Configuration

Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)

Parabricks 3.7.0-1, 2 GPUs on AWS as run in Table 1.

Overview

Parabricks 3.7.0-1, 2 GPUs on AWS as run in Table 1.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

6 evaluations · 30 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Source checking is not independent reproduction. Release 2026-10-09-8cc1db47c7f9.

Use this model

How it works, versions and access

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-09-8cc1db47c7f9
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-09-8cc1db47c7f9 · Record review: source checked

1 source records and release history

Accelerating genomic workflows using NVIDIA Parabricks · Original source · BMC Bioinformatics 24:221, published 2023-05-31; PMC10230726 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: model-execution-20261009-config-oconnell2023-aws-gpu2

areas: dna-genomes
contexts: clinical_research
method types: conventional_pipeline
foundation model eligible: false
reported name: Parabricks 3.7.0-1, 2 GPUs on AWS
hardware: description: AWS GPU machine, 2 GPUs; GPU model unresolved (Table 1 footnote: p3 family, NVIDIA Tesla V100; Results text: p4 family, A100)
source locator: Table 1 VM-type column; Methods 'GCP configuration', 'AWS configuration', 'DGX configuration'
version: Parabricks v. 3.7.0-1
protocol: Parabricks Germline Pipeline, DeepVariant Germline Pipeline, mutectcaller, somaticsniper_workflow, muse or lofreq, by protocol
model identity note: Table 1 footnote says the AWS GPU rows are the p3 family with V100 GPUs, but Results 'GPU performance across cloud platforms' paragraph 2 attributes the AWS savings printed in Table 1 (for example 63% for HaplotypeCaller with 4 GPUs) to the p4 machine with A100 GPUs and the p3 results to Additional file 1 Table S1. The Table 1 AWS GPU costs equal the printed minutes times 12.24 USD per hour for 2 and 4 GPUs and 31.22 USD per hour for 8 GPUs; none was priced at the 32.8 USD per hour p4d.24xlarge rate given in Results 'GPU performance across cloud platforms' paragraph 4.

Related records

Suggest a correction

Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	29.6 compute-cost us-dollar · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepVariant on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-deepvariant Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 2 (AWS, GPU2, DeepVariant), column 'Cost ($)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	0.83% cost-saving percent · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepVariant on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-deepvariant Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 2 (AWS, GPU2, DeepVariant), column '% cost-savings'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	145 runtime minute · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepVariant on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-deepvariant Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 2 (AWS, GPU2, DeepVariant), column 'Time (min)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	2.42 runtime hour · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepVariant on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-deepvariant Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 2 (AWS, GPU2, DeepVariant), column 'Time (h)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: DeepVariant execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	9.07 speedup unitless · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepVariant on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-deepvariant Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 2 (AWS, GPU2, DeepVariant), column 'Fold acceleration'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	26.9 compute-cost us-dollar · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HaplotypeCaller on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-haplotypecaller Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 13 (AWS, GPU2, HaplotypeCaller), column 'Cost ($)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	45.4% cost-saving percent · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HaplotypeCaller on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-haplotypecaller Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 13 (AWS, GPU2, HaplotypeCaller), column '% cost-savings'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	132 runtime minute · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HaplotypeCaller on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-haplotypecaller Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 13 (AWS, GPU2, HaplotypeCaller), column 'Time (min)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	2.2 runtime hour · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HaplotypeCaller on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-haplotypecaller Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 13 (AWS, GPU2, HaplotypeCaller), column 'Time (h)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: HaplotypeCaller execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: HG002 (GIAB) WGS FASTQ down-sampled to 30x, precisionFDA Truth Challenge V2	16.5 speedup unitless · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HaplotypeCaller on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-haplotypecaller Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 13 (AWS, GPU2, HaplotypeCaller), column 'Fold acceleration'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	29.6 compute-cost us-dollar · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LoFreq on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-lofreq Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 24 (AWS, GPU2, LoFreq), column 'Cost ($)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	− 625.07% cost-saving percent · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LoFreq on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-lofreq Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 24 (AWS, GPU2, LoFreq), column '% cost-savings'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	145 runtime minute · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LoFreq on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-lofreq Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 24 (AWS, GPU2, LoFreq), column 'Time (min)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	2.42 runtime hour · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LoFreq on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-lofreq Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 24 (AWS, GPU2, LoFreq), column 'Time (h)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: LoFreq execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	1.24 speedup unitless · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LoFreq on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-lofreq Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 24 (AWS, GPU2, LoFreq), column 'Fold acceleration'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	13.3 compute-cost us-dollar · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Muse on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-muse Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 35 (AWS, GPU2, Muse), column 'Cost ($)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	− 37.97% cost-saving percent · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Muse on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-muse Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 35 (AWS, GPU2, Muse), column '% cost-savings'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	65.2 runtime minute · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Muse on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-muse Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 35 (AWS, GPU2, Muse), column 'Time (min)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	1.09 runtime hour · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Muse on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-muse Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 35 (AWS, GPU2, Muse), column 'Time (h)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Muse execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	6.52 speedup unitless · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Muse on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-muse Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 35 (AWS, GPU2, Muse), column 'Fold acceleration'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	5.79 compute-cost us-dollar · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mutect2 on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-mutect2 Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 46 (AWS, GPU2, Mutect2), column 'Cost ($)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	38.3% cost-saving percent · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mutect2 on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-mutect2 Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 46 (AWS, GPU2, Mutect2), column '% cost-savings'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	28.4 runtime minute · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mutect2 on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-mutect2 Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 46 (AWS, GPU2, Mutect2), column 'Time (min)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	0.47 runtime hour · lower Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mutect2 on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-mutect2 Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 46 (AWS, GPU2, Mutect2), column 'Time (h)'
Configuration: Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023)	Protocol: Mutect2 execution on CPU and GPU cloud and DGX machines (O'Connell et al. 2023 Table 1) Dataset: Synthetic tumour BAM: HG002 30x with 198 SNVs added by SomatoSim v1.0.0	14.6 speedup unitless · higher Uncertainty: Not reported by the source: Single recorded run per cell; no repeats or intervals printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Mutect2 on Parabricks 3.7.0-1, 2 GPUs on AWS (O'Connell et al. 2023) model-execution-20261009-protocol-oconnell2023-mutect2 Aggregation: Not reported Accelerating genomic workflows using NVIDIA Parabricks · Table 1, row 46 (AWS, GPU2, Mutect2), column 'Fold acceleration'