EXP-068NEGATIVE
Canonical GPU engineering / SHA-256d

Low nonces-per-thread geometry sweep

NPT values 1, 2, 4 or 8 at TPB 256/512 can outperform the retained T512-N32 baseline by at least 1%.

Claim statusNO END-TO-END MINING ADVANTAGE DEMONSTRATED

Diagnostic work, exact algebra and local capabilities are not treated as end-to-end mining advantage.

Date2026-08-14
HardwareNVIDIA GeForce RTX 5080 · exact SHA-256d verifier
Run scopePreregistered campaign with sealed result and audit
ReproducibilityKeep equal hash counts, publish all geometries and separate this failed gate from the successor replication.
01 / Question & hypothesis

What was tested?

NPT values 1, 2, 4 or 8 at TPB 256/512 can outperform the retained T512-N32 baseline by at least 1%.

02 / Scientific basis

Why the test is meaningful

Lower NPT can reduce per-thread serial work but increases launch/scheduling overhead; equal total hashes are required.

candidates=TPB{256,512}×NPT{1,2,4,8}R=throughput_candidate/throughput_T512-N32gate R≥1.01
Low nonces-per-thread geometry sweepVisual reading of the published metrics and gates for EXP-068; it summarizes the registered result, not a mining advantage.EXP-068 / LOW NONCES-PER-THREAD GEOMETRY SWEEPBEST RATIO1.003573POSITIVE HEADERS4 / 4PRIMARY GATEFAILED
FIGURE / RESULT READINGVisual reading of the published metrics and gates for EXP-068; it summarizes the registered result, not a mining advantage.
03 / Method

How it was tested

Compile ten exact binaries and test four unseen headers, two repetitions and 80 equal-work runs.

04 / Observed result

What happened

Best ratio1.003573
Positive headers4 / 4
Primary gateFAILED

T512-N4 was best at 1.003573×, positive on 4/4 headers but below the 1.01 gate on every dataset. All binaries verified B32 with zero discrepancies/spills.

05 / Validation

Exactness and statistical controls

The preregistered experiment closes negative. The consistent 0.36% direction is retained only as a discovery signal for an independent replication.

06 / Interpretation

What the result means

No registered low-NPT geometry clears the primary gate; N4 receives a separate replication, not retrospective promotion.

Limitations

  • The 1% gate intentionally rejects small discovery effects.
  • Only integer registered geometries were tested.
  • No energy inference is made.
07 / Reproduction

Evidence trail

Keep equal hash counts, publish all geometries and separate this failed gate from the successor replication.

Canonical variants

CANONICAL-EXP-144PREREGISTERED-CAMPAIGNSEALED-AUDIT

Source: internally audited canonical reports. Local filesystem structure, private headers and operational identifiers are excluded from publication.