{
  "id": 20762463,
  "title": "Intel says its graphics-free D270 GPU beats Nvidia's RTX Pro 6000 by up to 5.9x in benchmarks",
  "url": "https://urgent.news/2026/11/19/intel-says-its-graphics-free-d270-gpu-beats-nvidias-rtx-pro-6000-by",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-19T14:49:00.000Z",
  "source": {
    "name": "TechSpot",
    "slug": "techspot",
    "url": "https://www.techspot.com/news/114624-intel-graphics-free-d270-gpu-beats-nvidia-rtx.html"
  },
  "original_language": "en",
  "account": "Intel's latest graphics-free GPU, the D270, has demonstrated impressive performance in benchmarks against Nvidia's RTX Pro 6000. At the SC26 supercomputing show in Chicago, Intel showcased the D270's capabilities by pitting it against the RTX Pro 6000 in four workloads typically used by banks to value financial contracts. The D270 outperformed Nvidia's card by up to 5.9 times, with its best result coming in a European Monte Carlo simulation.\n\nOne key factor behind the D270's success is its Xe3P architecture, which handles double-precision, or FP64, calculations at full speed. This full-speed FP64 support gives the D270 a significant advantage over Nvidia's RTX Pro 6000, which uses the same chip as the GeForce RTX 5090. The RTX 5090 only manages FP64 at a fraction of its usual speed, making it more vulnerable in tasks that heavily rely on FP64 calculations.\n\nIntel's choice to focus on FP64-heavy workloads in this benchmark aimed to highlight the D270's strengths, as Nvidia's card tends to fall behind in such scenarios. The RTX Pro 6000, on the other hand, offers modest improvements in AI tests, achieving only a 12% throughput advantage over the D270. This outcome is somewhat surprising, considering the D270 was designed with AI performance in mind.\n\nInterestingly, Nvidia's latest Blackwell Ultra chips offer only about a teraflop of double-precision compute, while Intel's D270 delivers a more substantial FP64 performance. This discrepancy has prompted Intel to target software that emulates FP64 on Nvidia's Tensor Cores, with promises of enhanced FP64 capabilities in future Blackwell Ultra chips. The D270, however, is already being tested ahead of its anticipated 2027 launch, though Intel has not disclosed pricing information.",
  "summary": "In a post, Intel put the D270 up against Nvidia's RTX Pro 6000 Blackwell Server Edition. Instead of games or AI models, Intel went with something a little more niche. It picked four workloads that banks rely on to put a price on financial contracts. Read Entire Article",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}