AMD Radeon HD 8950M vs NVIDIA GeForce GTX 590 Comparison

The AMD Radeon HD 8950M and NVIDIA GeForce GTX 590 represent two very different approaches to high-performance graphics from different eras. The HD 8950M is a mobile-first GCN 2.0 part from 2013, while the GTX 590 is a dual-GPU desktop monster from 2011. Based on the data available, the HD 8950M holds a single benchmark win, but the architectural and specification gaps between these two end-of-life products tell a story of divergent design priorities.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon HD 8950M has an average benchmark score of 13376, while the NVIDIA GeForce GTX 590 scores 12830. This places the HD 8950M at the 54th percentile of all GPUs, compared to the GTX 590's 52nd percentile.

Q: How large is the performance gap in the head-to-head test?

A: In the Geekbench OpenCL test, the HD 8950M scores 13772 versus the GTX 590's 12830, giving the AMD part a 7.3% lead. This is the only head-to-head benchmark recorded, and AMD wins it.

Q: What are the memory specifications of each card?

A: The HD 8950M has 2 GB of GDDR5 on a 128-bit bus with 88.00 GB/s bandwidth. The GTX 590 has 1536 MB of GDDR5 on a 384-bit bus with 164.0 GB/s bandwidth, which is nearly double the bandwidth despite the smaller capacity.

Q: How do their power requirements compare?

A: The HD 8950M is rated at 100 W TDP and uses an MXM Module slot width, making it suitable for portable devices. The GTX 590 is rated at 365 W TDP, requires a 750 W suggested PSU, uses a dual-slot design, and needs 2x 8-pin power connectors.

Q: Which card supports more modern APIs?

A: The HD 8950M supports DirectX 12 (12_0) and Vulkan 1.2.170, while the GTX 590 supports DirectX 12 (11_0) and has no Vulkan support listed. Both support OpenGL 4.6.

Q: What are their physical dimensions?

A: The GTX 590 is 279 mm long, 111 mm tall, and 40 mm wide. The HD 8950M has no listed dimensions, as it is a portable-device-dependent MXM module.

Architecture Differences

The HD 8950M is built on AMD's GCN 2.0 architecture using the Saturn chip, manufactured on a 28 nm process at TSMC. It packs 2,080 million transistors into a 160 mm² die, yielding a transistor density of 13.0M per mm². The GTX 590 uses NVIDIA's Fermi 2.0 architecture with the GF110 chip, fabricated on a 40 nm process, also at TSMC. It contains 3,000 million transistors spread across a much larger 520 mm² die, with a lower density of 5.8M per mm².

The core configurations diverge significantly. The HD 8950M has 768 shading units, 48 texture mapping units, and 16 ROPs. The GTX 590 has 512 shading units, 64 TMUs, and 48 ROPs. This means the GTX 590 has more texture units and ROPs, but fewer shading units. The HD 8950M belongs to the Solar System generation (HD 8900M series) with a predecessor of London and successor of Gem System. The GTX 590 is part of the GeForce 500 generation, following GeForce 400 and preceding GeForce 600.

Memory architecture also differs. The HD 8950M runs GDDR5 at 1375 MHz (5.5 Gbps effective) on a 128-bit bus, giving 88.00 GB/s bandwidth. The GTX 590 runs GDDR5 at 854 MHz (3.4 Gbps effective) on a 384-bit bus, achieving 164.0 GB/s. The GTX 590's wider bus compensates for its lower memory clock, resulting in nearly double the bandwidth. The HD 8950M uses a PCIe 3.0 x16 interface, while the GTX 590 uses PCIe 2.0 x16. Display outputs are portable-device-dependent for the AMD part, while the GTX 590 offers 3x DVI and 1x mini-DisplayPort.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench OpenCL test. The HD 8950M scores 13772, while the GTX 590 scores 12830. This yields a 7.3% advantage for the AMD card. In absolute terms, the HD 8950M is 942 points ahead. This puts the HD 8950M in the 54th percentile of all GPUs, while the GTX 590 sits at the 52nd percentile.

Looking at the nearest rivals provides additional context. The HD 8950M's closest competitor is the AMD Radeon Pro 555 with an average score of 13407, which is 0.2% higher. The AMD Radeon RX 5500M scores 13356, just 0.2% lower. The AMD FirePro M6100 scores 13354, also 0.2% lower, and the AMD Radeon Pro 555X scores 13321, which is 0.4% lower. For the GTX 590, the AMD Radeon 740M scores 12870, 0.3% higher. The AMD FirePro W5100 scores 12847, 0.1% higher. The AMD Radeon Pro 455 scores 12831, essentially tied at 0% delta. The NVIDIA GeForce GTX 670 scores 12773, which is 0.4% lower.

The HD 8950M's raw compute is listed at 1.651 TFLOPS FP32, compared to the GTX 590's 1,244.2 GFLOPS (approximately 1.244 TFLOPS). The HD 8950M also has higher pixel rate (17.20 GPixel/s vs 19.46 GPixel/s) and texture rate (51.60 GTexel/s vs 38.91 GTexel/s). Despite the GTX 590 having more ROPs, its pixel rate is actually lower, and its texture rate is significantly lower despite having more TMUs — likely due to clock speed differences not fully captured here.

The Verdict

The data clearly favors the AMD Radeon HD 8950M in the one benchmark where they are directly compared. Its 7.3% lead in Geekbench OpenCL, combined with its higher average score (13376 vs 12830) and better percentile ranking (54th vs 52nd), makes it the more capable performer in compute workloads. The HD 8950M also offers more modern API support, including Vulkan 1.2.170 and DirectX 12 (12_0), which the GTX 590 lacks in Vulkan and only partially supports in DirectX (11_0).

However, the GTX 590 is not without merit. It offers substantially more memory bandwidth (164.0 GB/s vs 88.00 GB/s), which could benefit certain bandwidth-sensitive workloads. Its 3,000 million transistors and 520 mm² die indicate a more complex design, though on an older and less efficient 40 nm process. The GTX 590 also has a higher pixel rate (19.46 GPixel/s) despite having fewer shading units and lower FP32 throughput.

For a buyer choosing between these two end-of-life products, the HD 8950M is the better choice for general compute and modern API compatibility. The GTX 590's higher power draw (365 W vs 100 W) and lack of Vulkan support make it harder to recommend, despite its bandwidth advantage. The HD 8950M is also more portable, using an MXM Module form factor versus the GTX 590's massive dual-slot, 279 mm long desktop design.

Specification Differences

| Specification | AMD Radeon HD 8950M | NVIDIA GeForce GTX 590 |

|---|---|---|

| Architecture | GCN 2.0 | Fermi 2.0 |

| Process Node | 28 nm | 40 nm |

| Transistors | 2,080 million | 3,000 million |

| Die Size | 160 mm² | 520 mm² |

| Transistor Density | 13.0M / mm² | 5.8M / mm² |

| Memory Size | 2 GB | 1536 MB |

| Memory Bus | 128 bit | 384 bit |

| Memory Bandwidth | 88.00 GB/s | 164.0 GB/s |

| Shading Units | 768 | 512 |

| TMUs | 48 | 64 |

| ROPs | 16 | 48 |

| Pixel Rate | 17.20 GPixel/s | 19.46 GPixel/s |

| Texture Rate | 51.60 GTexel/s | 38.91 GTexel/s |

| FP32 | 1.651 TFLOPS | 1,244.2 GFLOPS |

| TDP | 100 W | 365 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None listed | 2x 8-pin |

| Suggested PSU | None listed | 750 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |

| DirectX | 12 (12_0) | 12 (11_0) |

| Vulkan | 1.2.170 | None |

| Release Date | 2013-05-13 | 2011-03-23 |

| Launch MSRP | Not listed | 699 USD |

Where Each One Wins

The AMD Radeon HD 8950M wins in compute performance, as demonstrated by its 7.3% lead in Geekbench OpenCL and its higher FP32 throughput of 1.651 TFLOPS. It is also the clear winner in API support, offering Vulkan 1.2.170 and full DirectX 12 (12_0) support, while the GTX 590 lacks Vulkan entirely. The HD 8950M is more power-efficient, with a 100 W TDP versus the GTX 590's 365 W, making it suitable for portable devices via its MXM Module form factor. Its texture rate is also higher at 51.60 GTexel/s versus 38.91 GTexel/s.

The NVIDIA GeForce GTX 590 wins in memory bandwidth, delivering 164.0 GB/s versus the HD 8950M's 88.00 GB/s, which could matter for high-resolution textures or certain compute tasks. It also has more TMUs (64 vs 48) and ROPs (48 vs 16), along with a higher pixel rate of 19.46 GPixel/s. The GTX 590's 384-bit memory bus is three times wider than the HD 8950M's 128-bit bus. Its dual-slot desktop design with 3x DVI and 1x mini-DisplayPort outputs makes it a better fit for multi-monitor desktop setups, though it requires a 750 W PSU and 2x 8-pin power connectors.

For texture-heavy workloads, the GTX 590's higher TMU count is offset by its lower texture rate, meaning the HD 8950M actually processes textures faster. For pixel-heavy workloads, the GTX 590's 48 ROPs and higher pixel rate give it an edge. The HD 8950M is the better choice for modern games that use Vulkan or DirectX 12 features, while the GTX 590 might still hold up in older titles that favor raw bandwidth and fill rate.