AMD Radeon RX 580 vs NVIDIA GeForce GTX 590 Comparison

# AMD Radeon RX 580 vs NVIDIA GeForce GTX 590

The AMD Radeon RX 580 is the decisive winner in this head-to-head comparison, delivering nearly triple the compute performance in the only shared benchmark while also offering a dramatically newer architecture, more memory, and higher feature support. The NVIDIA GeForce GTX 590, a dual-GPU flagship from 2011, holds a niche advantage in raw memory bus width and transistor count per die, but those specifications do not translate into competitive benchmark results against the RX 580.

Head-to-Head Benchmarks

The only benchmark where both cards have recorded scores is Geekbench OpenCL, and the results are lopsided. The AMD Radeon RX 580 scores 37,453 points, while the NVIDIA GeForce GTX 590 scores 12,830 points. This represents a 191.9% advantage for the RX 580, meaning the AMD card delivers nearly three times the OpenCL compute performance of the older NVIDIA flagship. This is not a marginal victory; it is a generational gap made visible in a single metric.

Looking at the broader benchmark landscape, the RX 580 posts an average benchmark score of 12,928 across its eleven recorded tests. The GTX 590's average score of 12,830 comes from a single Geekbench OpenCL run, which places it just 0.8% below the RX 580's average. However, this comparison is misleading because the RX 580's average includes several lower-scoring DirectX tests that pull its mean down. In the specific OpenCL test where both cards compete, the RX 580's 37,453 absolutely dwarfs the GTX 590's 12,830.

The RX 580 also holds a higher percentile ranking among all GPUs, sitting at the 53rd percentile compared to the GTX 590's 52nd percentile. While both cards are near the middle of the performance distribution, the RX 580's percentile is achieved with far more benchmark data points, indicating consistent performance across a wider range of workloads. The GTX 590's percentile is based on a single test, making its ranking less reliable as a general indicator.

In terms of nearest rivals, the RX 580's average score of 12,928 places it within 0.1% of the NVIDIA GeForce RTX 3050 Ti Mobile (12,940) and 0.4% behind the GTX 1660 SUPER (12,986). The GTX 590's average of 12,830 is essentially tied with the AMD Radeon Pro 455 (12,831) and sits 0.4% ahead of the GTX 670 (12,773). These proximity rankings confirm that while the GTX 590 is not the weakest card in its class, it is firmly anchored to mid-2010s performance levels, whereas the RX 580 competes with much more recent hardware.

FAQ

Q: Which card has higher OpenCL performance?

A: The AMD Radeon RX 580 scores 37,453 in Geekbench OpenCL, which is 191.9% higher than the NVIDIA GeForce GTX 590's score of 12,830.

Q: How do the two cards compare in overall average benchmark scores?

A: The RX 580 has an average benchmark score of 12,928 across eleven tests, while the GTX 590 has an average of 12,830 from a single test. The RX 580 is 0.8% higher.

Q: What are the memory capacities of each card?

A: The RX 580 has 8 GB of GDDR5 memory on a 256-bit bus, while the GTX 590 has 1536 MB of GDDR5 on a 384-bit bus.

Q: Which card supports more modern APIs?

A: The RX 580 supports DirectX 12 (12_0) and Vulkan 1.3, while the GTX 590 supports DirectX 12 (11_0) and has no Vulkan support listed.

Q: What is the transistor density difference?

A: The RX 580 has a transistor density of 24.6 million transistors per square millimeter on a 14 nm node, while the GTX 590 has 5.8 million per square millimeter on a 40 nm node.

Q: Which card has a higher pixel fill rate?

A: The RX 580 has a pixel rate of 42.88 GPixel/s, more than double the GTX 590's 19.46 GPixel/s.

Architecture Differences

The architectural gap between these two GPUs is vast, reflecting nearly six years of semiconductor progress. The AMD Radeon RX 580 uses the Polaris 20 chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. This node allows for 5,700 million transistors packed into a 232 mm² die, yielding a transistor density of 24.6 million per square millimeter. The NVIDIA GeForce GTX 590 uses the GF110 chip on the Fermi 2.0 architecture, manufactured on a 40 nm process at TSMC. It houses 3,000 million transistors across a much larger 520 mm² die, resulting in just 5.8 million transistors per square millimeter.

The RX 580's newer process node is the primary driver of its performance advantage. The 14 nm process enables higher clock speeds and greater efficiency, as evidenced by the RX 580's base clock of 1257 MHz and boost clock of 1340 MHz. The GTX 590's memory clock is 854 MHz (3.4 Gbps effective), but it has no listed base or boost clocks for the GPU cores themselves, suggesting that its core clock architecture is not directly comparable to the RX 580's modern boost behavior.

The shading unit count also differs dramatically. The RX 580 has 2304 shading units, 144 texture mapping units, and 32 ROPs. The GTX 590 has 512 shading units, 64 TMUs, and 48 ROPs. While the GTX 590 has more ROPs, the RX 580 compensates with far higher texture rate (193.0 GTexel/s vs 38.91 GTexel/s) and pixel rate (42.88 GPixel/s vs 19.46 GPixel/s). The RX 580's FP32 performance is 6.175 TFLOPS, while the GTX 590 manages 1,244.2 GFLOPS — a fivefold difference. The RX 580 also supports FP16 at 6.175 TFLOPS (1:1), while the GTX 590 has no FP16 capability listed.

The memory subsystems reflect different design philosophies. The RX 580 uses 8 GB of GDDR5 on a 256-bit bus, achieving 256.0 GB/s of bandwidth. The GTX 590 uses 1536 MB of GDDR5 on a wider 384-bit bus but only reaches 164.0 GB/s. The RX 580's memory clock of 2000 MHz (8 Gbps effective) is more than double the GTX 590's 854 MHz (3.4 Gbps effective), explaining why the narrower bus still delivers superior bandwidth.

Specification Differences

The two cards differ across nearly every specification field. The RX 580 is built on a 14 nm process at GlobalFoundries, while the GTX 590 uses a 40 nm process at TSMC. The RX 580 has 5,700 million transistors on a 232 mm² die; the GTX 590 has 3,000 million on a 520 mm² die. Transistor density is 24.6M/mm² for the RX 580 versus 5.8M/mm² for the GTX 590.

Clock speeds show the RX 580's advantage: base 1257 MHz and boost 1340 MHz, versus no listed base or boost clocks for the GTX 590. Memory clocks are 2000 MHz (8 Gbps effective) for the RX 580 and 854 MHz (3.4 Gbps effective) for the GTX 590. Memory capacity is 8 GB versus 1536 MB, with bus widths of 256-bit versus 384-bit. Bandwidth favors the RX 580 at 256.0 GB/s versus 164.0 GB/s.

Compute resources are heavily skewed toward the RX 580: 2304 shading units, 144 TMUs, and 32 ROPs versus 512 shading units, 64 TMUs, and 48 ROPs. Pixel rate is 42.88 GPixel/s versus 19.46 GPixel/s, and texture rate is 193.0 GTexel/s versus 38.91 GTexel/s. FP32 performance is 6.175 TFLOPS versus 1,244.2 GFLOPS, and only the RX 580 lists FP16 performance.

Power requirements are starkly different: the RX 580 has a TDP of 185 W with a single 8-pin connector and a suggested 450 W PSU, while the GTX 590 draws 365 W, requires two 8-pin connectors, and needs a 750 W PSU. The RX 580 is 241 mm long; the GTX 590 is 279 mm long, 111 mm tall, and 40 mm wide. The RX 580 uses PCIe 3.0 x16, while the GTX 590 uses PCIe 2.0 x16. Display outputs differ: the RX 580 offers 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the GTX 590 provides 3x DVI and 1x mini-DisplayPort.

API support also diverges. The RX 580 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The GTX 590 supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan support. The RX 580 has a launch MSRP of 229 USD, while the GTX 590 launched at 699 USD.

The Verdict

The data unambiguously favors the AMD Radeon RX 580. In the only directly comparable benchmark, the RX 580 delivers 191.9% higher OpenCL performance than the GTX 590. The RX 580 also holds a higher percentile ranking (53rd vs 52nd) and has a higher average benchmark score (12,928 vs 12,830) across a much larger test suite. The RX 580 achieves this with lower power consumption (185 W vs 365 W), a smaller physical footprint, and modern API support including Vulkan 1.3 and full DirectX 12_0.

The GTX 590's only technical advantages are its wider 384-bit memory bus and higher ROP count (48 vs 32). However, these do not translate into benchmark wins, as the RX 580's superior memory clock and shader throughput dominate in actual performance metrics. The GTX 590's 1536 MB memory capacity is also a severe limitation for modern workloads, while the RX 580's 8 GB provides ample headroom.

For any current use case — gaming, compute, or general GPU acceleration — the RX 580 is the clear choice. The GTX 590's higher launch MSRP (699 USD) did not deliver lasting performance, and its end-of-life status means no further optimization or driver feature development is likely. The RX 580, despite also being end-of-life, offers a more capable and efficient platform.

Where Each One Wins

The AMD Radeon RX 580 wins in every benchmark category that has data. It dominates OpenCL compute with a 191.9% advantage, and its higher pixel rate (42.88 GPixel/s vs 19.46 GPixel/s) and texture rate (193.0 GTexel/s vs 38.91 GTexel/s) indicate superior rasterization throughput. The RX 580's 8 GB memory capacity and 256.0 GB/s bandwidth make it suitable for higher-resolution textures and larger datasets. Its support for Vulkan 1.3 and DirectX 12_0 opens the door to modern graphics APIs, while its lower TDP (185 W vs 365 W) makes it easier to cool and power.

The NVIDIA GeForce GTX 590 wins in specific specification categories: it has a wider memory bus (384-bit vs 256-bit), more ROPs (48 vs 32), and a larger die area (520 mm² vs 232 mm²). These specs do not produce any benchmark wins, but they suggest the GTX 590 might have been competitive in certain legacy fill-rate-bound workloads from its era. The GTX 590's three DVI outputs also provide native support for older digital displays, whereas the RX 580's HDMI 2.0b and DisplayPort 1.4a outputs are geared toward modern monitors.

In practical terms, the RX 580 is the superior card for any workload that benefits from high shader throughput, modern API features, or large memory capacity. The GTX 590 is only relevant for historical comparison or for systems that require its specific legacy connectivity options. The data does not support choosing the GTX 590 for performance reasons under any current benchmark scenario.