AMD Radeon Pro 455 vs NVIDIA GeForce GTX 590 Comparison

The AMD Radeon Pro 455 and NVIDIA GeForce GTX 590 are two end-of-life GPUs separated by five years of architecture and design philosophy, yet they land in nearly the same performance tier. Based on aggregate benchmark scores, the Radeon Pro 455 averages 12,831 points, while the GTX 590 averages 12,830 points — a difference of just 1 point, or 0.0%. Both cards sit at the 52nd percentile of all GPUs, making them statistically indistinguishable in overall compute performance. The GTX 590 wins the only direct head-to-head test, Geekbench OpenCL, with a score of 12,830 versus 10,336 for the Radeon Pro 455, a 19.4% advantage. However, the Radeon Pro 455 counters with a Geekbench Metal score of 15,916 and a Vulkan score of 12,240 — tests the GTX 590 cannot run due to its lack of Vulkan support and different API profile. This comparison is less about raw speed and more about ecosystem fit, power constraints, and which workloads each card was designed to serve.

The Verdict

Pick the AMD Radeon Pro 455 if you need a modern, low-power compute card for a portable workstation or a system with strict thermal limits. Its 35 W TDP is dramatically lower than the GTX 590's 365 W, and its MXM module form factor makes it suitable for laptops or compact chassis where space and power are at a premium. The Radeon Pro 455 also offers access to Vulkan 1.3 and DirectX 12 (12_0), while the GTX 590 is limited to DirectX 12 (11_0) and has no Vulkan support at all. If your workloads rely on Metal — Apple's GPU API — the Radeon Pro 455 is the only viable choice here, as its Geekbench Metal score of 15,916 is its strongest result. The data also shows the Radeon Pro 455 has a higher FP32 throughput at 1,313.3 GFLOPS versus 1,244.2 GFLOPS, meaning it can handle raw floating-point compute more efficiently.

Pick the NVIDIA GeForce GTX 590 if you have an older desktop system with a robust power supply and you prioritize OpenCL compute performance above all else. The GTX 590 wins the only head-to-head benchmark, posting 12,830 in Geekbench OpenCL against the Radeon Pro 455's 10,336 — a 19.4% margin. It also offers significantly more memory bandwidth at 164.0 GB/s versus 81.28 GB/s, and a wider 384-bit memory bus compared to 128-bit, which matters for memory-bound workloads. The GTX 590 has a higher pixel rate (19.46 GPixel/s versus 13.68 GPixel/s) and more ROPs (48 versus 16), making it better suited for fill-rate-limited tasks. However, this card demands a 750 W suggested PSU, dual 8-pin power connectors, and takes up a dual-slot, 279 mm length footprint — it is not a card for small builds or low-power systems.

Where Each One Wins

The Radeon Pro 455 wins in modern API support and energy efficiency. It delivers a Geekbench Vulkan score of 12,240, which is notable because the GTX 590 has no Vulkan implementation at all. Its DirectX 12 feature level of 12_0 is a full step ahead of the GTX 590's 11_0, making it the better choice for any application that leverages newer graphics APIs. The Radeon Pro 455 also excels in Metal performance, scoring 15,916 on Geekbench Metal — its best benchmark result and one that the GTX 590 cannot compete with, as NVIDIA's card has no Metal support listed. Additionally, the Radeon Pro 455's 14 nm process node from GlobalFoundries versus the GTX 590's 40 nm TSMC node means the AMD card runs at a fraction of the power draw, with a 35 W TDP that is 330 W lower than the GTX 590's 365 W TDP. The Radeon Pro 455 also has a much denser transistor layout at 24.4M transistors per mm² versus 5.8M for the GTX 590, reflecting its modern design.

The GTX 590 wins in raw OpenCL compute and memory throughput. Its Geekbench OpenCL score of 12,830 is 19.4% higher than the Radeon Pro 455's 10,336, and that is the only test where both cards have comparable data. The GTX 590's memory subsystem is superior in every measurable way: 164.0 GB/s bandwidth versus 81.28 GB/s, a 384-bit bus versus 128-bit, and a larger 1536 MB frame buffer (though note the Radeon Pro 455 has 2 GB, so the GTX 590's advantage is in speed, not capacity). The GTX 590 also has more TMUs (64 versus 48) and more ROPs (48 versus 16), which contributes to its higher pixel rate of 19.46 GPixel/s versus 13.68 GPixel/s. For legacy OpenCL acceleration or fill-rate-bound rendering, the GTX 590 is the stronger card.

Architecture Differences

The Radeon Pro 455 is built on AMD's GCN 4.0 architecture, using the Baffin chip manufactured on a 14 nm process at GlobalFoundries. It packs 3,000 million transistors into a 123 mm² die, achieving a transistor density of 24.4M per mm². The GPU has 768 shading units, 48 TMUs, and 16 ROPs, with a texture rate of 41.04 GTexel/s and a pixel rate of 13.68 GPixel/s. Its FP32 performance is rated at 1,313.3 GFLOPS, and it also supports FP16 at 1,313.3 GFLOPS with a 1:1 ratio. Memory is 2 GB of GDDR5 on a 128-bit bus, running at 1270 MHz (5.1 Gbps effective), yielding 81.28 GB/s of bandwidth. The card uses a PCIe 3.0 x8 interface and is an MXM module with no external power connectors. It supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3.

The GTX 590 is based on NVIDIA's Fermi 2.0 architecture, using the GF110 chip on a 40 nm process at TSMC. It also contains 3,000 million transistors, but on a much larger 520 mm² die, giving a transistor density of just 5.8M per mm². The GPU has 512 shading units, 64 TMUs, and 48 ROPs, with a texture rate of 38.91 GTexel/s and a pixel rate of 19.46 GPixel/s. Its FP32 performance is 1,244.2 GFLOPS, and it has no FP16 support listed. Memory is 1536 MB of GDDR5 on a 384-bit bus, running at 854 MHz (3.4 Gbps effective), producing 164.0 GB/s of bandwidth. The card uses a PCIe 2.0 x16 interface, is a dual-slot design at 279 mm long, and requires 2x 8-pin power connectors with a suggested 750 W PSU. It supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan support.

FAQ

Q: Which card has better overall benchmark performance?

A: They are effectively tied. The Radeon Pro 455 averages 12,831 points across all benchmarks, while the GTX 590 averages 12,830 points — a 0.0% difference. Both rank at the 52nd percentile of all GPUs.

Q: Can the GTX 590 run Vulkan games or applications?

A: No. The GTX 590 has no Vulkan support listed in its API specifications, while the Radeon Pro 455 supports Vulkan 1.3 and scores 12,240 on Geekbench Vulkan.

Q: Which card is better for OpenCL compute workloads?

A: The GTX 590 wins the only direct head-to-head test, scoring 12,830 in Geekbench OpenCL versus 10,336 for the Radeon Pro 455, a 19.4% advantage.

Q: How do their power requirements compare?

A: The Radeon Pro 455 has a 35 W TDP and uses no external power connectors, while the GTX 590 has a 365 W TDP and requires 2x 8-pin connectors with a 750 W suggested PSU.

Q: Which card has higher memory bandwidth?

A: The GTX 590 offers 164.0 GB/s on a 384-bit bus, more than double the Radeon Pro 455's 81.28 GB/s on a 128-bit bus. However, the Radeon Pro 455 has 2 GB of memory versus the GTX 590's 1536 MB.

Q: Is the Radeon Pro 455 compatible with Apple's Metal API?

A: Yes, the Radeon Pro 455 scores 15,916 on Geekbench Metal, which is its highest benchmark result. The GTX 590 has no Metal support listed.

Head-to-Head Benchmarks

The only direct comparison available is Geekbench OpenCL, and it clearly favors the GTX 590. NVIDIA's card scores 12,830, while the Radeon Pro 455 scores 10,336 — a 19.4% difference in favor of the GTX 590. This is a substantial margin, especially considering the two cards have nearly identical average benchmark scores overall. The gap likely stems from the GTX 590's memory system: with 164.0 GB/s of bandwidth and a 384-bit bus, it can feed data to its 512 shading units faster than the Radeon Pro 455's 81.28 GB/s and 128-bit bus can feed its 768 shading units. In OpenCL workloads that are memory-intensive, the GTX 590's advantage is decisive.

However, the Radeon Pro 455 has wins that do not appear in the head-to-head table because the GTX 590 cannot run those tests. The Radeon Pro 455's Geekbench Metal score of 15,916 is its strongest result, and its Vulkan score of 12,240 shows strong modern API performance. The GTX 590 lacks Vulkan support entirely, and with no Metal support listed, the Radeon Pro 455 is the only card that can handle those workloads. In terms of theoretical compute, the Radeon Pro 455 also has a slight edge in FP32 throughput at 1,313.3 GFLOPS versus 1,244.2 GFLOPS, while the GTX 590 counters with higher pixel throughput (19.46 GPixel/s versus 13.68 GPixel/s) and texture rate (38.91 GTexel/s versus 41.04 GTexel/s — here the Radeon Pro 455 is actually ahead on texture rate, though the GTX 590 wins on pixel rate). The overall picture is a split decision: GTX 590 for legacy OpenCL, Radeon Pro 455 for everything modern.

Specification Differences

The two cards differ across nearly every major specification category. The Radeon Pro 455 uses a 14 nm process at GlobalFoundries, while the GTX 590 uses a 40 nm process at TSMC. Both have 3,000 million transistors, but the Radeon Pro 455 packs them into 123 mm² versus 520 mm² for the GTX 590, resulting in a transistor density of 24.4M per mm² versus 5.8M per mm². The Radeon Pro 455 has 768 shading units, 48 TMUs, and 16 ROPs; the GTX 590 has 512 shading units, 64 TMUs, and 48 ROPs. The Radeon Pro 455 achieves 41.04 GTexel/s texture rate and 13.68 GPixel/s pixel rate, while the GTX 590 achieves 38.91 GTexel/s and 19.46 GPixel/s respectively. FP32 performance is 1,313.3 GFLOPS for the Radeon Pro 455 versus 1,244.2 GFLOPS for the GTX 590, and only the Radeon Pro 455 lists FP16 support. Memory configurations differ significantly: 2 GB GDDR5 on 128-bit with 81.28 GB/s for the Radeon Pro 455 versus 1536 MB GDDR5 on 384-bit with 164.0 GB/s for the GTX 590. TDP is a massive differentiator at 35 W versus 365 W. The Radeon Pro 455 is an MXM module with no power connectors and a PCIe 3.0 x8 interface; the GTX 590 is a dual-slot card requiring 2x 8-pin connectors, a 750 W PSU, and a PCIe 2.0 x16 interface. Display outputs are portable-device-dependent for the Radeon Pro 455, while the GTX 590 offers 3x DVI and 1x mini-DisplayPort. API support diverges with DirectX 12 (12_0) and Vulkan 1.3 on the Radeon Pro 455 versus DirectX 12 (11_0) and no Vulkan on the GTX 590. The GTX 590 has a launch MSRP of 699 USD.