NVIDIA GeForce GTX 580 vs NVIDIA GeForce RTX 5090 D V2 Comparison
NVIDIA GeForce GTX 580
GeForce RTX 5090 D V2
PERFORMANCE BENCHMARKS
Analysis: NVIDIA GeForce GTX 580 vs NVIDIA GeForce RTX 5090 D V2
NVIDIA’s GeForce RTX 5090 D V2 and the GeForce GTX 580 represent two distinct eras of GPU design, separated by over a decade of architectural evolution. The data shows two products with radically different benchmark profiles, where the RTX 5090 D V2 achieves a score of 16504 in 3DMark Steel Nomad DX12, while the GTX 580 posts 15283 in Geekbench OpenCL. These are not directly comparable tests, but the percentile rankings tell a clear story: the RTX 5090 D V2 sits at the 59th percentile among all GPUs, while the GTX 580 sits at the 58th percentile, placing them in a similar overall performance tier despite their generational gap. The nearest rivals for the RTX 5090 D V2 include the NVIDIA T400 with an average score of 16508 (a 0% delta) and the AMD Radeon PRO W7500 at 16415 (0.5% behind), while the GTX 580’s closest competitor is the NVIDIA GeForce RTX 2060 at 15290 (0% delta) and the AMD Radeon 680M at 15270 (0.1% ahead).
Head-to-Head Benchmarks
The benchmark results indicate that the RTX 5090 D V2 holds a decisive lead in raw compute throughput, but the GTX 580 is not without its own statistical merits. In the only available 3DMark Steel Nomad DX12 test, the RTX 5090 D V2 scores 16504, which is 7.9% higher than the GTX 580’s Geekbench OpenCL score of 15283. This gap is modest when viewed purely as a percentage, but the underlying specifications reveal why the newer card dominates in modern workloads. The RTX 5090 D V2 delivers 104.8 TFLOPS of FP32 compute, a figure that dwarfs the GTX 580’s 1.581 TFLOPS by a factor of roughly 66. Similarly, pixel rate stands at 423.6 GPixel/s for the RTX 5090 D V2 versus 24.70 GPixel/s for the GTX 580, and texture rate is 1,636.8 GTexel/s compared to 49.41 GTexel/s.
Looking at the nearestRivals data, the RTX 5090 D V2’s score of 16504 is nearly identical to the NVIDIA T400’s 16508, with a delta of 0%, meaning the two are statistically tied in this metric. It also edges out the AMD Radeon PRO W7500 by 0.5% and the NVIDIA RTX PRO 6000 Blackwell by 0.6%. The GTX 580, meanwhile, posts 15283, which is essentially level with the NVIDIA GeForce RTX 2060’s 15290 (0% delta) and just 0.1% behind the AMD Radeon 680M. This suggests that in the Geekbench OpenCL test, the GTX 580 performs on par with mid-range GPUs from much later generations, evidence of its legacy architecture’s efficiency in certain compute tasks.
Where the RTX 5090 D V2 wins decisively is in memory bandwidth and capacity. It offers 24 GB of GDDR7 memory on a 384-bit bus, yielding 1.34 TB/s of bandwidth, versus the GTX 580’s 1536 MB of GDDR5 on the same 384-bit bus but with only 192.4 GB/s. That is a 6.9x increase in bandwidth, which directly impacts texture-heavy and high-resolution workloads. The GTX 580 does have one advantage in the head-to-head: its power draw. The data shows a TDP of 244 W for the GTX 580 versus 575 W for the RTX 5090 D V2, and while no performance-per-watt metric is provided, the older card’s lower thermal footprint is evident from the specifications alone. However, in every raw performance category measured—FP32, pixel rate, texture rate, and memory bandwidth—the RTX 5090 D V2 is the clear winner, and the benchmark scores reflect that.
FAQ
Q: How does the RTX 5090 D V2’s benchmark score compare to its nearest rivals?
A: The RTX 5090 D V2 scores 16504 in 3DMark Steel Nomad DX12, which is statistically tied with the NVIDIA T400 (16508, 0% delta) and 0.5% ahead of the AMD Radeon PRO W7500 (16415). It also leads the NVIDIA RTX PRO 6000 Blackwell (16408) by 0.6%.
Q: What is the GTX 580’s closest competitor in terms of average benchmark score?
A: The GTX 580 scores 15283 in Geekbench OpenCL, which is essentially level with the NVIDIA GeForce RTX 2060 (15290, 0% delta) and 0.1% ahead of the AMD Radeon 680M (15270). It trails the NVIDIA GeForce RTX 3050 OEM (15199) by 0.6% and the AMD Radeon RX 7600 (15171) by 0.7%.
Q: Which GPU has a higher transistor count, and what does that imply?
A: The RTX 5090 D V2 contains 92,200 million transistors on a 5 nm process, compared to the GTX 580’s 3,000 million transistors on a 40 nm process. The newer card’s transistor density is 122.9M per mm² versus 5.8M per mm², indicating a far more complex architecture.
Q: Is there any benchmark where the GTX 580 comes close to the RTX 5090 D V2?
A: No direct head-to-head benchmarks are available, but the percentile rankings are close: the RTX 5090 D V2 is at the 59th percentile and the GTX 580 at the 58th percentile. In raw compute metrics, the RTX 5090 D V2 leads by massive margins, such as 104.8 TFLOPS versus 1.581 TFLOPS in FP32.
Q: What memory specifications differentiate the two GPUs?
A: The RTX 5090 D V2 uses 24 GB of GDDR7 with a 384-bit bus and 1.34 TB/s bandwidth, while the GTX 580 uses 1536 MB of GDDR5 with a 384-bit bus and 192.4 GB/s bandwidth. Both share the same bus width, but the newer card has vastly more capacity and bandwidth.
Q: How do their release dates and production statuses compare?
A: The RTX 5090 D V2 was released on 2025-08-14 and is marked as Active, while the GTX 580 was released on 2010-11-08 and is End-of-life. The RTX 5090 D V2 is part of the GeForce 50 generation, whereas the GTX 580 belongs to the GeForce 500 generation.
Where Each One Wins
The RTX 5090 D V2 wins in every scenario that demands raw computational power and modern feature support. Its 104.8 TFLOPS FP32 performance makes it a superior choice for compute-heavy applications like scientific simulation, AI inference, and high-end content creation, where shader and tensor core throughput are critical. The 24 GB memory capacity and 1.34 TB/s bandwidth allow it to handle large datasets and high-resolution textures that would exhaust the GTX 580’s 1536 MB frame buffer almost immediately. For gaming at high resolutions or with ray tracing enabled, the RTX 5090 D V2’s 170 RT cores and 680 tensor cores provide dedicated hardware that the GTX 580 lacks entirely, as it has no RT or tensor cores listed. The newer card also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, ensuring compatibility with the latest APIs, while the GTX 580 only reaches DirectX 12 (11_0) and has no Vulkan support listed.
The GTX 580 wins in scenarios where power efficiency and legacy software compatibility are priorities. Its TDP of 244 W is less than half of the RTX 5090 D V2’s 575 W, making it a more manageable option for older power supplies or constrained thermal environments—the suggested PSU is 550 W versus 950 W for the newer card. The GTX 580’s 48 ROPs, while far fewer than the RTX 5090 D V2’s 176, are paired with a simpler architecture that may deliver predictable behavior in older DirectX 11 titles, which aligns with its DirectX 12 (11_0) API support. Its dual-DVI and mini-HDMI 1.3a outputs cater to legacy monitors, whereas the RTX 5090 D V2 offers one HDMI 2.1b and three DisplayPort 2.1b connections, which require modern displays. For users running software that has not been updated in years, the GTX 580’s Fermi 2.0 architecture might be a more stable choice, though the data does not provide explicit compatibility metrics.
Specification Differences
The two GPUs differ across nearly every measurable specification. The RTX 5090 D V2 uses a GB202 chip on a 5 nm process, while the GTX 580 uses a GF110 chip on a 40 nm process. Transistor counts are 92,200 million versus 3,000 million, and die sizes are 750 mm² versus 520 mm². Memory configurations are starkly different: 24 GB of GDDR7 at 1750 MHz (28 Gbps effective) with 1.34 TB/s bandwidth versus 1536 MB of GDDR5 at 1002 MHz (4 Gbps effective) with 192.4 GB/s bandwidth. The RTX 5090 D V2 has 21760 shading units, 680 TMUs, and 176 ROPs, while the GTX 580 has 512 shading units, 64 TMUs, and 48 ROPs. RT cores and tensor cores are present on the newer card (170 and 680, respectively) but are null on the older card. Clock speeds also differ: the RTX 5090 D V2 has a base clock of 2017 MHz and boost of 2407 MHz, while the GTX 580 has no base or boost clock listed, only a memory clock. Power requirements are 575 W TDP with a 950 W suggested PSU for the RTX 5090 D V2, versus 244 W TDP and a 550 W suggested PSU for the GTX 580. The bus interface is PCIe 5.0 x16 on the newer card versus PCIe 2.0 x16 on the older one. Display outputs are 1x HDMI 2.1b and 3x DisplayPort 2.1b versus 2x DVI and 1x mini-HDMI 1.3a. Physical dimensions are 304 mm x 137 mm x 48 mm for the RTX 5090 D V2 and 267 mm x 111 mm for the GTX 580 (width not specified).
Architecture Differences
The architectural divide is fundamental. The RTX 5090 D V2 is built on Blackwell 2.0, a modern architecture that supports 12 Ultimate (12_2) DirectX features, Vulkan 1.4, and OpenGL 4.6. It includes dedicated ray tracing cores (170) and tensor cores (680), which enable hardware-accelerated ray tracing and AI-based features like DLSS—none of which are present on the GTX 580. The older card uses Fermi 2.0, which predates these technologies and offers only DirectX 12 (11_0) support, with no Vulkan API listed. The RTX 5090 D V2’s FP16 performance matches its FP32 at 104.8 TFLOPS (1:1 ratio), indicating a unified compute pipeline, while the GTX 580 has no FP16 data provided. The transistor density difference—122.9M per mm² versus 5.8M per mm²—reflects the shift from planar to FinFET and then to gate-all-around processes, enabling far more complex logic in the same physical space. The memory architecture also differs: GDDR7 on the newer card supports higher data rates per pin (28 Gbps effective) compared to GDDR5’s 4 Gbps, and while both use a 384-bit bus, the newer memory technology achieves 1.34 TB/s versus 192.4 GB/s. The RTX 5090 D V2’s 680 TMUs allow a texture rate of 1,636.8 GTexel/s, a 33x improvement over the GTX 580’s 49.41 GTexel/s. The pixel rate follows suit at 423.6 GPixel/s versus 24.70 GPixel/s.
The Verdict
The data points to a straightforward conclusion for most users: the RTX 5090 D V2 is the superior performer in nearly every measurable category, from compute throughput to memory bandwidth to feature support. Its benchmark score of 16504 places it in the 59th percentile, and its nearest rivals—like the NVIDIA T400 and AMD Radeon PRO W7500—are not mainstream gaming cards, indicating that it competes in a professional or enthusiast tier. The GTX 580, with a score of 15283 and a 58th percentile ranking, is statistically close in overall position, but its nearest rivals (RTX 2060, Radeon 680M) are far older or lower-end, suggesting it is a relic that only holds up in legacy workloads. Users who need maximum performance for modern gaming, 3D rendering, or AI tasks should choose the RTX 5090 D V2, as it offers 104.8 TFLOPS, 24 GB of GDDR7, and dedicated RT and tensor cores. Users who require a low-power card for a retro build or a system with a 550 W PSU might consider the GTX 580, given its 244 W TDP and support for older display interfaces. However, the lack of modern API support (no Vulkan, limited DirectX 12) makes the GTX 580 a poor choice for any current software. The RTX 5090 D V2 is the clear recommendation for anyone prioritizing performance, while the GTX 580 is only viable for niche, legacy-specific use cases.