PacBio needed to raise the throughput and accuracy of its long-read sequencing instruments without increasing system footprint, power draw, or cost, but CPU-based base calling and consensus generation had become the bottleneck.
Reported impact
PacBio raised Revio compute power 20x over Sequel IIe, cut circular consensus sequencing from more than 15 hours to 2.5 hours, improved HiFi read generation from 30 hours to 24 hours, and scaled the system to 1,300 human genomes per year at 99.9 percent accuracy.
PacBio redesigned the Revio long-read sequencer around NVIDIA A100 Tensor Core GPUs so core analysis stages could run inside the instrument rather than waiting on slow CPU-only workflows. The A100-based stack accelerates base calling and circular consensus sequencing, while CUDA optimizations keep those GPU kernels efficient enough to meet instrument-throughput targets in the same device footprint. Once CCS became fast enough, PacBio added the transformer-based DeepConsensus model on the same GPUs to improve HiFi read accuracy without new hardware. Downstream, customers can hand the resulting reads to NVIDIA Parabricks for GPU-accelerated alignment and variant calling, extending the faster in-instrument pipeline into secondary analysis. Together these layers make Revio a higher-throughput, more affordable long-read system for genomics and clinical research workloads.
Raw long-read signals are base-called and processed through circular consensus sequencing on A100 GPUs inside Revio, DeepConsensus refines the resulting HiFi reads, and customers can then pass those reads into Parabricks for GPU-accelerated alignment and variant calling.
PacBio incorporated the NVIDIA A100 Tensor Core GPU into their Revio system to accelerate the speed and accuracy of long-read sequencing, while minimizing costs.
Revio can scale up to 1,300 human genomes per year.
This achieved a shorter time to high-accuracy HiFi reads-from 30 hours on the CPU-based Sequel IIe to 24 hours on the Revio.
WIth Revio using NVIDIA GPUS, PacBio was able to reduce the CCS process from over 15 hours to 2.5 hours.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The 2025 Form 10-K states: "As of December 31, 2025, we had 485 full-time employees."
Related
NVIDIA Sample Sep 22, 2026 DELFI Diagnostics DELFI Diagnostics needed to speed genomic analysis for cancer screening and therapeutic monitoring, but CPU-bound alignment and somatic variant-calling steps created turnaround-time and cost bottlenecks that limited how… 10–20 business days DeepSomatic · MutectCaller · NVIDIA Parabricks NVIDIA Sample Jul 10, 2026 Astellas Pharma Inc. Astellas needed to shorten the slow handoff between experimental scientists and computational chemists in early drug discovery so more researchers could use structure prediction and affinity screening without waiting on… More than 50 regular users and over 2,000 total users within four months NVIDIA BioNeMo · NVIDIA Boltz-2 NIM · NVIDIA DGX H100/H200 NVIDIA Sample Apr 23, 2026 Biofy Hospitals needed pathogen identification and antibiotic-resistance analysis much faster than five-day culture and antibiogram workflows, but CPU-bound genomic processing and limited AI expertise made it hard to turn… 100,000+ synthetic DNA sequences generated by the biology model Abby · H100 Tensor Core GPUs · NVIDIA CUDA-accelerated libraries 