AMD Radeon Pro 555 vs NVIDIA GeForce GTX 590 Comparison

The AMD Radeon Pro 555 and NVIDIA GeForce GTX 590 represent two very different eras of GPU design, separated by six years of architectural evolution. The benchmark data shows a narrow overall victory for the older NVIDIA card, which wins the only shared test, the Geekbench OpenCL benchmark, by a margin of 8.9%. However, the Radeon Pro 555 achieves a higher average benchmark score of 13407 compared to the GTX 590’s 12830, and it holds a slightly better percentile ranking at 54 versus 52. This creates an interesting dynamic where the newer, power-efficient AMD part scores better on aggregate while the older, power-hungry NVIDIA part wins the direct comparison.

The Verdict

The data paints a clear picture for different use cases. The NVIDIA GeForce GTX 590 is the choice for users who prioritize raw OpenCL compute performance in a desktop environment, as its 12830 score in that specific test outpaces the Radeon Pro 555’s 11682. This is a meaningful 8.9% advantage in the only head-to-head benchmark available. The GTX 590 also offers superior memory bandwidth at 164.0 GB/s, which is more than double the Radeon Pro 555’s 81.60 GB/s, a feature that can matter for large data sets.

The AMD Radeon Pro 555, however, presents a more balanced profile. Its average benchmark score of 13407 is 4.5% higher than the GTX 590’s 12830, and it achieves this while being a fundamentally different class of hardware—an integrated graphics processor (IGP) with a 75 W TDP, versus the GTX 590’s dual-slot, 365 W design with a 750 W suggested power supply. The Radeon Pro 555 also supports modern APIs including Vulkan 1.3 and DirectX 12 (12_0), whereas the GTX 590 lacks Vulkan support entirely and only reaches DirectX 12 (11_0). For users building a portable or power-constrained system, the Radeon Pro 555 is the only viable option despite its lower peak performance. For users with a desktop tower and a high-wattage power supply, the GTX 590 offers the better raw OpenCL score.

Architecture Differences

The two GPUs are products of fundamentally different design philosophies and manufacturing processes. The AMD Radeon Pro 555 uses the Polaris 21 chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. This modern process allows for a transistor density of 24.4 million transistors per square millimeter, packing 3,000 million transistors into a compact 123 mm² die. The NVIDIA GeForce GTX 590 uses the GF110 chip based on the much older Fermi 2.0 architecture, manufactured on a 40 nm process at TSMC. This process yields a transistor density of just 5.8 million transistors per square millimeter, meaning the same 3,000 million transistors require a massive 520 mm² die—over four times larger than the AMD chip.

The architectural differences extend to compute capabilities. The Radeon Pro 555 features 768 shading units, 48 texture mapping units, and 16 raster operations pipelines. The GTX 590 counters with 512 shading units, 64 texture mapping units, and 48 raster operations pipelines. This configuration gives the GTX 590 a higher pixel rate of 19.46 GPixel/s versus 13.60 GPixel/s for the Radeon Pro 555, despite the AMD card having more shading units. The texture rates are nearly identical, with the Radeon Pro 555 at 40.80 GTexel/s and the GTX 590 at 38.91 GTexel/s. In terms of floating-point performance, the Radeon Pro 555 achieves 1,305.6 GFLOPS in FP32, slightly ahead of the GTX 590’s 1,244.2 GFLOPS. The AMD card also supports FP16 at the same rate of 1,305.6 GFLOPS, while the NVIDIA card has no FP16 capability listed.

Memory architecture differs substantially. The Radeon Pro 555 uses 2 GB of GDDR5 on a 128-bit bus, delivering 81.60 GB/s of bandwidth. The GTX 590 uses 1536 MB of GDDR5 on a 384-bit bus, delivering 164.0 GB/s of bandwidth. The GTX 590’s memory clock is 854 MHz (3.4 Gbps effective), while the Radeon Pro 555’s memory runs at 1275 MHz (5.1 Gbps effective), showing how the wider bus compensates for lower clock speeds on the older card.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test, and the results favor the NVIDIA GeForce GTX 590. The GTX 590 scores 12830, while the AMD Radeon Pro 555 scores 11682. This represents an 8.9% advantage for the NVIDIA card. This is a significant margin in a compute workload, suggesting that the GTX 590’s higher memory bandwidth and greater raster operations pipeline count provide a tangible benefit in OpenCL tasks that outweigh the Radeon Pro 555’s advantages in shading units and FP32 throughput.

Looking at the broader benchmark picture, however, the AMD card shows strength in other compute APIs. The Radeon Pro 555 scores 16236 in Geekbench Metal and 12303 in Geekbench Vulkan, though no comparable scores exist for the GTX 590 in these tests. The GTX 590’s lack of Vulkan support in its API list suggests it would not be able to run that benchmark at all. For users working in Metal-based applications, which are common in the macOS ecosystem where the Radeon Pro 555 is designed to operate, the AMD card’s 16236 Metal score indicates robust performance.

The average benchmark scores further contextualize the head-to-head result. The Radeon Pro 555 achieves an average of 13407 across all its tested benchmarks, placing it in the 54th percentile of all GPUs. The GTX 590, with only a single OpenCL benchmark result, has an average of 12830, placing it in the 52nd percentile. The nearest rival to the GTX 590 is the AMD Radeon Pro 455 with an average score of 12831 and a delta of 0%, effectively tying the NVIDIA card. The Radeon Pro 555, meanwhile, sits closest to the AMD Radeon HD 8950M with a delta of 0.2%.

Specification Differences

The specification sheets for these two cards reveal stark contrasts in nearly every category. The process node is a major differentiator: the Radeon Pro 555 uses a 14 nm process from GlobalFoundries, while the GTX 590 uses a 40 nm process from TSMC. This leads to the die size difference, with the AMD card at 123 mm² and the NVIDIA card at 520 mm², and the transistor density difference of 24.4M per mm² versus 5.8M per mm².

Power consumption and physical design are polar opposites. The Radeon Pro 555 has a TDP of 75 W and is classified as an integrated graphics processor (IGP) with no power connectors and a PCIe 3.0 x8 interface. The GTX 590 has a TDP of 365 W, requires two 8-pin power connectors and a 750 W suggested power supply, uses a dual-slot design, and connects via PCIe 2.0 x16. The dimensions reflect this: the GTX 590 measures 279 mm in length, 111 mm in height, and 40 mm in width, while the Radeon Pro 555 has no listed dimensions due to its integrated nature.

Memory specifications differ in capacity and bandwidth. The Radeon Pro 555 has 2 GB of memory, while the GTX 590 has 1536 MB. The bus widths are 128-bit versus 384-bit, and the bandwidth figures are 81.60 GB/s versus 164.0 GB/s. The memory clocks are 1275 MHz versus 854 MHz. The Radeon Pro 555 has more shading units at 768 versus 512, but fewer texture mapping units at 48 versus 64, and far fewer raster operations pipelines at 16 versus 48. The pixel rate is 13.60 GPixel/s for AMD and 19.46 GPixel/s for NVIDIA.

API support shows the generational gap. The Radeon Pro 555 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 listed. The display outputs also differ, with the Radeon Pro 555 being portable device dependent and the GTX 590 offering 3x DVI and 1x mini-DisplayPort. The release dates are June 4, 2017 for the AMD card and March 23, 2011 for the NVIDIA card. The GTX 590 has a predecessor in the GeForce 400 series and a successor in the GeForce 600 series, while the Radeon Pro 555 has no listed predecessor or successor. The GTX 590 had a launch MSRP of 699 USD, while the Radeon Pro 555 has no listed launch MSRP.

FAQ

Q: Which GPU wins the only direct benchmark comparison?

A: The NVIDIA GeForce GTX 590 wins the Geekbench OpenCL benchmark with a score of 12830, while the AMD Radeon Pro 555 scores 11682. This gives the GTX 590 an 8.9% advantage in that specific test.

Q: Does the AMD Radeon Pro 555 have a higher average benchmark score?

A: Yes, the Radeon Pro 555 has an average benchmark score of 13407, while the GTX 590 has an average of 12830. This represents a 4.5% advantage for the AMD card when averaging across all available benchmarks.

Q: What are the memory bandwidth differences between the two cards?

A: The GTX 590 offers 164.0 GB/s of memory bandwidth with a 384-bit bus, while the Radeon Pro 555 offers 81.60 GB/s with a 128-bit bus. The GTX 590’s bandwidth is more than double that of the AMD card.

Q: How do the shading unit counts compare?

A: The AMD Radeon Pro 555 has 768 shading units, while the NVIDIA GeForce GTX 590 has 512 shading units. Despite having fewer shading units, the GTX 590 achieves a higher pixel rate of 19.46 GPixel/s versus 13.60 GPixel/s for the AMD card.

Q: Which GPU supports more modern APIs?

A: The AMD Radeon Pro 555 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The NVIDIA GeForce GTX 590 supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan support listed in its specifications.

Q: What is the power consumption difference?

A: The Radeon Pro 555 has a TDP of 75 W and uses no power connectors, while the GTX 590 has a TDP of 365 W and requires two 8-pin power connectors. The NVIDIA card also has a suggested power supply of 750 W.