---
title: "No primary source confirms CRISP's claim that PIM cut DNA-alignment time from '20 hours to less than a second'"
type: "claim"
status: "seedling"
audit_status: "flagged — the only source located for this figure is a Tier-3 university-press article citing no underlying paper, benchmark, or dataset; the phrase was retrieved this session via WebFetch (a summarizing tool), so per the quote-provenance rule it is not admissible as a sourced source_quote and is not recorded as one below. See [[question-verify-crisp-dna-alignment-20hr-to-1sec]] for the verification this note and its companion resolve."
source_url: "https://news.virginia.edu/content/say-goodbye-memory-wall"
source_author: "Audra Book, UVA Today"
source_date: "2022-02-08"
source_tier: 3
provenance: "Promotion from 10-inbox/raw/2026-07-30-does-a-primary-source-confirm-crisps-20-hours.md, 2026-07-30"
origin: "batch"
derived_from: ["10-inbox/raw/2026-07-30-does-a-primary-source-confirm-crisps-20-hours.md"]
date_created: "2026-07-30T00:00:00.000Z"
writer_model: "claude-sonnet-5"
tags: ["processing-in-memory","genomics","sequence-alignment","CRISP","computer-architecture","verification","quant","source-criticism"]
related_notes: ["claim-processing-in-memory-beats-memory-wall-dna-alignment","claim-memory-wall-named-1994-wulf-mckee","claim-rapid-rapidx-speedups-fall-short-of-crisp-press-figure"]
audits: ["2026-07-31 claude-opus-4-8"]
---


UVA Today (Audra Book, 2022-02-08, "Say Goodbye to the Memory Wall") reports that researchers at CRISP — the Center for Research in Intelligent Storage and Processing in Memory, a DARPA/SRC JUMP-funded center — found that processing-in-memory (PIM) redesigns "could shorten sequence alignment time from 20 hours to less than a second," framed as an achieved result. No paper, benchmark name, or dataset accompanies the figure, and Kevin Skadron (CRISP's director, quoted elsewhere in the same piece) is not quoted attributing the number directly.

A direct search for the underlying primary — including CRISP's own peer-reviewed PIM sequence-alignment publications, the natural place such a result would appear — found no paper stating or reproducing this figure. See [[claim-rapid-rapidx-speedups-fall-short-of-crisp-press-figure]] for what CRISP's actual Tier-1 output reports instead, and by how much it falls short of this figure's implied magnitude.

This is a quantitative claim resting on a single Tier-3 source with no cited study, which does not clear the sourcing floor for quantitative claims (Tier 1–2 required per `00-meta/specs/sources.md`). It carries **[unverified-quant — needs primary]**. Separately, because the exact phrase was retrieved this session through a summarizing tool rather than a direct fetch, it also carries **[unverified-quote — needs direct read]** and is not recorded in `source_quote` above.

> [!note] Seek's commentary:
> Two sessions, two attempts, same wall: the number has no home. Not "hard to find" — actively unsupported by the one body of work positioned to support it.