-V2 Time per operation 0.56 ns 0.56 ns +0.00% (-0.18% to +0.00%)
f64-mul default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 0.86 ns 0.86 ns +0.00% (-0.12% to +0.00%)
f64-square default arm64 Neoverse-V2 Time per operation 0.55 ns 0.55 ns +0.00% (-0.91% to +0.18%)
f64-square default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 1.08 ns 1.08 ns +0.00% (-0.83% to +1.20%)
transpose-64bytes default arm64 Neoverse-V2 Time per operation 12.00 ns 12.00 ns -0.02% (-0.07% to +0.00%)
transpose-64bytes default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 0.84 ns 0.84 ns +0.00% (-0.84% to +0.72%)
transpose-64x64 default arm64 Neoverse-V2 Time per operation 96.38 ns 96.40 ns -0.01% (-0.08% to +0.09%)
transpose-64x64 default x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 73.18 ns 73.19 ns -0.02% (-0.21% to +0.24%)

Flock

benchmark threads runner CPU measure base this PR change
flock-alu-batch-262144 16 arm64 Neoverse-V2 Proving time 51.48 ms 51.01 ms -0.50% (-5.02% to +0.15%)
flock-alu-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 28.77 ms 29.21 ms +0.48% (-17.40% to +10.41%)
flock-div-batch-262144 16 arm64 Neoverse-V2 Proving time 365.72 ms 365.49 ms -0.14% (-0.30% to +0.81%)
flock-div-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 170.21 ms 170.08 ms -0.04% (-1.28% to +0.01%)
flock-hash-batch-262144 16 arm64 Neoverse-V2 Proving time 759.43 ms 761.54 ms +0.43% (-0.70% to +1.55%)
flock-hash-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 356.10 ms 355.50 ms -0.10% (-0.32% to -0.04%)
flock-ld-batch-262144 16 arm64 Neoverse-V2 Proving time 15.62 ms 15.61 ms -0.15% (-7.17% to +1.74%)
flock-ld-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 9.37 ms 9.40 ms -0.06% (-3.50% to +17.02%)
flock-load-batch-262144 16 arm64 Neoverse-V2 Proving time 49.81 ms 49.81 ms +0.13% (-6.23% to +0.47%)
flock-load-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 28.06 ms 28.08 ms +1.01% (-6.12% to +14.43%)
flock-mul-batch-262144 16 arm64 Neoverse-V2 Proving time 186.67 ms 186.59 ms -0.16% (-6.72% to +0.34%)
flock-mul-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 96.37 ms 89.81 ms -0.94% (-6.80% to -0.22%)
flock-mulh-batch-262144 16 arm64 Neoverse-V2 Proving time 357.36 ms 357.51 ms +0.07% (-0.23% to +0.44%)
flock-mulh-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 175.24 ms 168.35 ms -3.78% (-7.00% to +0.25%)
flock-sd-batch-262144 16 arm64 Neoverse-V2 Proving time 16.13 ms 16.13 ms -0.01% (-1.37% to +7.30%)
flock-sd-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 9.52 ms 9.61 ms -1.31% (-6.21% to +19.17%)
flock-shift-batch-262144 16 arm64 Neoverse-V2 Proving time 49.90 ms 50.01 ms +0.25% (+0.19% to +0.93%)
flock-shift-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 27.34 ms 27.89 ms -0.40% (-8.61% to +13.33%)
flock-store-batch-262144 16 arm64 Neoverse-V2 Proving time 49.40 ms 49.61 ms +0.76% (-1.29% to +1.15%)
flock-store-batch-262144 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 28.15 ms 28.02 ms +0.74% (-6.11% to +8.38%)

PCS

benchmark threads runner CPU measure base this PR change
pcs-commit-22 16 arm64 Neoverse-V2 Proving time 7.29 ms 7.25 ms -0.81% (-3.21% to +2.26%)
pcs-commit-22 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 5.41 ms 5.05 ms -6.08% (-13.02% to +14.03%)
pcs-open-22 16 arm64 Neoverse-V2 Proving time 21.08 ms 21.09 ms +0.03% (-1.53% to +2.81%)
pcs-open-22 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 15.12 ms 15.13 ms +0.03% (-6.17% to +1.98%)
ntt-forward-22 16 arm64 Neoverse-V2 Time per operation 3.63 ms 3.69 ms +0.91% (-0.07% to +2.56%)
ntt-forward-22 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Time per operation 3.02 ms 2.83 ms -6.20% (-16.33% to +0.36%)

leanSPHINCS

benchmark threads runner CPU measure base this PR change
leansphincs-26 16 arm64 Neoverse-V2 Proving time 181.40 ms 182.44 ms +0.57% (-0.20% to +1.82%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 128.70 ms 131.27 ms +2.66% (-6.09% to +4.98%)
leansphincs-26 16 arm64 Neoverse-V2 Verifying time 3.25 ms 3.25 ms +0.07% (-0.85% to +0.83%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.25 ms 3.26 ms -0.70% (-1.28% to +2.09%)
leansphincs-26 16 arm64 Neoverse-V2 Proof size 316,466 B 316,466 B 0 B (+0.00%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 316,466 B 316,466 B 0 B (+0.00%)
leansphincs-26 16 arm64 Neoverse-V2 Peak memory 1734.50 MiB 1727.03 MiB -0.45% (-0.53% to +0.89%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 707.08 MiB 709.02 MiB +0.24% (-0.10% to +0.63%)
leansphincs-26 16 arm64 Neoverse-V2 Peak heap 1395.19 MiB 1395.13 MiB -0.00% (-0.01% to +0.00%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 587.78 MiB 587.80 MiB +0.01% (+0.00% to +0.03%)
leansphincs-26 16 arm64 Neoverse-V2 Allocations 25,165 25,165 +0.00% (+0.00% to +0.00%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 25,864 25,864 +0.00% (-0.00% to +0.01%)
Prover stages
benchmark threads runner CPU base this PR change
leansphincs-26 16 arm64 Neoverse-V2 181.40 ms 182.44 ms +0.57% (-0.20% to +1.82%)
 ↳ build-witness 5.69 ms 5.71 ms +0.28% (-4.52% to +4.20%)
 ↳ commit 23.74 ms 23.86 ms -0.09% (-1.71% to +0.80%)
 ↳ execute-program 12.02 ms 12.17 ms +1.22% (-0.00% to +3.79%)
 ↳ flock-reductions 62.12 ms 62.31 ms +0.64% (-0.50% to +3.33%)
 ↳ pcs-open 58.19 ms 58.22 ms +0.04% (-0.64% to +2.02%)
 ↳ prove-bus 15.05 ms 15.07 ms +0.46% (-0.62% to +1.63%)
 ↳ prove-constraints 4.21 ms 4.22 ms +0.81% (-1.78% to +4.45%)
leansphincs-26 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 128.70 ms 131.27 ms +2.66% (-6.09% to +4.98%)
 ↳ build-witness 8.24 ms 8.22 ms +0.45% (-4.62% to +3.95%)
 ↳ commit 14.97 ms 14.94 ms +4.55% (-6.65% to +6.43%)
 ↳ execute-program 14.13 ms 14.19 ms +0.76% (-1.98% to +2.77%)
 ↳ flock-reductions 34.74 ms 34.74 ms +1.92% (-7.11% to +6.74%)
 ↳ pcs-open 40.30 ms 42.03 ms +4.29% (-6.92% to +6.23%)
 ↳ prove-bus 11.61 ms 11.48 ms +1.02% (-5.72% to +4.36%)
 ↳ prove-constraints 4.81 ms 4.94 ms +3.54% (-5.53% to +4.83%)

leanXMSS

benchmark threads runner CPU measure base this PR change
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Proving time 952.34 ms 953.24 ms +0.09% (-0.41% to +0.25%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Proving time 268.19 ms 267.86 ms +0.10% (-0.26% to +0.33%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Proving time 156.85 ms 156.57 ms -0.22% (-0.62% to +0.34%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Proving time 102.82 ms 102.94 ms +0.12% (-0.64% to +0.70%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 575.22 ms 577.02 ms +0.33% (-0.44% to +0.88%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 176.03 ms 176.36 ms +0.08% (-0.28% to +0.56%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 119.33 ms 119.58 ms -0.36% (-1.38% to +1.19%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 87.62 ms 87.19 ms -1.05% (-5.36% to +2.11%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Proving time 1.01 s 1.01 s -0.00% (-0.43% to +0.16%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Proving time 283.39 ms 283.29 ms +0.04% (-0.37% to +0.66%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Proving time 165.07 ms 165.33 ms +0.14% (-0.54% to +0.48%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Proving time 107.51 ms 107.52 ms +0.48% (-0.22% to +2.54%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 616.43 ms 615.92 ms -0.10% (-1.13% to +0.36%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 185.84 ms 186.69 ms +0.57% (-0.93% to +1.04%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 123.49 ms 125.15 ms +0.89% (+0.05% to +2.71%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 89.82 ms 89.72 ms -1.64% (-7.00% to +5.97%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Proving time 1.88 s 1.89 s +0.21% (-0.15% to +0.40%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Proving time 519.96 ms 519.55 ms -0.14% (-0.19% to +0.01%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Proving time 300.58 ms 300.28 ms -0.37% (-0.88% to +0.20%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Proving time 190.43 ms 190.81 ms +0.20% (-0.58% to +0.47%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 1.13 s 1.14 s -0.06% (-0.32% to +0.68%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 340.03 ms 334.34 ms -1.97% (-3.69% to +3.46%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 218.12 ms 217.28 ms +0.30% (-1.47% to +1.92%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 157.46 ms 159.44 ms +1.26% (-5.89% to +8.79%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Proving time 2.05 s 2.06 s +0.01% (-0.29% to +0.29%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Proving time 565.50 ms 564.11 ms -0.16% (-0.37% to +0.11%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Proving time 325.64 ms 324.33 ms -0.27% (-0.63% to -0.16%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Proving time 206.70 ms 206.61 ms +0.23% (-0.22% to +1.32%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 1.24 s 1.24 s +0.24% (-0.63% to +0.58%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 369.14 ms 367.75 ms -1.87% (-4.07% to +1.80%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 234.76 ms 235.66 ms +0.26% (-1.00% to +6.01%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 174.10 ms 167.73 ms -2.72% (-4.52% to +4.40%)
leanxmss-100 1 arm64 Neoverse-V2 Proving time 1.77 s 1.78 s -0.00% (-0.19% to +0.71%)
leanxmss-100 4 arm64 Neoverse-V2 Proving time 472.38 ms 474.90 ms +0.53% (+0.01% to +1.41%)
leanxmss-100 8 arm64 Neoverse-V2 Proving time 264.35 ms 264.49 ms +0.08% (-0.21% to +0.38%)
leanxmss-100 16 arm64 Neoverse-V2 Proving time 162.03 ms 161.49 ms -0.50% (-5.04% to +0.24%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 1.02 s 1.02 s +0.30% (-0.04% to +0.60%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 297.99 ms 298.54 ms +0.19% (-0.15% to +0.42%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 180.16 ms 180.60 ms +0.46% (-7.00% to +2.99%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proving time 125.21 ms 121.19 ms -1.09% (-5.38% to +1.83%)
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Verifying time 4.00 ms 3.99 ms -0.49% (-1.00% to +0.27%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Verifying time 2.83 ms 2.85 ms +0.56% (-0.15% to +7.41%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Verifying time 2.72 ms 2.72 ms +0.06% (-1.51% to +0.88%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Verifying time 2.77 ms 2.77 ms -0.11% (-4.41% to +1.25%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.77 ms 3.76 ms +0.21% (-1.68% to +3.35%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 2.84 ms 2.80 ms -0.97% (-2.57% to +1.38%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 2.94 ms 2.92 ms +0.42% (-0.91% to +4.83%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 2.97 ms 2.98 ms +1.52% (-4.44% to +2.34%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Verifying time 6.68 ms 6.66 ms -0.04% (-3.39% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Verifying time 3.58 ms 3.60 ms +0.57% (-0.84% to +2.18%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Verifying time 3.16 ms 3.16 ms -0.07% (-1.76% to +0.66%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Verifying time 3.06 ms 3.05 ms -0.28% (-0.48% to +0.02%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 7.21 ms 7.32 ms +2.40% (-0.74% to +4.77%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.75 ms 3.74 ms +0.40% (-1.86% to +1.41%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.42 ms 3.47 ms +1.86% (-1.58% to +3.43%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.07 ms 3.10 ms +1.12% (-0.27% to +2.29%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Verifying time 4.85 ms 4.85 ms +0.34% (-0.64% to +0.50%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Verifying time 3.18 ms 3.18 ms +0.31% (-0.75% to +0.87%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Verifying time 3.02 ms 3.01 ms -0.25% (-2.52% to +2.34%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Verifying time 3.01 ms 3.00 ms -0.36% (-1.33% to +0.37%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 4.61 ms 4.28 ms -3.91% (-10.15% to -1.10%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.20 ms 3.27 ms +1.36% (-0.27% to +6.04%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.05 ms 3.06 ms +0.33% (-3.05% to +2.89%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.05 ms 3.05 ms +0.33% (-3.50% to +5.18%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Verifying time 10.18 ms 10.20 ms +0.78% (-2.44% to +2.99%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Verifying time 4.56 ms 4.59 ms -0.31% (-0.47% to +2.04%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Verifying time 3.82 ms 3.84 ms +0.60% (-0.71% to +1.63%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Verifying time 3.49 ms 3.48 ms -0.36% (-1.63% to +1.47%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 11.71 ms 11.58 ms -1.07% (-5.62% to +3.23%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 4.79 ms 4.81 ms -0.32% (-1.38% to +2.64%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 4.06 ms 4.07 ms -0.51% (-2.73% to +1.69%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.55 ms 3.55 ms -0.40% (-1.25% to +2.84%)
leanxmss-100 1 arm64 Neoverse-V2 Verifying time 3.07 ms 3.08 ms +0.56% (-1.50% to +7.52%)
leanxmss-100 4 arm64 Neoverse-V2 Verifying time 2.99 ms 2.99 ms +0.17% (-1.15% to +1.12%)
leanxmss-100 8 arm64 Neoverse-V2 Verifying time 3.06 ms 3.04 ms -0.48% (-0.93% to +0.14%)
leanxmss-100 16 arm64 Neoverse-V2 Verifying time 3.23 ms 3.27 ms +0.72% (-0.74% to +1.20%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.01 ms 3.02 ms +0.05% (-0.25% to +0.68%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.01 ms 3.01 ms -0.34% (-0.78% to +2.36%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.12 ms 3.20 ms +2.65% (-0.94% to +9.80%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Verifying time 3.23 ms 3.22 ms +0.37% (-0.61% to +0.57%)
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,731 B 256,731 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 256,379 B 256,379 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,703 B 280,703 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,863 B 280,863 B 0 B (+0.00%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 280,863 B 280,863 B 0 B (+0.00%)
leanxmss-100 1 arm64 Neoverse-V2 Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 4 arm64 Neoverse-V2 Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 8 arm64 Neoverse-V2 Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 16 arm64 Neoverse-V2 Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 303,762 B 303,762 B 0 B (+0.00%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Proof size 303,762 B 303,762 B 0 B (+0.00%)
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Peak memory 1586.50 MiB 1586.48 MiB -0.00% (-0.01% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Peak memory 1604.62 MiB 1606.17 MiB +0.12% (-0.05% to +0.25%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Peak memory 1636.55 MiB 1637.61 MiB +0.12% (-0.19% to +0.23%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Peak memory 1718.57 MiB 1721.22 MiB +0.15% (-0.16% to +0.68%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 774.58 MiB 774.59 MiB +0.00% (-0.26% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 805.14 MiB 805.40 MiB +0.03% (-0.66% to +1.22%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 830.57 MiB 833.30 MiB +0.04% (-0.56% to +0.60%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 874.94 MiB 874.60 MiB +0.06% (-0.62% to +0.39%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Peak memory 1586.62 MiB 1586.61 MiB -0.00% (-0.01% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Peak memory 1606.61 MiB 1608.01 MiB +0.09% (-0.07% to +0.25%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Peak memory 1639.17 MiB 1639.89 MiB +0.16% (-0.35% to +0.23%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Peak memory 1740.02 MiB 1741.27 MiB +0.14% (-0.22% to +0.88%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 774.58 MiB 774.59 MiB +0.00% (-0.26% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 810.28 MiB 811.56 MiB +0.16% (-0.59% to +0.88%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 847.51 MiB 850.21 MiB +0.35% (-0.90% to +0.51%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 914.40 MiB 912.29 MiB -0.19% (-0.95% to +0.50%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Peak memory 1780.77 MiB 1780.61 MiB -0.01% (-0.10% to +0.02%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Peak memory 1800.07 MiB 1800.92 MiB +0.07% (-0.08% to +0.12%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Peak memory 1829.71 MiB 1832.32 MiB +0.03% (-0.10% to +0.18%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Peak memory 1918.46 MiB 1918.32 MiB +0.04% (-0.87% to +0.56%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 960.62 MiB 960.59 MiB -0.00% (-0.41% to +0.20%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 999.73 MiB 998.19 MiB -0.15% (-0.50% to +0.54%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 1023.54 MiB 1026.58 MiB +0.30% (+0.03% to +0.53%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 1073.94 MiB 1073.09 MiB -0.37% (-1.35% to +0.28%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Peak memory 1781.23 MiB 1785.05 MiB +0.21% (+0.01% to +0.24%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Peak memory 1800.95 MiB 1802.51 MiB +0.10% (-0.04% to +0.13%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Peak memory 1838.62 MiB 1838.84 MiB -0.03% (-0.28% to +0.34%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Peak memory 1935.28 MiB 1939.53 MiB -0.27% (-0.81% to +0.46%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 986.59 MiB 986.59 MiB -0.00% (-1.01% to +0.00%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 1011.34 MiB 1008.47 MiB -0.28% (-0.52% to +0.04%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 1046.57 MiB 1044.28 MiB +0.05% (-0.92% to +0.79%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 1108.31 MiB 1106.12 MiB -0.75% (-1.70% to +1.47%)
leanxmss-100 1 arm64 Neoverse-V2 Peak memory 1406.52 MiB 1406.60 MiB +0.02% (-0.01% to +0.13%)
leanxmss-100 4 arm64 Neoverse-V2 Peak memory 1429.58 MiB 1430.90 MiB +0.11% (-0.17% to +0.17%)
leanxmss-100 8 arm64 Neoverse-V2 Peak memory 1460.96 MiB 1463.70 MiB +0.08% (+0.01% to +0.34%)
leanxmss-100 16 arm64 Neoverse-V2 Peak memory 1531.19 MiB 1526.12 MiB -0.18% (-0.98% to +0.08%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 586.58 MiB 586.58 MiB +0.04% (-0.72% to +0.30%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 608.59 MiB 608.14 MiB -0.09% (-0.97% to +0.87%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 626.67 MiB 628.66 MiB +0.14% (-0.11% to +0.49%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak memory 653.94 MiB 650.16 MiB -0.56% (-0.71% to -0.34%)
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Peak heap 602.79 MiB 602.79 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Peak heap 602.85 MiB 602.86 MiB +0.00% (-0.01% to +0.01%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Peak heap 602.74 MiB 602.80 MiB +0.01% (-0.00% to +0.03%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Peak heap 602.93 MiB 602.91 MiB +0.01% (-0.01% to +0.02%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.27 MiB 265.27 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.33 MiB 265.28 MiB -0.02% (-0.04% to +0.00%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.33 MiB 265.34 MiB +0.00% (-0.03% to +0.02%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.45 MiB 265.39 MiB -0.04% (-0.11% to +0.04%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Peak heap 602.50 MiB 602.50 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Peak heap 602.53 MiB 602.51 MiB -0.00% (-0.01% to +0.00%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Peak heap 602.51 MiB 602.51 MiB -0.00% (-0.01% to +0.02%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Peak heap 602.69 MiB 602.58 MiB -0.02% (-0.04% to +0.03%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 264.98 MiB 264.98 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.04 MiB 265.09 MiB +0.03% (-0.04% to +0.06%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.06 MiB 264.98 MiB -0.03% (-0.07% to +0.07%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 265.13 MiB 265.14 MiB +0.01% (-0.09% to +0.05%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Peak heap 1205.49 MiB 1205.49 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Peak heap 1205.51 MiB 1205.51 MiB +0.00% (-0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Peak heap 1205.48 MiB 1205.53 MiB +0.00% (-0.01% to +0.02%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Peak heap 1205.60 MiB 1205.66 MiB +0.00% (-0.00% to +0.01%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.47 MiB 530.47 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.51 MiB 530.48 MiB -0.01% (-0.02% to +0.01%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.42 MiB 530.37 MiB -0.01% (-0.02% to +0.01%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.50 MiB 530.40 MiB -0.00% (-0.07% to +0.01%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Peak heap 1205.02 MiB 1205.02 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Peak heap 1205.08 MiB 1205.05 MiB +0.00% (-0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Peak heap 1205.03 MiB 1204.99 MiB -0.01% (-0.01% to +0.00%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Peak heap 1205.20 MiB 1205.17 MiB -0.00% (-0.02% to +0.01%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 529.99 MiB 529.99 MiB +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.01 MiB 529.99 MiB -0.00% (-0.02% to +0.01%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 529.88 MiB 529.89 MiB +0.00% (-0.01% to +0.01%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 530.00 MiB 529.96 MiB -0.00% (-0.04% to +0.06%)
leanxmss-100 1 arm64 Neoverse-V2 Peak heap 1200.93 MiB 1200.93 MiB +0.00% (+0.00% to +0.00%)
leanxmss-100 4 arm64 Neoverse-V2 Peak heap 1201.00 MiB 1200.93 MiB -0.00% (-0.01% to +0.00%)
leanxmss-100 8 arm64 Neoverse-V2 Peak heap 1201.00 MiB 1200.99 MiB +0.00% (-0.00% to +0.00%)
leanxmss-100 16 arm64 Neoverse-V2 Peak heap 1201.27 MiB 1201.19 MiB -0.00% (-0.02% to +0.00%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 504.34 MiB 504.34 MiB +0.00% (+0.00% to +0.00%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 504.42 MiB 504.44 MiB +0.00% (-0.01% to +0.02%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 504.47 MiB 504.47 MiB +0.00% (-0.02% to +0.03%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Peak heap 504.63 MiB 504.66 MiB +0.00% (-0.00% to +0.03%)
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 Allocations 16,729 16,729 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 Allocations 16,855 16,855 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 Allocations 16,999 16,999 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 Allocations 17,287 17,287 +0.00% (+0.00% to +0.04%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 16,831 16,831 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 16,960 16,960 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 17,108 17,108 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 17,404 17,404 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 Allocations 20,453 20,453 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 Allocations 20,579 20,579 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 Allocations 20,723 20,723 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 Allocations 21,011 21,011 +0.00% (-0.11% to +0.00%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 20,547 20,547 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 20,676 20,676 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 20,824 20,824 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 21,120 21,120 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 Allocations 28,645 28,645 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 Allocations 28,783 28,783 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 Allocations 28,967 28,967 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 Allocations 29,287 29,287 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 28,791 28,791 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 28,932 28,932 +0.00% (-0.03% to +0.01%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 29,120 29,120 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 29,448 29,448 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 Allocations 35,453 35,453 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 Allocations 35,591 35,591 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 Allocations 35,775 35,775 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 Allocations 36,095 36,095 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 35,599 35,599 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 35,740 35,740 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 35,928 35,928 +0.00% (+0.00% to +0.00%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 36,256 36,256 +0.00% (+0.00% to +0.00%)
leanxmss-100 1 arm64 Neoverse-V2 Allocations 24,801 24,801 +0.00% (+0.00% to +0.00%)
leanxmss-100 4 arm64 Neoverse-V2 Allocations 25,019 25,019 +0.00% (+0.00% to +0.00%)
leanxmss-100 8 arm64 Neoverse-V2 Allocations 25,255 25,255 +0.00% (+0.00% to +0.00%)
leanxmss-100 16 arm64 Neoverse-V2 Allocations 25,727 25,727 +0.00% (-0.06% to +0.09%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 25,319 25,319 +0.00% (+0.00% to +0.00%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 25,574 25,574 +0.00% (-0.00% to +0.00%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 25,858 25,857 -0.00% (-0.00% to +0.00%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N Allocations 26,426 26,426 +0.00% (+0.00% to +0.00%)
Prover stages
benchmark threads runner CPU base this PR change
aggregate-leanxmss-100-2to1-first 1 arm64 Neoverse-V2 952.34 ms 953.24 ms +0.09% (-0.41% to +0.25%)
 ↳ build-circuit 12.50 ms 12.46 ms +0.17% (-1.38% to +0.23%)
 ↳ prove-recursion 917.33 ms 917.98 ms +0.09% (-0.38% to +0.22%)
 ↳ reduce-claims 15.44 ms 15.38 ms +0.39% (-1.25% to +1.91%)
 ↳ reduce-in-rows 1.39 ms 1.41 ms +0.99% (-2.89% to +3.99%)
 ↳ verify 5.86 ms 5.84 ms -0.17% (-1.04% to +0.20%)
aggregate-leanxmss-100-2to1-first 4 arm64 Neoverse-V2 268.19 ms 267.86 ms +0.10% (-0.26% to +0.33%)
 ↳ build-circuit 10.54 ms 10.70 ms -0.08% (-1.23% to +2.13%)
 ↳ prove-recursion 244.88 ms 244.49 ms +0.05% (-0.16% to +0.20%)
 ↳ reduce-claims 5.30 ms 5.40 ms +1.89% (-7.54% to +3.01%)
 ↳ reduce-in-rows 1.46 ms 1.45 ms -0.33% (-3.85% to +6.71%)
 ↳ verify 5.72 ms 5.75 ms -0.12% (-0.54% to +1.65%)
aggregate-leanxmss-100-2to1-first 8 arm64 Neoverse-V2 156.85 ms 156.57 ms -0.22% (-0.62% to +0.34%)
 ↳ build-circuit 10.20 ms 10.23 ms +0.46% (-1.18% to +0.54%)
 ↳ prove-recursion 134.91 ms 134.71 ms -0.11% (-0.30% to +0.38%)
 ↳ reduce-claims 4.35 ms 4.13 ms -5.04% (-7.29% to -1.38%)
 ↳ reduce-in-rows 1.44 ms 1.41 ms -1.60% (-3.58% to +2.81%)
 ↳ verify 5.89 ms 5.87 ms -0.18% (-1.65% to +0.61%)
aggregate-leanxmss-100-2to1-first 16 arm64 Neoverse-V2 102.82 ms 102.94 ms +0.12% (-0.64% to +0.70%)
 ↳ build-circuit 10.34 ms 10.31 ms -0.07% (-1.69% to +0.50%)
 ↳ prove-recursion 80.81 ms 81.02 ms +0.28% (-0.49% to +0.82%)
 ↳ reduce-claims 3.95 ms 3.83 ms -2.57% (-8.52% to +6.62%)
 ↳ reduce-in-rows 1.41 ms 1.43 ms +1.55% (-5.07% to +6.91%)
 ↳ verify 6.27 ms 6.23 ms -0.31% (-0.99% to +0.03%)
aggregate-leanxmss-100-2to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N 575.22 ms 577.02 ms +0.33% (-0.44% to +0.88%)
 ↳ build-circuit 14.61 ms 15.07 ms +2.14% (-0.13% to +6.68%)
 ↳ prove-recursion 534.09 ms 534.64 ms +0.27% (-0.49% to +0.71%)
 ↳ reduce-claims 18.53 ms 18.70 ms +1.63% (+0.34% to +2.67%)
 ↳ reduce-in-rows 1.75 ms 1.85 ms +4.86% (-0.02% to +12.36%)
 ↳ verify 6.67 ms 6.69 ms -0.55% (-0.93% to +1.77%)
aggregate-leanxmss-100-2to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N 176.03 ms 176.36 ms +0.08% (-0.28% to +0.56%)
 ↳ build-circuit 14.13 ms 14.15 ms +0.17% (-3.51% to +3.60%)
 ↳ prove-recursion 147.01 ms 147.19 ms +0.14% (-0.38% to +0.37%)
 ↳ reduce-claims 6.82 ms 7.15 ms -7.38% (-9.19% to +23.13%)
 ↳ reduce-in-rows 1.88 ms 1.79 ms -3.13% (-6.71% to +4.44%)
 ↳ verify 6.25 ms 6.25 ms -0.13% (-0.28% to +0.32%)
aggregate-leanxmss-100-2to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N 119.33 ms 119.58 ms -0.36% (-1.38% to +1.19%)
 ↳ build-circuit 14.68 ms 14.75 ms -0.34% (-2.24% to +4.12%)
 ↳ prove-recursion 89.12 ms 89.23 ms +0.60% (-0.47% to +0.78%)
 ↳ reduce-claims 6.52 ms 6.18 ms -14.09% (-22.24% to +8.14%)
 ↳ reduce-in-rows 1.94 ms 1.91 ms +3.46% (-17.20% to +10.53%)
 ↳ verify 6.76 ms 6.70 ms -0.57% (-2.68% to +2.23%)
aggregate-leanxmss-100-2to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 87.62 ms 87.19 ms -1.05% (-5.36% to +2.11%)
 ↳ build-circuit 13.97 ms 14.21 ms +1.75% (-2.58% to +4.21%)
 ↳ prove-recursion 58.06 ms 58.13 ms -2.03% (-4.64% to +3.85%)
 ↳ reduce-claims 7.01 ms 6.76 ms -7.28% (-22.31% to +5.28%)
 ↳ reduce-in-rows 1.81 ms 1.78 ms -1.55% (-8.45% to +1.74%)
 ↳ verify 6.89 ms 6.86 ms +0.72% (-1.49% to +3.37%)
aggregate-leanxmss-100-2to1-node 1 arm64 Neoverse-V2 1.01 s 1.01 s -0.00% (-0.43% to +0.16%)
 ↳ build-circuit 12.21 ms 12.38 ms +0.26% (-0.27% to +2.01%)
 ↳ prove-recursion 963.02 ms 963.00 ms +0.03% (-0.46% to +0.18%)
 ↳ reduce-claims 30.57 ms 30.59 ms -0.22% (-0.71% to +0.23%)
 ↳ reduce-in-rows 1.49 ms 1.47 ms -1.34% (-2.35% to +1.88%)
aggregate-leanxmss-100-2to1-node 4 arm64 Neoverse-V2 283.39 ms 283.29 ms +0.04% (-0.37% to +0.66%)
 ↳ build-circuit 11.58 ms 11.57 ms -0.01% (-2.04% to +8.25%)
 ↳ prove-recursion 254.82 ms 254.92 ms +0.08% (-0.29% to +0.80%)
 ↳ reduce-claims 10.59 ms 10.44 ms -1.39% (-2.04% to -0.10%)
 ↳ reduce-in-rows 1.50 ms 1.51 ms +1.05% (-3.47% to +6.02%)
aggregate-leanxmss-100-2to1-node 8 arm64 Neoverse-V2 165.07 ms 165.33 ms +0.14% (-0.54% to +0.48%)
 ↳ build-circuit 11.30 ms 11.36 ms +0.31% (-1.93% to +3.05%)
 ↳ prove-recursion 139.99 ms 140.19 ms +0.17% (-0.46% to +0.26%)
 ↳ reduce-claims 7.58 ms 7.62 ms +0.57% (-0.75% to +6.11%)
 ↳ reduce-in-rows 1.47 ms 1.51 ms +2.10% (-8.72% to +5.44%)
aggregate-leanxmss-100-2to1-node 16 arm64 Neoverse-V2 107.51 ms 107.52 ms +0.48% (-0.22% to +2.54%)
 ↳ build-circuit 11.47 ms 11.42 ms -0.48% (-1.91% to -0.14%)
 ↳ prove-recursion 83.38 ms 83.52 ms +0.74% (-0.24% to +3.99%)
 ↳ reduce-claims 6.53 ms 6.46 ms -1.02% (-4.17% to +1.61%)
 ↳ reduce-in-rows 1.49 ms 1.47 ms -1.50% (-2.95% to +1.82%)
aggregate-leanxmss-100-2to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N 616.43 ms 615.92 ms -0.10% (-1.13% to +0.36%)
 ↳ build-circuit 16.54 ms 15.88 ms -3.98% (-7.75% to +2.83%)
 ↳ prove-recursion 557.07 ms 556.52 ms -0.23% (-0.71% to +0.61%)
 ↳ reduce-claims 34.72 ms 34.37 ms -0.19% (-4.47% to +0.84%)
 ↳ reduce-in-rows 1.86 ms 1.83 ms -1.76% (-5.52% to +0.40%)
aggregate-leanxmss-100-2to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N 185.84 ms 186.69 ms +0.57% (-0.93% to +1.04%)
 ↳ build-circuit 15.06 ms 15.04 ms -1.84% (-2.74% to +3.89%)
 ↳ prove-recursion 151.83 ms 152.43 ms +0.46% (-0.12% to +0.69%)
 ↳ reduce-claims 11.80 ms 12.08 ms +2.89% (-13.04% to +18.68%)
 ↳ reduce-in-rows 1.82 ms 1.85 ms +1.34% (-1.43% to +6.15%)
aggregate-leanxmss-100-2to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N 123.49 ms 125.15 ms +0.89% (+0.05% to +2.71%)
 ↳ build-circuit 15.46 ms 16.05 ms +2.06% (+0.01% to +15.91%)
 ↳ prove-recursion 91.36 ms 91.95 ms +0.51% (+0.01% to +2.19%)
 ↳ reduce-claims 9.56 ms 9.82 ms +0.15% (-0.86% to +2.74%)
 ↳ reduce-in-rows 1.95 ms 2.00 ms +4.80% (-6.62% to +6.54%)
aggregate-leanxmss-100-2to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 89.82 ms 89.72 ms -1.64% (-7.00% to +5.97%)
 ↳ build-circuit 15.06 ms 14.91 ms +1.26% (-2.86% to +2.74%)
 ↳ prove-recursion 59.97 ms 58.18 ms -2.32% (-7.45% to +7.51%)
 ↳ reduce-claims 8.89 ms 9.61 ms +4.39% (-16.06% to +9.32%)
 ↳ reduce-in-rows 1.88 ms 1.89 ms +0.73% (-0.50% to +6.44%)
aggregate-leanxmss-100-4to1-first 1 arm64 Neoverse-V2 1.88 s 1.89 s +0.21% (-0.15% to +0.40%)
 ↳ build-circuit 25.03 ms 25.17 ms +0.56% (-0.30% to +0.77%)
 ↳ prove-recursion 1.82 s 1.83 s +0.19% (-0.17% to +0.40%)
 ↳ reduce-claims 20.88 ms 21.04 ms +0.43% (-0.25% to +1.34%)
 ↳ reduce-in-rows 2.70 ms 2.71 ms +0.74% (-0.96% to +2.80%)
 ↳ verify 11.55 ms 11.56 ms +0.19% (-0.25% to +0.29%)
aggregate-leanxmss-100-4to1-first 4 arm64 Neoverse-V2 519.96 ms 519.55 ms -0.14% (-0.19% to +0.01%)
 ↳ build-circuit 21.34 ms 21.41 ms +0.36% (-0.61% to +0.69%)
 ↳ prove-recursion 477.15 ms 476.64 ms -0.15% (-0.32% to +0.01%)
 ↳ reduce-claims 7.13 ms 7.17 ms -0.30% (-1.83% to +7.98%)
 ↳ reduce-in-rows 2.82 ms 2.81 ms -0.39% (-4.93% to +0.14%)
 ↳ verify 11.28 ms 11.28 ms -0.01% (-0.67% to +1.40%)
aggregate-leanxmss-100-4to1-first 8 arm64 Neoverse-V2 300.58 ms 300.28 ms -0.37% (-0.88% to +0.20%)
 ↳ build-circuit 21.02 ms 20.90 ms -1.16% (-2.56% to +0.58%)
 ↳ prove-recursion 260.08 ms 259.85 ms -0.39% (-0.80% to +0.15%)
 ↳ reduce-claims 5.07 ms 5.17 ms +1.95% (-2.00% to +2.90%)
 ↳ reduce-in-rows 2.83 ms 2.75 ms -3.02% (-4.13% to -1.16%)
 ↳ verify 11.55 ms 11.53 ms -0.18% (-2.29% to +0.49%)
aggregate-leanxmss-100-4to1-first 16 arm64 Neoverse-V2 190.43 ms 190.81 ms +0.20% (-0.58% to +0.47%)
 ↳ build-circuit 20.93 ms 20.81 ms +0.73% (-2.91% to +0.90%)
 ↳ prove-recursion 150.11 ms 150.14 ms +0.09% (-0.86% to +0.90%)
 ↳ reduce-claims 4.41 ms 4.57 ms +3.62% (-0.13% to +6.12%)
 ↳ reduce-in-rows 2.78 ms 2.82 ms +1.63% (-2.57% to +2.22%)
 ↳ verify 12.26 ms 12.26 ms -0.10% (-0.48% to +0.58%)
aggregate-leanxmss-100-4to1-first 1 x86-64 INTEL(R) XEON(R) GOLD 6548N 1.13 s 1.14 s -0.06% (-0.32% to +0.68%)
 ↳ build-circuit 32.58 ms 33.15 ms +1.54% (+0.34% to +3.54%)
 ↳ prove-recursion 1.06 s 1.06 s -0.03% (-0.45% to +0.70%)
 ↳ reduce-claims 26.29 ms 26.21 ms -0.20% (-1.56% to +1.77%)
 ↳ reduce-in-rows 3.69 ms 3.73 ms +0.16% (-3.14% to +2.98%)
 ↳ verify 12.30 ms 12.28 ms -0.15% (-0.24% to +0.33%)
aggregate-leanxmss-100-4to1-first 4 x86-64 INTEL(R) XEON(R) GOLD 6548N 340.03 ms 334.34 ms -1.97% (-3.69% to +3.46%)
 ↳ build-circuit 31.00 ms 30.82 ms +1.49% (-7.98% to +3.10%)
 ↳ prove-recursion 283.38 ms 277.12 ms -2.57% (-4.33% to +3.58%)
 ↳ reduce-claims 8.67 ms 9.21 ms +5.48% (-6.72% to +15.35%)
 ↳ reduce-in-rows 3.63 ms 3.69 ms +2.26% (-0.46% to +6.25%)
 ↳ verify 11.89 ms 11.68 ms +0.46% (-3.82% to +2.12%)
aggregate-leanxmss-100-4to1-first 8 x86-64 INTEL(R) XEON(R) GOLD 6548N 218.12 ms 217.28 ms +0.30% (-1.47% to +1.92%)
 ↳ build-circuit 31.35 ms 31.38 ms +0.09% (-5.21% to +1.58%)
 ↳ prove-recursion 161.96 ms 162.03 ms +0.07% (-1.13% to +1.35%)
 ↳ reduce-claims 7.11 ms 7.80 ms +8.18% (+6.26% to +21.69%)
 ↳ reduce-in-rows 3.80 ms 3.74 ms -0.32% (-6.73% to +2.42%)
 ↳ verify 12.28 ms 12.24 ms -0.28% (-1.95% to +1.08%)
aggregate-leanxmss-100-4to1-first 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 157.46 ms 159.44 ms +1.26% (-5.89% to +8.79%)
 ↳ build-circuit 29.44 ms 28.80 ms -0.99% (-3.08% to +2.04%)
 ↳ prove-recursion 104.96 ms 107.10 ms +2.31% (-6.07% to +12.56%)
 ↳ reduce-claims 7.04 ms 7.83 ms +10.05% (-33.06% to +24.84%)
 ↳ reduce-in-rows 3.52 ms 3.54 ms +0.64% (-2.27% to +3.08%)
 ↳ verify 12.98 ms 12.72 ms -1.94% (-5.56% to +0.62%)
aggregate-leanxmss-100-4to1-node 1 arm64 Neoverse-V2 2.05 s 2.06 s +0.01% (-0.29% to +0.29%)
 ↳ build-circuit 29.41 ms 29.31 ms -0.50% (-1.17% to +0.33%)
 ↳ prove-recursion 1.95 s 1.95 s +0.00% (-0.33% to +0.27%)
 ↳ reduce-claims 55.73 ms 56.18 ms +0.77% (+0.49% to +1.40%)
 ↳ reduce-in-rows 2.91 ms 2.97 ms +1.92% (+0.05% to +3.58%)
aggregate-leanxmss-100-4to1-node 4 arm64 Neoverse-V2 565.50 ms 564.11 ms -0.16% (-0.37% to +0.11%)
 ↳ build-circuit 25.57 ms 25.62 ms +0.12% (-0.43% to +0.78%)
 ↳ prove-recursion 508.63 ms 507.38 ms -0.17% (-0.36% to +0.11%)
 ↳ reduce-claims 17.49 ms 17.35 ms +0.14% (-1.28% to +0.95%)
 ↳ reduce-in-rows 2.99 ms 3.01 ms +0.75% (-3.51% to +1.44%)
aggregate-leanxmss-100-4to1-node 8 arm64 Neoverse-V2 325.64 ms 324.33 ms -0.27% (-0.63% to -0.16%)
 ↳ build-circuit 25.20 ms 25.14 ms -0.14% (-2.72% to +0.49%)
 ↳ prove-recursion 275.09 ms 274.10 ms -0.34% (-0.42% to -0.23%)
 ↳ reduce-claims 11.81 ms 11.88 ms +0.39% (-1.46% to +2.32%)
 ↳ reduce-in-rows 3.01 ms 2.94 ms -1.20% (-3.10% to +2.91%)
aggregate-leanxmss-100-4to1-node 16 arm64 Neoverse-V2 206.70 ms 206.61 ms +0.23% (-0.22% to +1.32%)
 ↳ build-circuit 24.96 ms 24.87 ms -0.33% (-0.92% to +5.44%)
 ↳ prove-recursion 159.19 ms 159.48 ms +0.34% (-0.25% to +0.79%)
 ↳ reduce-claims 9.38 ms 9.36 ms -0.26% (-2.80% to +1.57%)
 ↳ reduce-in-rows 2.95 ms 2.95 ms -0.37% (-3.65% to +3.25%)
aggregate-leanxmss-100-4to1-node 1 x86-64 INTEL(R) XEON(R) GOLD 6548N 1.24 s 1.24 s +0.24% (-0.63% to +0.58%)
 ↳ build-circuit 39.43 ms 39.01 ms -1.21% (-5.88% to +3.65%)
 ↳ prove-recursion 1.12 s 1.12 s +0.21% (-0.79% to +1.02%)
 ↳ reduce-claims 66.40 ms 66.61 ms -0.11% (-2.28% to +1.84%)
 ↳ reduce-in-rows 3.62 ms 3.62 ms +0.19% (-4.78% to +1.01%)
aggregate-leanxmss-100-4to1-node 4 x86-64 INTEL(R) XEON(R) GOLD 6548N 369.14 ms 367.75 ms -1.87% (-4.07% to +1.80%)
 ↳ build-circuit 37.48 ms 36.67 ms -2.38% (-6.13% to +3.63%)
 ↳ prove-recursion 296.64 ms 296.01 ms -1.94% (-4.02% to +3.00%)
 ↳ reduce-claims 20.61 ms 20.23 ms -1.87% (-7.96% to +3.57%)
 ↳ reduce-in-rows 3.88 ms 3.83 ms -1.40% (-8.03% to +3.29%)
aggregate-leanxmss-100-4to1-node 8 x86-64 INTEL(R) XEON(R) GOLD 6548N 234.76 ms 235.66 ms +0.26% (-1.00% to +6.01%)
 ↳ build-circuit 36.46 ms 36.67 ms +0.50% (-3.37% to +3.90%)
 ↳ prove-recursion 169.07 ms 170.24 ms +0.09% (-0.29% to +6.73%)
 ↳ reduce-claims 14.59 ms 14.51 ms +1.90% (-7.77% to +15.69%)
 ↳ reduce-in-rows 4.08 ms 4.10 ms +0.16% (-0.54% to +2.17%)
aggregate-leanxmss-100-4to1-node 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 174.10 ms 167.73 ms -2.72% (-4.52% to +4.40%)
 ↳ build-circuit 34.30 ms 33.89 ms -2.13% (-7.16% to +0.53%)
 ↳ prove-recursion 110.14 ms 110.08 ms -3.14% (-5.60% to +10.12%)
 ↳ reduce-claims 12.65 ms 12.23 ms -9.93% (-23.32% to +1.39%)
 ↳ reduce-in-rows 3.83 ms 3.77 ms -1.38% (-3.19% to +0.58%)
leanxmss-100 1 arm64 Neoverse-V2 1.77 s 1.78 s -0.00% (-0.19% to +0.71%)
 ↳ build-witness 46.41 ms 46.49 ms +0.76% (-0.99% to +4.98%)
 ↳ commit 295.15 ms 296.13 ms +0.37% (-0.13% to +1.14%)
 ↳ execute-program 10.48 ms 10.59 ms +1.03% (-3.78% to +7.81%)
 ↳ flock-reductions 644.14 ms 644.98 ms +0.08% (-0.15% to +0.47%)
 ↳ pcs-open 631.32 ms 630.52 ms -0.35% (-1.27% to +1.07%)
 ↳ prove-bus 131.29 ms 131.83 ms -0.12% (-0.39% to +1.22%)
 ↳ prove-constraints 14.55 ms 14.59 ms +0.24% (-2.53% to +4.09%)
leanxmss-100 4 arm64 Neoverse-V2 472.38 ms 474.90 ms +0.53% (+0.01% to +1.41%)
 ↳ build-witness 12.85 ms 12.87 ms +0.05% (-0.31% to +1.53%)
 ↳ commit 74.22 ms 75.02 ms +0.92% (+0.21% to +2.75%)
 ↳ execute-program 10.22 ms 10.44 ms +1.03% (-1.85% to +4.36%)
 ↳ flock-reductions 169.03 ms 168.98 ms +0.06% (-0.23% to +0.31%)
 ↳ pcs-open 165.10 ms 165.41 ms +0.20% (+0.06% to +2.03%)
 ↳ prove-bus 35.47 ms 35.66 ms +0.81% (+0.05% to +2.60%)
 ↳ prove-constraints 5.54 ms 5.55 ms +0.35% (-1.67% to +6.97%)
leanxmss-100 8 arm64 Neoverse-V2 264.35 ms 264.49 ms +0.08% (-0.21% to +0.38%)
 ↳ build-witness 7.38 ms 7.36 ms -0.28% (-0.81% to +0.73%)
 ↳ commit 38.33 ms 38.45 ms +0.27% (-0.23% to +1.28%)
 ↳ execute-program 10.30 ms 10.34 ms +0.37% (-7.46% to +4.04%)
 ↳ flock-reductions 93.46 ms 93.51 ms +0.15% (-0.35% to +0.45%)
 ↳ pcs-open 89.89 ms 89.84 ms -0.18% (-0.40% to +0.79%)
 ↳ prove-bus 20.58 ms 20.59 ms +0.15% (-0.73% to +0.33%)
 ↳ prove-constraints 4.18 ms 4.16 ms -0.30% (-1.68% to -0.06%)
leanxmss-100 16 arm64 Neoverse-V2 162.03 ms 161.49 ms -0.50% (-5.04% to +0.24%)
 ↳ build-witness 4.83 ms 4.83 ms +0.58% (-12.71% to +1.95%)
 ↳ commit 20.40 ms 20.33 ms -0.37% (-9.31% to +0.04%)
 ↳ execute-program 10.30 ms 10.17 ms -0.87% (-4.69% to +1.67%)
 ↳ flock-reductions 56.37 ms 56.07 ms -0.45% (-9.99% to +1.22%)
 ↳ pcs-open 52.69 ms 52.84 ms +0.30% (-1.26% to +1.78%)
 ↳ prove-bus 13.30 ms 13.30 ms +0.17% (-0.49% to +0.67%)
 ↳ prove-constraints 3.81 ms 3.83 ms +1.10% (-3.75% to +2.84%)
leanxmss-100 1 x86-64 INTEL(R) XEON(R) GOLD 6548N 1.02 s 1.02 s +0.30% (-0.04% to +0.60%)
 ↳ build-witness 68.17 ms 68.59 ms +0.62% (-0.13% to +0.91%)
 ↳ commit 183.11 ms 183.97 ms +0.47% (-0.52% to +1.24%)
 ↳ execute-program 12.36 ms 12.31 ms -0.87% (-3.64% to +1.56%)
 ↳ flock-reductions 301.40 ms 301.64 ms +0.45% (-0.13% to +0.91%)
 ↳ pcs-open 351.35 ms 351.92 ms +0.14% (-0.25% to +0.83%)
 ↳ prove-bus 80.71 ms 80.86 ms +0.02% (-0.35% to +0.64%)
 ↳ prove-constraints 18.78 ms 18.97 ms -0.08% (-0.52% to +1.69%)
leanxmss-100 4 x86-64 INTEL(R) XEON(R) GOLD 6548N 297.99 ms 298.54 ms +0.19% (-0.15% to +0.42%)
 ↳ build-witness 19.44 ms 19.44 ms +0.46% (-1.32% to +5.90%)
 ↳ commit 47.52 ms 47.65 ms +0.27% (-0.77% to +0.68%)
 ↳ execute-program 12.64 ms 12.76 ms -0.18% (-1.17% to +5.32%)
 ↳ flock-reductions 84.51 ms 84.79 ms +0.05% (-0.38% to +0.89%)
 ↳ pcs-open 102.62 ms 102.18 ms -0.13% (-0.57% to +0.38%)
 ↳ prove-bus 24.10 ms 24.21 ms +1.05% (-0.91% to +1.74%)
 ↳ prove-constraints 7.37 ms 7.33 ms +0.12% (-1.62% to +0.72%)
leanxmss-100 8 x86-64 INTEL(R) XEON(R) GOLD 6548N 180.16 ms 180.60 ms +0.46% (-7.00% to +2.99%)
 ↳ build-witness 11.32 ms 11.57 ms +2.88% (-6.99% to +7.64%)
 ↳ commit 24.74 ms 24.76 ms +0.04% (-11.71% to +11.58%)
 ↳ execute-program 13.11 ms 13.17 ms +0.53% (-3.63% to +6.44%)
 ↳ flock-reductions 48.30 ms 48.69 ms +0.38% (-8.36% to +2.40%)
 ↳ pcs-open 61.08 ms 61.90 ms +0.61% (-5.79% to +2.89%)
 ↳ prove-bus 15.26 ms 15.33 ms -0.03% (-8.19% to +3.97%)
 ↳ prove-constraints 5.40 ms 5.45 ms -0.33% (-3.00% to +4.81%)
leanxmss-100 16 x86-64 INTEL(R) XEON(R) GOLD 6548N 125.21 ms 121.19 ms -1.09% (-5.38% to +1.83%)
 ↳ build-witness 7.32 ms 7.11 ms -1.84% (-8.50% to +12.26%)
 ↳ commit 14.11 ms 13.51 ms -4.10% (-5.37% to +1.39%)
 ↳ execute-program 11.89 ms 11.96 ms +1.74% (-4.61% to +3.48%)
 ↳ flock-reductions 34.28 ms 33.22 ms -0.87% (-5.70% to +5.35%)
 ↳ pcs-open 41.45 ms 39.63 ms -2.24% (-7.81% to -0.88%)
 ↳ prove-bus 10.99 ms 10.79 ms +0.22% (-7.40% to +2.21%)
 ↳ prove-constraints 5.01 ms 4.92 ms +0.12% (-4.70% to +1.98%)

@tcoratger
tcoratger force-pushed the zk-stack/1-spec branch 2 times, most recently from 6fe1814 to 21b8504 Compare October 12, 2026 14:08
The specification of zero-knowledge leaf proofs, before the code that implements it.

- Annex B, the hiding commitment (sec:pcs-zk): every level-0 row padded past its power of two by q_0 + 2 coefficients behind the factor W_m(X + s), which vanishes nowhere on the domain, and an aligned group of four uniform rows. Lemma pcs-zk-group: the group's fold weights span E over K except with probability below 2^-120, so the folded witness and the padding's fold are uniform; one uniform row would mask each coordinate only along a line, and any functional with coefficients in K would show the other two. Theorem pcs-zk: the opening is simulatable from them, every unopened leaf keeping at least 256 bits of min-entropy.
- Annex F, zero knowledge (new): the transcript under one-time-pad keys, the hidden final clock, the record as a rank-one system that depends on the transcript's shape alone, the deferred claims batched into the plain shape by one challenge, the outer zero-knowledge Spartan and the key commitment, the soundness additions (a second list factor paid by 12 more grinding bits before the bus), the zero-knowledge theorem, and recursion over zero-knowledge leaves with plain tree proofs.

Co-Authored-By: Kevaundray Wedderburn <kevtheappdev@gmail.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant