Nvidia: Difference between revisions
SinexTitan (talk | contribs) small list of "competitors" |
→References: fix date, etc |
||
| Line 26: | Line 26: | ||
On the Kepler-generation GK110 GPU, all variants of the chip contain 64 double precision (FP64) CUDA cores per SMX block, but on consumer cards such as the GTX 780 and GTX 780 Ti, Nvidia forced the FP64 units to run at one eighth of the GPU's clock rate, reducing effective FP64 throughput to 1/24 that of FP32.<ref>{{Cite web |last=Angelini |first=Chris |date=2013-02-19 |title=Compute Performance And Striking A Balance |url=https://www.tomshardware.com/reviews/geforce-gtx-titan-gk110-review,3438-3.html |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> The GeForce GTX Titan, also GK110, shipped with a control panel toggle that restored the full 1/3 FP64 rate, confirming the restriction was deliberate.<ref>{{Cite web |last=Angelini |first=Chris |date=2017-05-25 |title=Nvidia Titan Xp 12GB Review |url=https://www.tomshardware.com/reviews/nvidia-titan-xp,5066-14.html |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> The Tesla K40, built on the same die, delivered full FP64 at several times the consumer price. | On the Kepler-generation GK110 GPU, all variants of the chip contain 64 double precision (FP64) CUDA cores per SMX block, but on consumer cards such as the GTX 780 and GTX 780 Ti, Nvidia forced the FP64 units to run at one eighth of the GPU's clock rate, reducing effective FP64 throughput to 1/24 that of FP32.<ref>{{Cite web |last=Angelini |first=Chris |date=2013-02-19 |title=Compute Performance And Striking A Balance |url=https://www.tomshardware.com/reviews/geforce-gtx-titan-gk110-review,3438-3.html |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> The GeForce GTX Titan, also GK110, shipped with a control panel toggle that restored the full 1/3 FP64 rate, confirming the restriction was deliberate.<ref>{{Cite web |last=Angelini |first=Chris |date=2017-05-25 |title=Nvidia Titan Xp 12GB Review |url=https://www.tomshardware.com/reviews/nvidia-titan-xp,5066-14.html |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> The Tesla K40, built on the same die, delivered full FP64 at several times the consumer price. | ||
The GTX 680 and Quadro K5000 likewise shared the GK104 die,<ref>{{Cite web |last=Smith |first=Ryan |date=2012-08-07 |title=NVIDIA Announces Kepler-Based Quadro K5000 & Second-Generation Maximus |url=https://www.anandtech.com/show/6140/nvidia-announces-keplerbased-quadro-k5000-secondgeneration-maximus |url-status=live |access-date=2026-03-02 |website=AnandTech}}</ref> and users could cross-flash a Quadro vBIOS onto a GeForce card or modify resistor straps on the PCB to change the PCI device ID, unlocking features such as 10-bit colour output and professional OpenGL optimisations.<ref>{{Cite web |date=2013-03 |title=Hacking NVidia Cards into their Professional Counterparts |url=https://www.eevblog.com/forum/general-computing/hacking-nvidia-cards-into-their-professional-counterparts/ |url-status=live |access-date=2026-03-02 |website=EEVblog Forum}}</ref> With the GeForce 900 series in 2014, Nvidia introduced an on-die security processor codenamed Falcon that enforced vBIOS signature verification, preventing cards from booting with unauthorised firmware and ending the cross-flashing practice.<ref>{{Cite web |date=2023-08-21 |title=Nvidia vBIOS Modding Is Back After Signature Lock Broken |url=https://www.tomshardware.com/news/new-nvidia-bios-modding-tools |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> In August 2023, modders found that Nvidia's own NVFlash utility contained a built-in mismatch bypass and released two tools, OMGVflash and NVflashk, which re-enabled cross-flashing on cards up to the RTX 40 series.<ref>{{Cite web |date=2023-08-22 |title=NVIDIA BIOS Signature Lock breakthrough: New tools enable vBIOS modding and crossflash |url=https://www.igorslab.de/en/durchbruch-bei-nvidia-bios-signature-lock-neue-tools-ermoeglichen-vbios-modding-und-crossflash/ |url-status=live |access-date=2026-03-02 |website=igor'sLAB}}</ref> | The GTX 680 and Quadro K5000 likewise shared the GK104 die,<ref>{{Cite web |last=Smith |first=Ryan |date=2012-08-07 |title=NVIDIA Announces Kepler-Based Quadro K5000 & Second-Generation Maximus |url=https://www.anandtech.com/show/6140/nvidia-announces-keplerbased-quadro-k5000-secondgeneration-maximus |url-status=live |access-date=2026-03-02 |website=AnandTech}}</ref> and users could cross-flash a Quadro vBIOS onto a GeForce card or modify resistor straps on the PCB to change the PCI device ID, unlocking features such as 10-bit colour output and professional OpenGL optimisations.<ref>{{Cite web |date=2013-03-15 |title=Hacking NVidia Cards into their Professional Counterparts |url=https://www.eevblog.com/forum/general-computing/hacking-nvidia-cards-into-their-professional-counterparts/ |url-status=live |archive-url=https://web.archive.org/web/20200814064418/https://www.eevblog.com/forum/general-computing/hacking-nvidia-cards-into-their-professional-counterparts/ |archive-date=2020-08-14 |access-date=2026-03-02 |website=EEVblog Forum}}</ref> With the GeForce 900 series in 2014, Nvidia introduced an on-die security processor codenamed Falcon that enforced vBIOS signature verification, preventing cards from booting with unauthorised firmware and ending the cross-flashing practice.<ref>{{Cite web |date=2023-08-21 |title=Nvidia vBIOS Modding Is Back After Signature Lock Broken |url=https://www.tomshardware.com/news/new-nvidia-bios-modding-tools |url-status=live |access-date=2026-03-02 |website=Tom's Hardware}}</ref> In August 2023, modders found that Nvidia's own NVFlash utility contained a built-in mismatch bypass and released two tools, OMGVflash and NVflashk, which re-enabled cross-flashing on cards up to the RTX 40 series.<ref>{{Cite web |date=2023-08-22 |title=NVIDIA BIOS Signature Lock breakthrough: New tools enable vBIOS modding and crossflash |url=https://www.igorslab.de/en/durchbruch-bei-nvidia-bios-signature-lock-neue-tools-ermoeglichen-vbios-modding-und-crossflash/ |url-status=live |access-date=2026-03-02 |website=igor'sLAB}}</ref> | ||
Nvidia also restricts virtual GPU (vGPU) functionality to enterprise products through a driver-level PCI device ID check rather than any hardware limitation. The RTX 3090 and enterprise RTX A5500 are both built on the GA102 die with near-identical specifications, yet only the A5500 supports vGPU.<ref>{{Cite web |last=Lozano |first=Jorge |date=2025-08-10 |title=Nvidia locks datacenter features out of consumer GPUs |url=https://www.xda-developers.com/nvidia-locks-datacenter-features-out-of-consumer-gpus/ |url-status=live |access-date=2026-03-02 |website=XDA Developers}}</ref> The vgpu_unlock project demonstrates this by intercepting driver calls and spoofing the device ID, enabling Maxwell and newer consumer GPUs to run vGPU without hardware modification.<ref>{{Cite web |last=DualCoder |title=vgpu_unlock: Unlock vGPU functionality for consumer grade GPUs |url=https://github.com/DualCoder/vgpu_unlock |url-status=live |access-date=2026-03-02 |website=GitHub}}</ref> | Nvidia also restricts virtual GPU (vGPU) functionality to enterprise products through a driver-level PCI device ID check rather than any hardware limitation. The RTX 3090 and enterprise RTX A5500 are both built on the GA102 die with near-identical specifications, yet only the A5500 supports vGPU.<ref>{{Cite web |last=Lozano |first=Jorge |date=2025-08-10 |title=Nvidia locks datacenter features out of consumer GPUs |url=https://www.xda-developers.com/nvidia-locks-datacenter-features-out-of-consumer-gpus/ |url-status=live |access-date=2026-03-02 |website=XDA Developers}}</ref> The vgpu_unlock project demonstrates this by intercepting driver calls and spoofing the device ID, enabling Maxwell and newer consumer GPUs to run vGPU without hardware modification.<ref>{{Cite web |last=DualCoder |title=vgpu_unlock: Unlock vGPU functionality for consumer grade GPUs |url=https://github.com/DualCoder/vgpu_unlock |url-status=live |access-date=2026-03-02 |website=GitHub}}</ref> | ||