Hubbry Logo
GeForce 500 seriesGeForce 500 seriesMain
Open search
GeForce 500 series
Community hub
GeForce 500 series
logo
8 pages, 0 posts
0 subscribers
Be the first to start a discussion here.
Be the first to start a discussion here.
Contribute something
GeForce 500 series
GeForce 500 series
GeForce 500 series
View on Wikipedia
from Wikipedia

GeForce 500 series
A Nvidia GeForce GTX 590 released in 2011, the series' flagship model; this one from EVGA
Release dateNovember 9, 2010; 15 years ago (November 9, 2010)
CodenameGF11x
ArchitectureFermi
ModelsGeForce series
  • GeForce GT series
  • GeForce GTX series
Transistors292M 40 nm (GF119)
  • 585M 40 nm (GF108)
  • 1.170M 40 nm (GF116)
  • 1.950M 40 nm (GF114)
  • 3.000M 40 nm (GF110)
Cards
Entry-level510
GT 520
GT 530
Mid-rangeGT 545
GTX 550 Ti
GTX 555
GTX 560
GTX 560 Ti
GTX 560 SE
High-endGTX 570
GTX 580
EnthusiastGTX 590
API support
Direct3DDirect3D 12.0 (feature level 11_0)[1]
Shader Model 5.1
OpenCLOpenCL 1.1
OpenGLOpenGL 4.6
History
PredecessorGeForce 400 series
SuccessorGeForce 600 series
Support status
Unsupported

The GeForce 500 series is a series of graphics processing units developed by Nvidia, as a refresh of the Fermi based GeForce 400 series. It was first released on November 9, 2010 with the GeForce GTX 580.

Its direct competitor was AMD's Radeon HD 6000 series; they were launched approximately a month apart.

Overview

[edit]

The Nvidia Geforce 500 series graphics cards are significantly modified versions of the GeForce 400 series graphics cards, in terms of performance and power management. Like the Nvidia GeForce 400 series graphics cards, the Nvidia GeForce 500 series supports Direct3D 12.0 (feature level 11.0), OpenGL 4.6, and OpenCL 1.1.

The refreshed Fermi chip includes 512 stream processors, grouped in 16 stream multiprocessors clusters (each with 32 CUDA cores), and is manufactured by TSMC in a 40 nm process.

The Nvidia GeForce GTX 580 graphics card is the first in the Nvidia GeForce 500 series to use a fully enabled chip based on the refreshed Fermi architecture, with all 16 stream multiprocessors clusters and all six 64-bit memory controllers active. The new GF110 GPU was enhanced with full speed FP16 filtering (the previous generation GF100 GPU could only do half-speed FP16 filtering) and improved z-culling units.

On January 25, 2011, Nvidia launched the GeForce GTX 560 Ti, to target the "sweet spot" segment where price/performance ratio is considered important. With its more than 30% improvement over the GTX 460, and performance in between the Radeon HD 6870 and 6950 1GB, the GTX 560 Ti directly replaced the GeForce GTX 470.

On February 17, 2011, it was reported that the GeForce GTX 550 Ti would be launching on March 15, 2011. Although the GTX 550 Ti is a GF116 mainstream chip, Nvidia chose to name its new card the GTX 550 Ti, and not the GTS 550. Performance was shown to be at least comparable and up to 12% faster than the current Radeon HD 5770. Price-wise, the new card trod into the range occupied by the GeForce GTX 460 (768 MB) and the Radeon HD 6790.[2]

On March 24, 2011, the GTX 590 was launched as the flagship graphics card for Nvidia. The GTX 590 is a dual-GPU card, similar to past releases such as the GTX 295, and boasted the potential to handle Nvidia's 3D Vision technology by itself.[3]

On April 13, 2011, the GT 520 was launched as the bottom-end card in the range, with lower performance than the equivalent number cards in the two previous generations, the GT 220 and the GT 420.[citation needed] However, it supported DirectX 11 and was more powerful than the GeForce 210, the GeForce 310, and the integrated graphics options on Intel CPUs.

On May 17, 2011, Nvidia launched a less expensive (non-Ti) version of the GeForce GTX 560 to strengthen Nvidia's price-performance in the $200 range. Like the faster GTX 560 Ti that came before it, this video card was also faster than the GeForce GTX 460. Standard versions of this card performed comparably to the AMD Radeon HD 6870, and would eventually replace the GeForce GTX 460. Premium versions of this card operate at higher speed (factory overclocked), and are slightly faster than the Radeon 6870, approaching the performance of basic versions of the Radeon HD 6950 and the GeForce GTX 560 Ti.

On November 28, 2011, Nvidia launched the "GTX 560 Ti With 448 Cores".[4] However, it does not use the silicon of the GTX 560 series: it is a GF110 chip with two shader blocks disabled. The most powerful version of the 560 series, this card was widely known to be a "limited production" card and was used as a marketing tool making use of the popularity of the GTX 560 brand for the 2011 Holiday season. The performance of the card resides between the regular 560 Ti and 570.

Products

[edit]

GeForce 500 (5xx) series

[edit]
  • 1 Unified shaders: Texture mapping units: Render output units
  • 2 Each Streaming Multiprocessor (SM) in the GPU of GF110 architecture contains 32 SPs and 4 SFUs. Each Streaming Multiprocessor (SM) in the GPU of GF114/116/118 architecture contains 48 SPs and 8 SFUs. Each SP can fulfil up to two single precision operations FMA per clock. Each SFU can fulfil up to four operations SF per clock. The approximate ratio of operations FMA to operations SF is equal 4:1. The theoretical shader performance in single-precision floating point operations (FMA)[FLOPSsp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp ˜ f × n × 2. Alternative formula: FLOPS sp ˜ f × m × (32 SPs × 2(FMA)). [m] – SM count. Total Processing Power: FLOPSsp ˜ f × m × (32 SPs × 2(FMA) + 4 × 4 SFUs) or FLOPSsp ˜ f × n × 2.5.
  • 3 Each SM in the GF110 contains 4 texture filtering units for every texture address unit. The complete GF110 die contains 64 texture address units and 256 texture filtering units.[5] Each SM in the GF114/116/118 architecture contains 8 texture filtering units for every texture address unit but has doubled both addressing and filtering units.

All products are produced using a 40 nm fabrication process. All products support DirectX 12.0, OpenGL 4.6 and OpenCL 1.1.

GeForce 500M (5xxM) series

[edit]

The GeForce 500M series for notebook architecture.

Model Launch Code name Fab (nm) Bus interface Core config1 Clock speed Fillrate Memory API support (version) Processing Power2
(GFLOPS) 		TDP (watts) Notes
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL OpenCL Vulkan
GeForce GT 520M January 5, 2011 GF119 40 PCIe 2.0 x16 48:8:4 740 1480 1600 2.96 5.92 1024 12.8 DDR3 64 12.0
(11_0) 		4.6 1.1 — 142.08 12
GeForce GT 520M GF108 40 PCIe 2.0 x16 96:16:4 515 1030 1600 2.06 8.24 1024 12.8 DDR3 64 197.76 20 Noticed in Lenovo laptops
GeForce GT 520MX May 30, 2011 GF119 40 PCIe 2.0 x16 48:8:4 900 1800 1800 3.6 7.2 1024 14.4 DDR3 64 172.8 20
GeForce GT 525M January 5, 2011 GF108 40 PCIe 2.0 x16 96:16:4 600 1200 1800 2.4 9.6 1024 28.8 DDR3 128 230.4 20-23
GeForce GT 540M January 5, 2011 GF108 40 PCIe 2.0 x16 96:16:4 672 1344 1800 2.688 10.752 1024 28.8 DDR3 128 258.048 32-35
GeForce GT 550M January 5, 2011 GF108 40 PCIe 2.0 x16 96:16:4 740 1480 1800 2.96 11.84 1024 28.8 DDR3 128 284.16 32-35
GeForce GT 555M January 5, 2011 GF106

GF108 		40 PCIe 2.0 x16 144:24:24
144:24:16
96:16:4 		590
650
753 		1180
1300
1506 		1800
1800
3138 		14.6
10.4
3 		14.6
15.6
12 		1536
2048
1024 		43.2
28.8
50.2 		DDR3
DDR3
GDDR5 		192
128
128 		339.84
374.4
289.15 		30-35
GeForce GTX 560M May 30, 2011 GF116 40 PCIe 2.0 x16 192:32:16
192:32:24 		775 1550 2500 18.6 24.8 2048
1536, 3072 		40.0
60.0 		GDDR5 128
192 		595.2 75
GeForce GTX 570M[6] June 28, 2011 GF114 40 PCIe 2.0 x16 336:56:24 575 1150 3000 13.8 32.2 1536 72.0 GDDR5 192 772.8 75
GeForce GTX 580M June 28, 2011 GF114 40 PCIe 2.0 x16 384:64:32 620 1240 3000 19.8 39.7 2048 96.0 GDDR5 256 952.3 100

Chipset table

[edit]

GeForce 500 (5xx) series

[edit]
Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface SM count Core config[a][b] Clock rate Fillrate Memory configuration Supported API version Processing power (GFLOPS)[c] TDP (watts)[d] Release price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) DRAM type Bus width (bit) Vulkan Direct3D OpenGL OpenCL8 Single precision Double precision
GeForce 510 September 29, 2011 GF119 TSMC 40 nm 292 79 PCIe 2.0 x16 1 48:8:4 523 1046 1800 2.1 4.5 1024
2048 		14.4 DDR3 64 n/a[9] 12 (11_0) 4.6 1.1 100.4 Unknown 25 OEM
GeForce GT 520 April 12, 2011 PCIe 2.0 x16
PCIe 2.0 x1
PCI 		810 1620 3.25 6.5 14.4 155.5 Unknown 29 59
GeForce GT 530[10] May 14, 2011 GF108-220 585 116 PCIe 2.0 x16 2 96:16:4 700 1400 2.8 11.2 28.8 128 268.8 22.40 50 OEM
GeForce GT 545 GF116 ~1170 ~238 3 144:24:16 720 1440 11.52 17.28 1536
3072 		43 192 415.07 Unknown 70 149
870 1740 3996 13.92 20.88 1024 64 GDDR5 128 501.12 Unknown 105 OEM
GeForce GTX 550 Ti March 15, 2011 GF116-400 4 192:32:24 900 1800 4104 21.6 28.8 768+256
1536 		65.7+32.8
98.5 		128+64[e]
192 		691.2 Unknown 116 149
GeForce GTX 555 May 14, 2011 GF114 1950 332 6 288:48:24 736 1472 3828 17.6 35.3 1024 91.9 128+64[e] 847.9 Unknown 150 OEM
GeForce GTX 560 SE February 20, 2012[11] GF114-200-KB-A1[f] Unknown
GeForce GTX 560 May 17, 2011 GF114-325-A1[f] 7 336:56:32 810 1620 4008 25.92 45.36 1024 2048 128.1 256 1088.6 Unknown 199
GeForce GTX 560 Ti January 25, 2011 GF114-400-A1[f] 8 384:64:32 822 1645 26.3 52.61 128.26 1263.4 110 170 249
May 30, 2011 GF110[g] 3000[13] 520[13] 11 352:44:40 732 1464 3800 29.28 32.21 1280
2560 		152 320 1030.7 128.83 210[d] OEM
GeForce GTX 560 Ti 448 Cores November 29, 2011 GF110-270-A1[g] 14 448:56:40 40.99 1280 1311.7 163.97 289
GeForce GTX 570 December 7, 2010 GF110-275-A1[g] 15 480:60:40 43.92 1280 2560 1405.4 175.68 219[d] 349
GeForce GTX 580 November 9, 2010 GF110-375-A1[g] 16 512:64:48 772 1544 4008 37.05 49.41 1536
3072[h] 		192.384 384 1581.1 197.63 244[d][15] 499
GeForce GTX 590 March 24, 2011 2x GF110-351-A1 2x 3000 2x 520 2x16 2x 512:64:48 607 1215 3414 2x29.14 2x38.85 2x 1536 2x163.87 2x384 2488.3 311.04 365 699
Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface SM count Core config[a][b] Clock rate Fillrate Memory configuration Supported API version Processing power (GFLOPS)[c] TDP (Watts)[d] Release price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) DRAM type Bus width (bit) Vulkan Direct3D OpenGL OpenCL8 Single precision Double precision
  1. ^ a b Unified shaders: texture mapping units: render output units
  2. ^ a b Each SM in the GF110 contains 4 texture filtering units for every texture address unit. The complete GF110 die contains 64 texture address units and 256 texture filtering units.[7] Each SM in the GF114/116/118 architecture contains 8 texture filtering units for every texture address unit but has doubled both addressing and filtering units.
  3. ^ a b To calculate the processing power see Fermi (microarchitecture)#Performance.
  4. ^ a b c d e Similar to previous generation, GTX 580 and most likely future GTX 570,[needs update] while reflecting its improvement over GF100, still have lower rated TDP and higher power consumption, e.g. GTX 580 (243W TDP) is slightly less power hungry than GTX 480 (250W TDP). This is managed by clock throttling through drivers when a dedicated power hungry application is identified that could breach card TDP. Application name changing will disable throttling and enable full power consumption, which in some cases could be close to that of GTX 480.[8]
  5. ^ a b 1024 MB RAM on 192-bit bus assemble with 4 x (128 MB) + 2 x (256 MB).
  6. ^ a b c Internally referred to as GF104B[12]
  7. ^ a b c d Internally referred to as GF100B[12]
  8. ^ Some companies have announced that they will be offering the GTX 580 with 3GB RAM.[14]

Support

[edit]

Nvidia announced that after Release 390 drivers, it will no longer release 32-bit drivers for 32-bit operating systems.[16]

Nvidia announced in April 2018 that Fermi will transition to legacy driver support status and be maintained until January 2019.[17]

Counterfeit usage

[edit]

The cards of this generation, particularly the smaller length 550 Ti model, are common cards of choice by counterfeit resellers, who take the cards and illicitly modify the firmware to have them report as more modern cards such as the GTX 1060 and 1050 Ti models. These cards are then sold via eBay, Taobao, Aliexpress and Wish.com by scammers. They may have a minimum of functionality to ensure at a first glance they appear legitimate, but defects caused by the fake BIOS, manufacturing and software issues will almost always cause crashes in modern games and applications, and if not, the performance will still be extremely poor.[18]

See also

[edit]

Notes

[edit]

References

[edit]
[edit]
Revisions and contributorsEdit on WikipediaRead on Wikipedia

GeForce 500 series

View on Grokipedia
from Grokipedia
The GeForce 500 series is a lineup of graphics processing units (GPUs) developed by Nvidia and released starting November 9, 2010, as a refined iteration of the preceding GeForce 400 series based on the same Fermi microarchitecture. Built on a 40 nm manufacturing process, the series emphasized enhancements in power efficiency, thermal management, and DirectX 11 compatibility while addressing criticisms of the 400 series' high power draw and heat output. Key models in the desktop lineup included the flagship GeForce GTX 580, launched at $499 with 512 cores, 1.5 GB of GDDR5 memory on a 384-bit bus, and a base clock of 772 MHz, delivering top-tier performance for 11 gaming and NVIDIA PhysX effects at the time. Mid-range options included the GTX 570, GTX 560 Ti (, 2011), GTX 560 (May 17, 2011), and GTX 550 Ti, offering balanced performance for gaming with support for stereoscopic 3D. The dual-GPU GTX 590, released March 24, 2011, extended this with 1,024 cores and 3 GB GDDR5 across two GF110 chips for enthusiast-class multi-GPU setups, though it retained high power consumption up to 365 W. Entry-level cards such as the GT 520 targeted budget users and HTPC builds, providing 11 acceleration and hardware video decoding with lower power needs around 30 W. The series also encompassed mobile variants under the GeForce 500M designation, powering 2011 notebooks with models like the GTX 580M (up to 384 cores) and GT 540M, delivering up to four times the performance of integrated graphics for HD video, 3D playback, and light gaming. Overall, the GeForce 500 series marked 's maturation of Fermi technology, achieving competitive standing against AMD's HD 5000/6000 series in tessellation-heavy titles while enabling advanced features like Surround for setups, though it faced ongoing scrutiny for elevated TDP ratings up to 365 W on high-end models.

Development and Background

Announcement and Release Timeline

NVIDIA unveiled the GeForce 500 series as part of its broader Fermi architecture announcement during a keynote at the Consumer Electronics Show (CES) 2010 on January 7, 2010, marking the introduction of a new generation of graphics processing units focused on enhanced capabilities. This reveal highlighted the architecture's potential for both gaming and general-purpose computing, setting the stage for subsequent product launches. While the initial Fermi-based consumer products were released under the GeForce 400 series in 2010, the core GeForce 500 series proper emerged later in 2010, beginning with the flagship GeForce GTX 580 on November 9, 2010, followed by the GeForce GTX 570 on December 7, 2010. These high-end models addressed efficiency issues from the 400 series. Subsequent releases included the GeForce GTX 560 Ti on January 25, 2011, positioned as a high-value performance option. Further expansions like the GeForce GTX 550 Ti on March 15, 2011, the GeForce GTX 560 on May 17, 2011, and entry-level GeForce GT 520 on April 13, 2011, populated the lineup for mainstream and budget segments. The dual-GPU GeForce GTX 590 launched on March 24, 2011, as the enthusiast flagship. For mobile platforms, the 500M series was announced on January 5, 2011, at CES 2011, introducing high-performance models like the GeForce GTX 485M along with mainstream options such as GT 540M, GT 550M, and GT 555M, with availability starting in early 2011. Additional 500M variants followed through 2011, powering premium notebooks from major OEMs. Major releases for the GeForce 500 series concluded by mid-2011, as NVIDIA shifted focus toward the successor Kepler architecture, which debuted in the in March 2012.
ModelRelease DateSegment
GeForce GTX 580November 9, 2010High-end Desktop
GeForce GTX 570December 7, 2010High-end Desktop
GeForce GTX 560 TiJanuary 25, 2011Performance Desktop
GeForce GT 545February 28, 2011Entry-level Desktop
GeForce GTX 550 TiMarch 15, 2011Mainstream Desktop
GeForce GTX 590March 24, 2011Enthusiast Desktop
GeForce GT 520April 13, 2011Entry-level Desktop
GeForce GTX 560May 17, 2011Mainstream Desktop
GeForce GTX 485MJanuary 5, 2011High-end Mobile

Architectural Foundations

The GeForce 500 series is built on NVIDIA's Fermi architecture, fabricated using TSMC's 40 nm process node, which enabled a significant increase in transistor density with the initial GF100 GPU featuring 3 billion transistors. This design marked NVIDIA's evolution toward a more advanced unified shader model, where graphics and compute workloads are processed through the same flexible processing units, contrasting with earlier fixed-function pipelines. The architecture organizes processing power into 16 streaming multiprocessors (SMs) per GPU, each containing 32 CUDA cores for a total of up to 512 cores in high-end configurations, allowing for enhanced parallel execution of shaders and general-purpose computing tasks. A key innovation in Fermi was the introduction of hardware support for double-precision floating-point operations, aimed at compute-intensive applications, though in consumer GeForce variants, the peak double-precision throughput is limited to 1/32 the rate of single-precision to differentiate from Tesla products. This throttling ensures compatibility with IEEE 754-2008 standards but prioritizes single-precision efficiency for gaming and graphics rendering. Additionally, the architecture includes support for error-correcting code (ECC) memory, which protects in DRAM, caches, and registers using single-error correction and double-error detection (SECDED); however, ECC is disabled by default in consumer GeForce models to maximize bandwidth and , while it remains optional or enabled in variants for reliability in scientific . Development of the initial GF100 chip encountered significant challenges, including high power draw exceeding 250 W TDP and excessive heat generation, which necessitated aggressive cooling solutions and contributed to launch delays for the precursors. These issues stemmed from the large die size of 529 mm² and dense integration, leading to refine the design in subsequent iterations like the GF110, which reduced the die size slightly to 520 mm² through architectural optimizations and leakage current reductions, improving efficiency without sacrificing core counts. Compared to the predecessor Tesla architecture (e.g., with up to 240 cores), Fermi substantially enhanced parallelism by doubling the core count in flagship models and introducing features like concurrent kernel execution and faster atomic operations, enabling up to 16 kernels to run simultaneously for better utilization in workloads.

Technical Architecture

Core Design and Processing Units

The GeForce 500 series GPUs, built on NVIDIA's Fermi microarchitecture, center their processing capabilities around streaming multiprocessors (SMs), which serve as the fundamental execution units for both graphics rendering and general-purpose computing tasks. Each SM incorporates 32 CUDA cores dedicated to scalar floating-point and integer arithmetic operations, enabling parallel execution of shader programs. Complementing these are 16 load/store units per SM for handling memory accesses, 4 special function units (SFUs) optimized for complex mathematical operations such as reciprocals, square roots, and trigonometric functions, and a dual warp scheduler that simultaneously dispatches instructions to two independent warps of 32 threads each, enhancing instruction-level parallelism and occupancy. This structure allows for efficient handling of diverse workloads, from vertex shading to compute kernels. Texture processing units (TPs) are tightly integrated within the SMs to accelerate and filtering operations, with each SM featuring 4 TPs capable of performing bilinear filtering, , and up to 16x, while supporting both 32-bit floating-point (FP32) and integer data types for versatile texture fetches. In high-end configurations, such as the GTX 580 with 16 SMs, this results in up to 64 TPs across the GPU, enabling high-throughput texture sampling that contributes to improved rendering performance in complex scenes. The raster operating units (ROPs), responsible for final output tasks including depth testing, alpha blending, and (MSAA), vary by model to balance cost and capability; for instance, the GTX 480 employs 48 ROPs, each capable of processing multiple samples per clock cycle to support advanced modes like 8x MSAA. Clock speeds in the GeForce 500 series are tailored to model positioning, with base GPU clocks ranging from 810 MHz in the entry-level GT 520 to 772 MHz in the flagship GTX 580, while shader clocks operate at approximately double the base frequency for enhanced computational throughput. These configurations reflect the Fermi architecture's emphasis on balanced execution pipelines, where unified cores process instructions through dedicated floating-point and pipelines, achieving greater in instruction dispatch and resource utilization compared to preceding generations.

Memory Systems and Interfaces

The GeForce 500 series GPUs predominantly utilize GDDR5 memory, providing high-bandwidth access for graphics and compute workloads, with effective data rates up to 4.0 Gbps in flagship models such as the GTX 580. This memory standard enables efficient handling of large textures and framebuffers, marking an advancement over prior DDR3 options in lower-tier segments. While some entry-level variants like the GT 520 employed DDR3 at lower speeds around 1.8 Gbps effective, the core lineup shifted to GDDR5 for improved performance in 11-era applications. Memory bus widths vary by model tier to balance cost and performance, featuring 384-bit interfaces in high-end GPUs like the GTX 480 and GTX 580 for maximum throughput, 256-bit in mid-range options such as the GTX 560, and narrower 128-bit or 192-bit buses in entry- and mid-tier cards like the GTX 550 Ti. These configurations allow the series to scale bandwidth appropriately, with wider buses supporting intensive rasterization and tasks. The bandwidth is calculated using the : (GB/s) = (effective memory clock in MHz × bus width in bits × 2 for ) / 8 / 1000, though GDDR5's specifics often reference the effective data rate directly; for instance, the GTX 480 achieves 177.4 GB/s with its 3.7 Gbps effective clock and 384-bit bus. All GeForce 500 series GPUs employ a 2.0 x16 interface as the standard connection to the host system, delivering up to 8 GB/s bidirectional bandwidth per direction to facilitate data transfer between the GPU and CPU memory. These GPUs are compatible with PCIe 3.0 slots but operate at PCIe 2.0 speeds, with minimal real-world performance impact due to the bandwidth available. The memory hierarchy includes per-streaming multiprocessor (SM) L1 caches integrated with shared memory resources, totaling 64 KB configurable as 16 KB L1 cache plus 48 KB shared memory or vice versa, to accelerate local loads, stores, and texture fetches within each SM. A unified L2 cache, varying by model (e.g., 768 KB in high-end GPUs like the GTX 580 or 512 KB in mid-range models like the GTX 560), spans the entire GPU, servicing all global memory requests from the SMs and interfacing with the external GDDR5 DRAM, thereby reducing latency for coherent data access across processing units. This design enhances overall efficiency by caching frequently accessed data closer to the compute cores, integrating seamlessly with the Fermi architecture's execution hardware.

Product Lineup

Desktop GeForce 500 Series GPUs

The desktop GeForce 500 series GPUs formed NVIDIA's second-generation Fermi-based graphics cards for personal computers, targeting gamers and content creators seeking DirectX 11 support and advanced visual effects. These cards emphasized improved efficiency over the initial Fermi lineup while maintaining compatibility with multi-GPU setups via (SLI) technology, allowing up to three cards in high-end configurations for enhanced performance. The high-end segment featured flagship models optimized for demanding applications and extreme resolutions. The GTX 580, launched on November 9, 2010, included 512 cores and 1.5 GB of GDDR5 memory on a 384-bit interface, positioning it as the series' top performer with full hardware tessellation capabilities. The GTX 570, released on December 7, 2010, offered 480 cores and 1.25 GB of GDDR5 memory, serving as a slightly more power-efficient alternative while retaining similar architectural strengths. The dual-GPU GTX 590, released on March 24, 2011, featured 1,024 cores and 3 GB of GDDR5 across two GF110 chips, targeting enthusiast-class multi-GPU setups with a TDP of 365 W. Mid-range options balanced cost and capability for mainstream gaming rigs. The GeForce GTX 560 Ti, introduced on January 25, 2011, provided 384 cores and 1 GB of GDDR5 memory, aimed at gaming with strong 11 feature support. Following it, the GeForce GTX 560 arrived on May 17, 2011, with 336 cores and 1 GB GDDR5, targeting budget-conscious enthusiasts. The GeForce GTX 550 Ti, launched March 15, 2011, featured 192 cores and 1 GB GDDR5, focusing on entry-to-mid-level 11 acceleration. Entry-level cards catered to basic multimedia and light gaming needs. The GeForce GT 520, released April 13, 2011, had 48 CUDA cores and 1 GB of DDR3 memory, emphasizing low power draw for integrated upgrades. Overall, the lineup positioned NVIDIA competitively against AMD's Radeon HD 6000 series, prioritizing enthusiast features like SLI scalability for multi-monitor and high-fidelity setups.

Mobile GeForce 500M Series GPUs

The Mobile GeForce 500M Series GPUs were designed specifically for laptops, adapting the Fermi architecture to balance performance with power efficiency and thermal limitations inherent to portable devices. Announced on January 5, 2011, at CES, this lineup emphasized optimizations for battery life and heat dissipation, including integration with NVIDIA Optimus technology, which seamlessly switches between the discrete GPU and integrated graphics to extend runtime during light tasks. These GPUs featured reduced clock speeds compared to their desktop counterparts to manage thermal output in confined laptop chassis. The high-end models targeted gaming and workloads in premium laptops. The GTX 580M, with 384 cores, up to 2 GB of GDDR5 on a 256-bit bus, and a TDP of 100 W, was positioned as the flagship for high-resolution gaming, launching on June 28, 2011. The GTX 570M offered 336 cores, 1.5 GB of GDDR5 on a 192-bit bus, and a TDP up to 100 W, released on August 18, 2011, providing strong performance for and while supporting dynamic clock throttling to prevent overheating. Mid-range options focused on mainstream laptops, delivering capable graphics for gaming without excessive power draw. The GTX 560M, with 192 cores, 1.5 GB of GDDR5 on a 192-bit bus, and a TDP of 75 W, arrived on May 30, 2011, incorporating improved efficiency for sustained performance under thermal constraints. The GT 550M, featuring 144 cores, 1-2 GB of GDDR5 memory on a 128-bit bus, and a TDP of 30 W, was released in January 2011. Entry-level GPUs in the series catered to ultrabooks and portables, prioritizing low power over peak . The GT 555M included 144 cores, 1-2 GB of DDR3 or GDDR5 memory on a 128-bit bus, and a TDP of 35 W, released in 2011. The GT 540M had 96 cores, 1-2 GB of DDR3 or GDDR5 on a 128-bit bus, and a 32 W TDP, also launching in 2011. Completing the tier, the GT 525M featured 64-96 cores, 1 GB of DDR3 on a 128-bit bus, and a 23 W TDP, introduced in 2011. The GT 520M had 48 cores, 1 GB of DDR3 on a 64-bit bus, and a 12 W TDP, released in 2011. Across the series, thermal and was critical, with TDPs ranging from 12 for low-power models like the GT 520M to 100 for high-end models like the GTX 580M. Dynamic clock throttling adjusted frequencies in real-time based on temperature and battery status, ensuring stability in varied environments while leveraging Optimus for up to 2x battery life gains during non-GPU-intensive use.
ModelCUDA CoresMemoryBus WidthTDP (W)Release Date
GTX 580M3842 GB GDDR5256-bit100Jun 28, 2011
GTX 570M3361.5 GB GDDR5192-bit100Aug 18, 2011
GTX 560M1921.5 GB GDDR5192-bit75May 30, 2011
GT 550M1441-2 GB GDDR5128-bit30Jan 2011
GT 555M1441-2 GB DDR3/GDDR5128-bit352011
GT 540M961-2 GB DDR3/GDDR5128-bit322011
GT 525M64-961 GB DDR3128-bit232011
GT 520M481 GB DDR364-bit122011

Features and Capabilities

Graphics and Compute APIs

The GeForce 500 series, based on NVIDIA's Fermi architecture, provided full support for from its launch in late , enabling developers to leverage advanced rendering techniques such as for more detailed geometry and compute shaders for parallel processing tasks on the GPU. This compatibility marked a significant advancement over prior generations, allowing for enhanced visual fidelity in games and applications through features like improved lighting, shadows, and particle effects processed directly on the hardware. The series also achieved compliance with 4.0, introduced via driver updates shortly after release, which included core support for shaders and shaders to facilitate complex models and procedural generation. Extensions such as GL_EXT_texture_array and GL_ARB_gpu_shader5 further expanded capabilities for advanced techniques, enabling more efficient handling of multi-textured surfaces and uniform buffer objects in professional and gaming workloads. For compute workloads, the GeForce 500 series supported 3.0 and later versions, corresponding to compute capability 2.0 (for GF110-based models like the GTX 580) and 2.1 (for GF106-based models like the GTX 560), which facilitated general-purpose GPU (GPGPU) for tasks including physics simulations, scientific modeling, and image processing. This architecture's and enhanced memory access patterns improved efficiency in parallel algorithms, making it suitable for accelerating non-graphics computations in software like or custom simulations. Cross-platform compute was enabled through OpenCL 1.0 support, available for all GeForce 8-series and later GPUs including the 500 series, allowing developers to write portable kernel code for heterogeneous computing environments without reliance on vendor-specific APIs. This integration complemented CUDA by providing an open standard for compute tasks, though performance optimizations were often tied to NVIDIA's driver implementations. Additionally, the GeForce 500 series offered hardware-accelerated PhysX support, utilizing the GPU's processing units as a dedicated co-processor in higher-end models to enhance real-time physics simulations in games, such as destructible environments and cloth dynamics, delivering up to several times the performance of CPU-based calculations. This feature was particularly impactful in titles optimized for NVIDIA hardware, bridging graphics rendering and physics computation seamlessly.

Display and Connectivity Options

The GeForce 500 series GPUs primarily featured dual-link DVI-D outputs capable of supporting resolutions up to 2560x1600, enabling high-definition digital flat-panel displays without compression. These outputs were standard across most models, providing robust compatibility for contemporary monitors and projectors at the time of release. Additionally, integrated RAMDACs allowed for analog resolutions up to 2048x1536 at 85 Hz, facilitating connectivity to legacy VGA displays through DVI-to-VGA adapters. HDMI 1.4a connectivity was included via a mini- on the majority of cards, supporting video playback with HDCP 1.3 for protected content such as Blu-ray and broadcast HD streams. This implementation ensured secure transmission of high-definition audio and video, including 7.1-channel , though the GPU's output capabilities limited resolutions to at 60 Hz. Higher-end models, such as variants of the GTX 580, additionally offered 1.1a support, expanding options for multi-stream transport and adaptive sync precursors. Multi-monitor configurations were a key strength, with most cards providing up to three simultaneous outputs per GPU for independent displays. 's Mosaic technology enabled seamless spanning across up to four displays in multi-GPU setups, ideal for productivity and immersive workflows. For gaming, Surround allowed bezel-corrected spanning across multiple screens, enhancing immersion in titles by treating connected displays as a single ultra-wide canvas, typically requiring SLI for three-monitor configurations on single-output-limited cards. This combination of physical ports and software features positioned the series as versatile for both single- and multi-display environments prevalent in 2010-2012 systems.

Performance Characteristics

Benchmark Comparisons

The GeForce 500 series GPUs provided solid performance in synthetic benchmarks, particularly in 11-focused tests that highlighted their Fermi architecture's strengths in and processing. In 11's Performance preset, the top-end GeForce GTX 580 scored around 6000 points, surpassing the AMD HD 6970's score of approximately 5300 points by 13%, while also edging out the previous-generation GeForce GTX 570 at about 5700 points. In the more demanding 11 Extreme preset, the GTX 580 reached graphics sub-scores of 1950, compared to 1800 for the HD 6970, demonstrating Nvidia's edge in compute-intensive scenarios. These results positioned the 500 series as competitive with AMD's HD 6000 lineup in balanced synthetic workloads, though aggregate user benchmarks showed the GTX 580 only 3% faster overall than the HD 6970 across varied tests. In real-world gaming at 1920x1080 resolution with high to ultra settings, the GeForce 500 series delivered playable frame rates in 11 titles, often benefiting from Nvidia's superior performance. The GTX 580 averaged 52 FPS in at Very High settings with DX11 enabled, providing smooth gameplay that highlighted the series' improvements over the 400 series, where the GTX 480 managed only about 40 FPS under similar conditions—a 30% uplift driven by higher clock speeds and refined shaders. Similarly, the mid-range GTX 560 Ti achieved 40-50 FPS in at High settings, competitive with the HD 6870 but trailing slightly in pure rasterization-heavy scenes without heavy geometry effects. Against the , the 500 series held advantages in -intensive games like (up to 15% faster for GTX 580 vs. HD 6970), but outperformed by up to 30% in rasterization-focused titles such as due to Nvidia's architectural optimizations. Compute workloads further underscored the 500 series' CUDA optimizations, with the GTX 580 showing roughly 20% better performance than the GTX 480 in -compatible benchmarks like early LuxMark versions, thanks to enhanced double-precision support and driver maturity—though still trailing in raw throughput. Overall, the series offered 20-50% gains over the GeForce 400 lineup in DX11-specific games, making it a worthwhile refresh for enthusiasts targeting emerging features.

Power Efficiency and Thermal Management

The GeForce 500 series graphics processing units, built on NVIDIA's 40 nm Fermi architecture, exhibited varied power consumption profiles, with models like the GTX 580 rated at a (TDP) of 244 W, addressing some inefficiencies from the prior generation through optimized die layout and reduced leakage on the same process node. This TDP necessitated robust power supplies but represented an improvement in over earlier Fermi designs, with system-level draw typically under 400 W in gaming configurations. Efficiency metrics for the series highlighted progressive improvements over the preceding , with models like the GTX 560 Ti achieving approximately 21% better in gaming workloads, thanks to architectural tweaks such as rearranged shader processing and better . This shift emphasized sustainable resource usage, allowing mid-range cards to balance output with lower average consumption—around 170 W TDP for the GTX 560 Ti—without sacrificing competitiveness in benchmarks like or . In contrast to the 400 series' roughly 10-15% lower perf/watt ratios in similar tests, the 500 series prioritized conceptual advancements in dynamic to mitigate the 40 nm process's inherent overhead. Thermal management in the GeForce 500 series relied on reference designs featuring dual-slot coolers with vapor chamber bases and dual axial fans to dissipate heat from the large die area, with models like the GTX 580 typically reaching junction temperatures under 90°C under sustained loads. Third-party add-in-board (AIB) partners enhanced this with custom solutions; for instance, EVGA's implementations incorporated advanced paths and bearing technologies in their FTW variants to reduce noise and extend fan longevity while maintaining stock thermals below 80°C in optimized cases. headroom was generally limited to 15-20% core clock uplifts on due to the 40 nm process's heat generation, with users reporting stability caps around 95°C to avoid throttling, underscoring the series' sensitivity to ambient conditions and . In mobile variants, the GeForce 500M series employed significantly lower TDPs—such as 100 W for the GTX 580M and 75 W for the GTX 560M—enabled by aggressive voltage scaling and clock binning tailored for power envelopes, yielding 20-30% superior efficiency compared to desktop counterparts in battery-constrained scenarios. This allowed for extended runtime in HD gaming and tasks, with integrated dynamic frequency adjustments ensuring scaled proportionally to thermal budgets, often outperforming integrated by factors of 3-5x at comparable power draws.

Support and Legacy

Driver and Software Support

The GeForce 500 series GPUs, built on NVIDIA's Fermi architecture, received initial driver support via ForceWare release 262.99, which launched in November 2010 alongside the GeForce GTX 580 and provided foundational compatibility with 11 features and hardware acceleration. NVIDIA continued to release drivers for the series through its evolving ForceWare and GeForce branches, including Game Ready optimizations tailored for new titles, with support extending to the R390 branch—the final such release being version 390.77 in January 2018. In April 2018, the Fermi architecture transitioned to legacy status under NVIDIA's unified driver model, restricting updates to critical fixes only, which were provided through January 2019; no new features or performance enhancements followed. The NVIDIA Control Panel, distributed with these drivers, allowed users to adjust custom display resolutions, configure (SLI) for multi-GPU setups, and integrate with the CUDA toolkit for workloads. GeForce Experience, unveiled in open beta in January 2013, delivered automated game optimization profiles, automatic driver updates, and in-game overlay tools for recording and streaming, with full retroactive compatibility for the GeForce 500 series to enhance usability on existing hardware.

Discontinuation and End-of-Life

The production of the GeForce 500 series GPUs, based on the , effectively ceased by early 2013 as shifted focus to the successor Kepler architecture, with the GeForce GTX 680 launching in March 2012 to replace high-end models like the GTX 580. The flagship GTX 580 model specifically saw production halted in 2012, marking the beginning of the phase-out for the entire lineup. Retail availability for new GeForce 500 series cards declined sharply by late 2012, with remaining inventory primarily cleared through original equipment manufacturers (OEMs) for pre-built systems rather than standalone retail channels. Driver support for the GeForce 500 series transitioned to legacy status in April 2018, with ceasing new Game Ready driver releases at that time and limiting updates to critical bug fixes until 2019. No further security patches or optimizations have been provided for consumer GeForce 500 series products beyond this period, though professional Fermi-based variants received extended maintenance until the end of in some cases. As of 2025, these GPUs remain compatible with older operating systems and 11-era applications but lack support for modern features such as hardware-accelerated ray tracing or DLSS, limiting their viability to light gaming, basic compute tasks, or legacy software emulation. NVIDIA's general product recycling programs, which handle e-waste from 40 nm process GPUs like those in the GeForce 500 series, emphasize and certified disposal to recover metals and components, with 100% of eligible employee-issued hardware processed accordingly. In 2025, used GeForce 500 series cards, such as the GTX 580, hold low resale value on secondary markets, typically ranging from $50 to $70 depending on condition, reflecting their amid rapid advancements in GPU .

Issues and Market Impact

Counterfeit Products and Authenticity

The for the discontinued GeForce 500 series has seen products, particularly as demand grows among budget users and vintage hardware enthusiasts. These fakes often involve rebadging or modifying lower-performance cards to appear as higher-end models from the series. However, a more common issue is the repurposing of genuine 500 series cards—such as the GTX 550 Ti—by flashing modified to emulate newer models like the GTX 1050 Ti, which reduces the availability of authentic units and drives up prices for collectors. Authentic GeForce 500 series cards can be identified through several verification methods. NVIDIA's official stickers, often featuring holographic elements that shift under light, are a key visual indicator; fakes typically use poor-quality replicas lacking this security feature. Running software reveals discrepancies in sensor readings, such as mismatched core counts or configurations, often prefixing the device name with "[FAKE]" for affected cards. Serial numbers printed on the card's backplate or PCB can be cross-checked against NVIDIA's validation tool on their support site, where invalid or duplicated entries signal potential counterfeits. These fakes have impacted secondary markets like , where listings for discontinued hardware often include fraudulent items. has pursued legal actions against operations, collaborating with platforms and authorities to seize fake inventory and shut down sellers, though enforcement challenges persist in regions like . As of early 2025, GPU issues remain a concern in the for hardware, with contributing to scams. Buyers are advised to purchase from authorized resellers or trusted platforms with buyer protection, and to verify authenticity by extracting the VBIOS using and computing its against official versions available from add-in-board manufacturers like EVGA or .

Manufacturing and Reliability Concerns

The GeForce 500 series graphics processing units, built on NVIDIA's Fermi architecture, were fabricated using 40 nm process node, which suffered from initial immaturity and low yields during early production in 2010. These manufacturing challenges, stemming from difficulties in layer connections and overall process stability at , contributed to significant delays in the series' launch and raised concerns about the long-term reliability of the chips under stress. A primary reliability issue arose from the high thermal output of the flagship GeForce GTX 480, rated at a 250 W TDP, which often resulted in operating temperatures reaching the low to mid-90s during 3D workloads. The GPU was engineered to thermal throttle around 105°C to safeguard against damage, leading to frequent performance reductions during extended gaming or compute-intensive tasks, particularly in poorly ventilated cases. This design choice, while preventing immediate hardware failure, accelerated wear on components due to sustained high temperatures and aggressive cooling demands. The intense heat necessitated high fan speeds—often exceeding 70% RPM under load—which generated substantial and placed strain on fan bearings and motors. User reports indicated common fan failures within two years of heavy usage, sometimes requiring replacement or full card returns, as the constant high-RPM operation led to premature degradation. These thermal management flaws, combined with the 40 nm limitations, contributed to elevated stress on modules (VRMs) in early models, though iterated on designs to mitigate some risks in later revisions. Initial driver releases for the Fermi-based GeForce 500 series in 2010 exhibited instability, including crashes and visual glitches in 11 titles, which addressed through updates in 2011 to improve compatibility and reduce artifacting. Overall, these production and thermal concerns led to a tarnished reputation for the series in contemporary reviews, with higher power draw and heat compared to AMD's HD 5000 equivalents exacerbating perceptions of inferior reliability.

References

  1. https://www.techpowerup.com/gpu-specs/geforce-gtx-580.c270
  2. https://nvidianews.nvidia.com/_gallery/download_pdf/54481926f6091d273500019d/
  3. https://www.techpowerup.com/gpu-specs/geforce-gtx-590.c281
  4. https://nvidia.custhelp.com/app/answers/detail/a_id/4656/~/list-of-fermi-series-geforce-gpus
  5. https://nvidianews.nvidia.com/news/nvidia-geforce-500m-series-gpus-power-top-notebooks-of-2011
  6. https://nvidianews.nvidia.com/news/nvidia-geforce-gtx-590-is-world-s-fastest-graphics-card
  7. https://hardforum.com/threads/live-from-nvidias-ces-press-event.1484456/post-1035156376
  8. https://www.techpowerup.com/127435/new-nvidia-fermi-class-quadro-launches-the-era-of-computational-visualization
  9. https://www.techpowerup.com/gpu-specs/geforce-gtx-570.c269
  10. https://nvidianews.nvidia.com/news/the-new-nvidia-geforce-gtx-560-ti-gpu-pwns-the-gamer-s-sweet-spot
  11. https://www.techpowerup.com/gpu-specs/geforce-gtx-550-ti.c274
  12. https://www.techpowerup.com/gpu-specs/geforce-gtx-560.c287
  13. https://www.techpowerup.com/gpu-specs/geforce-gt-520.c285
  14. https://www.notebookcheck.net/CES-2011-Nvidia-launch-GeForce-GT-500M-serie-and-GTX-485M-GPU.43895.0.html
  15. https://www.techpowerup.com/282478/nvidia-to-end-kepler-support-with-r470-drivers-9-years-after-release-support-roadmap
  16. https://www.nvidia.com/content/pdf/fermi_white_papers/nvidiafermicomputearchitecturewhitepaper.pdf
  17. https://www.cs.cmu.edu/afs/cs/academic/class/15869-f11/www/readings/wittenbrink11_fermi.pdf
  18. https://www.nvidia.com/content/PDF/fermi_white_papers/T.Halfhill_Looking_Beyond_Graphics.pdf
  19. https://www.nvidia.com/content/pdf/fermi_white_papers/nvidia_fermi_compute_architecture_whitepaper.pdf
  20. https://www.nvidia.com/content/PDF/fermi_white_papers/N.Brookwood_NVIDIASolvesTheGPUComputingPuzzle.pdf
  21. https://www.techpowerup.com/gpu-specs/geforce-gtx-480.c268
  22. https://www.evga.com/products/specs/gpu.aspx?pn=B89674F6-FED6-464E-B0DC-B9B13929F8E8
  23. https://www.techpowerup.com/gpu-specs/?f=generation_NVIDIA%2BGeForce%2B500
  24. https://www.nvidia.com/docs/IO/100940/GeForce_GTX_580_Datasheet.pdf
  25. https://www.techpowerup.com/gpu-specs/geforce-gtx-560-ti.c273
  26. https://nvidianews.nvidia.com/news/nvidia-introduces-new-geforce-gtx-560-gpu-and-faster-geforce-r275-drivers
  27. https://nvidianews.nvidia.com/news/geforce-gtx-550-ti-and-3d-vision-redefine-pc-gaming-at-149-each
  28. https://www.notebookcheck.net/NVIDIA-GeForce-GTX-580M.56636.0.html
  29. https://www.techpowerup.com/gpu-specs/geforce-gtx-570m.c937
  30. https://www.techpowerup.com/gpu-specs/geforce-gtx-560m.c936
  31. https://www.notebookcheck.net/NVIDIA-GeForce-GTX-560M.48313.0.html
  32. https://www.techpowerup.com/gpu-specs/geforce-gt-555m.c1494
  33. https://www.notebookcheck.net/NVIDIA-GeForce-GT-555M.41933.0.html
  34. https://www.techpowerup.com/gpu-specs/geforce-gt-540m.c702
  35. https://www.notebookcheck.net/NVIDIA-GeForce-GT-540M.41715.0.html
  36. https://www.techpowerup.com/gpu-specs/geforce-gt-525m.c1490
  37. https://www.notebookcheck.net/NVIDIA-GeForce-GT-525M.43889.0.html
  38. https://www.techpowerup.com/gpu-specs/geforce-gt-520m.c1488
  39. https://www.techpowerup.com/gpu-specs/geforce-gtx-580m.c938
  40. https://nvidianews.nvidia.com/news/nvidia-and-epic-games-showcase-dx11-partnership-at-game-developers-conference
  41. https://www.nvidia.com/en-us/drivers/windows/197_45/win7_winvista_64bit_197-45_whql/
  42. https://developer.download.nvidia.com/cg/gp5fp.html
  43. https://developer.nvidia.com/cuda-gpus
  44. https://www.nvidia.com/en-us/drivers/details/33461/
  45. https://www.nvidia.com/en-us/drivers/physx/9_12_0613/physx-9-12-0613-driver/
  46. https://www.evga.com/products/specs/gpu.aspx?pn=E01AB255-C491-48D6-9441-B4778F2459DE
  47. https://www.nvidia.com/en-us/technologies/nvidia-mosaic/
  48. https://www.gigabyte.com/fileupload/us/MicroSite/271/NVIDIA-GTX500-series.html
  49. https://www.fudzilla.com/news/graphics/21184-radeon-hd-6970-slower-than-gtx-580-in-3dmark-2011
  50. https://gpu.userbenchmark.com/Compare/Nvidia-GTX-580-vs-AMD-HD-6970/3150vsm7712
  51. https://pcper.com/2011/09/battlefield-3-beta-performance-testing-and-image-quality-evaluation-day-1/3/
  52. https://www.techspot.com/review/379-crysis-2-performance/page4.html
  53. https://www.techspot.com/review/458-battlefield-3-performance/page3.html
  54. https://www.phoronix.com/news/MTEyNTI
  55. https://www.crn.com/news/components-peripherals/229100228/nvidia-launches-geforce-560-ti-graphics-card
  56. https://www.anandtech.com/show/4135/nvidias-geforce-gtx-560-ti-upsetting-the-250-market/16
  57. https://www.evga.com/products/productlist.aspx?type=0&family=GeForce%20500%20Series%20Family
  58. https://www.techpowerup.com/134253/nvidia-intros-geforce-262-99-whql-drivers-for-geforce-gtx-580
  59. https://www.nvidia.com/en-us/drivers/details/130633/
  60. https://nvidia.custhelp.com/app/answers/detail/a_id/4654
  61. https://www.techpowerup.com/179429/nvidia-geforce-experience-open-beta-launched
  62. https://www.xda-developers.com/counterfeit-gpus-on-the-rise/
  63. https://www.nvidia.com/en-us/geforce/forums/gfn-general-chat/20/436891/check-warranty-and-serial-number-for-gpu/
  64. https://videocardz.com/newz/nvidia-wants-fake-geforce-gpus-to-disappear-from-the-market
  65. https://www.techpowerup.com/gpuz/
  66. https://hardforum.com/threads/nvidias-real-problem-the-next-generation.1506511/post-1035513663
  67. https://nvidia.custhelp.com/app/answers/detail/a_id/2602/~/what-are-the-normal-3d-operating-temperatures-for-geforce-gtx-480%252F470-graphics
  68. https://bjorn3d.com/2010/06/gtx-480-thermal-study/
  69. https://hardwarecanucks.com/forum/threads/gtx-480-fan-problem.35686/
  70. https://forums.tomshardware.com/threads/nvidia-gtx-480-crash-freeze-dynamically.766168/post-6905633
  71. https://www.anandtech.com/show/2977/nvidias-geforce-gtx-480-and-gtx-470-6-months-late-was-it-worth-the-wait/8
Add your contribution
Related Hubs
Contribute something
User Avatar
No comments yet.