Chips

Intel claims 5.9x Nvidia on double-precision finance math on pre-production silicon

Intel published the per-workload split the day SC26 opened in Chicago, with no price, no ship date and no independent audit, the same week shareholders sued over a 28.6% one-day drop that erased about $140 billion. For investors the card adds nothing to near-term revenue; the 14A clock is what runs.

Vincent JiangVincent Jiangthree-minute read
Share
Two Intel Arc Pro B70 workstation graphics cards stacked, showing the blower-style cooler, blue Intel Arc PRO B70 backplate lettering and PCIe edge connectors
Intel Arc Pro B70 workstation cards, three of which sat alongside the D270 in the Intel node of the November 6 double-precision test. Intel published the per-workload results on November 16 with no price and no ship date.

Intel's−1.17% — Intel, down 1.17 percent today D270 data center GPU got its first per-workload numbers on November 16, the opening day of Supercomputing 2026 in Chicago 1. Against Nvidia's−1.33% — Nvidia, down 1.33 percent today RTX PRO 6000 Blackwell Server Edition on double-precision finance workloads, Intel claims 5.9x the throughput on European Monte Carlo pricing, 5.6x on European Black-Scholes, 4.6x on binomial pricing and 1.92x on American Black-Scholes 1. The tests ran on November 6 on pre-production silicon 1.

Intel's D270 FP64 claims run 5.9x to 1.92x on four finance workloads

Intel's lead thins from 5.9x on Monte Carlo to 1.92x on American Black-Scholes

  • Estimate
0x2x4x6xEuropean Monte Carlo5.9xEuropean Black-Scholes5.6xBinomial pricing4.6xAmerican Black-Scholes1.92x
Data
Value
European Monte Carlo (estimate)5.9x
European Black-Scholes (estimate)5.6x
Binomial pricing (estimate)4.6x
American Black-Scholes (estimate)1.92x
Intel's claimed D270 vs RTX PRO 6000 Blackwell Server Edition FP64 application throughput ratios, vendor-run on pre-production silicon, November 6, 2026. Sources: TechTimes/Intel newsroom, November 17, 2026.1

The footnotes are where this benchmark lives

Intel's node held one Xeon 6741P, one D270 and three Arc Pro B70 cards; the Nvidia node held two Xeon 6944P processors and eight RTX PRO 6000 cards, and Intel never states whether the comparison is per card 1. The listed Nvidia software stack was CUDA 12.8.0, while Nvidia's FP64 emulation, which reaches about 37 TFLOPS on matrix multiply, shipped in CUDA Toolkit 13.0 1. And Nvidia's dedicated H100 and H200 parts, each at roughly 34 TFLOPS of FP64, appear nowhere in the table 1.

The peak FP64 rate is about a third of an H100's

The RTX PRO 6000 shares silicon with a gaming chip and runs FP64 at 1:64 of its FP32 rate, about 1.968 TFLOPS 1. Nand Research, an independent semiconductor analysis firm, estimates the D270's peak FP64 vector rate near 10.2 TFLOPS, which would put it around 30% of an H100; that ratio is TechTimes' arithmetic, not Intel's 1. Jon Peddie Research, a graphics-industry analyst firm, notes no independent D270 benchmark had been published as of November 16 1. There is no price and no ship date; customer sampling began in October, and Nand Research projects volume availability only in 2027 1.

The H100 Intel left out of its table carries about 3.3x the D270's estimated FP64 peak

  • Estimate
0 TFLOPS10 TFLOPS20 TFLOPS30 TFLOPS40 TFLOPSNvidia H10034 TFLOPSNvidia H20034 TFLOPSIntel D270 (Nand est.)10.2 TFLOPSNvidia RTX PRO 60001.97 TFLOPS
Data
Value
Nvidia H10034 TFLOPS
Nvidia H20034 TFLOPS
Intel D270 (Nand est.) (estimate)10.2 TFLOPS
Nvidia RTX PRO 60001.97 TFLOPS
Peak FP64 throughput in TFLOPS. Nvidia's H100 and H200 are each roughly 34 TFLOPS; the D270 figure is Nand Research's estimate of its peak FP64 vector rate, which would put it near 30% of an H100; the RTX PRO 6000 runs FP64 at 1:64 of its FP32 rate. Intel's benchmark table includes none of the H100 or H200 rows. Sources: TechTimes/Intel newsroom and Nand Research, November 17, 2026.1

The market is paying 43x for 11% growth

The same week, Intel shareholders filed a proposed class action on November 13 in federal court in San Jose, naming CEO Lip-Bu Tan and CFO David Zinsner, alleging the company understated a PC slowdown and excess inventory before shares fell 28.6% on October 30, erasing roughly $140 billion of market value 23. The class covers buyers between July 23 and October 29 23. Dan Niles, founder of Niles Investment Management, puts the valuation plainly: Intel trades near 43x next-twelve-months earnings at its November 13 close of $59.66, on about 11% expected revenue growth, against Nvidia at 14x 2. The lawsuit's allegations are unproven.

Where the 5.9x holds and where it thins

European Monte Carlo draws random numbers, builds price paths and averages payoffs, vector work that suits the D270's full-rate FP64 1. American Black-Scholes, the hardest test in the table, thins the lead to 1.92x 1. Intel published no TFLOPS figure, no problem sizes, and no performance-per-watt despite rating the D270 at 350W against the Nvidia card's up to 600W 1. Two of the four results exceed the roughly 5.2x peak-ratio arithmetic, which suggests software or memory capacity contributes, and Intel has not separated the factors 1.

Buyers should run their own kernels first

Teams needing true double precision for model-risk rules or Greeks have a reason to request D270 hardware and run their own kernels 2. Teams that accept single-precision Monte Carlo face an Nvidia card whose FP32 rate is not throttled 2. Until an independent audit, a price and a date arrive, the 5.9x stays a vendor-run claim on pre-production silicon 2. The number that matters for investors is elsewhere: outside design commitments for Intel's 14A process, which management expects by mid-2027 2.

Get Chips by email, free

How AI demand is reshaping chipmakers, memory and the fabs behind them. In our daily email, every weekday.

Loading INTC

Reader comments

0 comments

    Chips

    SK hynix will spend $1 billion on Korean chip suppliers, failures included

    SK hynix is spending 1.4 trillion won to speed up how quickly Korean suppliers' tools and materials qualify, because contracts already cover more than half of its 2027–28 capacity. The stock is falling on the other memory cycle, the spot-price one.

    Chips

    TSMC fell nearly 5% in the first session to trade the US chip rule; SMIC rose 7%

    The Commerce rule's foundry clause reaches the world's largest contract chipmaker on a record quarter, and no wire has sized what it costs; SMIC's 7% rise on the same day shows which way investors read the shift.

    Chips

    GCT Semiconductor's 5G ramp slips into 2027 with $17.2 million of cash and a $120 million share-sale line

    GCT Semiconductor's 5G ramp is now guided into the first half of 2027, but its $17.2 million of cash covers about two quarters at the September burn rate. The bridge is a $120 million at-the-market facility, larger than the company's $108 million market value, and the company is set up to sell stock before the ramp delivers revenue.

    Chips

    Broadcom's $161 billion Anthropic bet meets Washington's new chip rule

    A new export rule and a downgrade to Neutral now bracket Broadcom's biggest customer bet, and the two marks settle together: Anthropic prices its IPO on November 18, Broadcom reports on December 9.

    Chips

    Ambiq Micro's CEO sold $5.28 million of stock on a preset plan and his stake never changed

    Fumihide Esaka's three-day sale ran on a preset 10b5-1 plan: options struck at $12.60 and $8.12, exercised and sold the same day, his 443,900-share stake untouched. For AMBQ holders the filing that matters is the 10-Q: four customers at 79% of sales and every wafer from one Taiwanese foundry.

    Chips

    Kalshi puts Arm's Rene Haas at 23% to be Nvidia's next CEO, ahead of Huang himself at 17%

    Arm closed down 8.1% on Monday, about twice Nvidia's fall, because the chief executive Nvidia wants carries Arm's whole data-center bet. SoftBank owns about 86% of Arm and gave him a second job in April, so the call is not the market's alone.

    Subscribe to TheInference for free