AMD FirePro M6100 vs NVIDIA GeForce GTX 590 Comparison

The AMD FirePro M6100 and NVIDIA GeForce GTX 590 represent two very different approaches to high-performance computing, separated by three years of GPU architecture evolution. The FirePro M6100 is a 2014 mobile workstation part built on AMD's GCN 2.0 architecture, while the GTX 590 is a 2011 dual-GPU desktop flagship based on NVIDIA's Fermi 2.0 design. The benchmark data shows the newer mobile chip outperforms the older dual-GPU monster in the one available test, but the specifications reveal a more complex story about bandwidth, memory capacity, and power requirements.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD FirePro M6100 scores 13354, which is 524 points higher than the NVIDIA GeForce GTX 590's score of 12830. This gives the FirePro M6100 a 4.1% lead in the head-to-head benchmark comparison.

Q: How do these GPUs compare to their nearest rivals?

A: The FirePro M6100 sits at the 54th percentile of all GPUs, with its closest rival being the AMD Radeon RX 5500M at a nearly identical 13356 score (0% delta). The GTX 590 is at the 52nd percentile, with the AMD Radeon Pro 455 matching it at 12831 (0% delta), while the NVIDIA GeForce GTX 670 trails by 0.4% with a score of 12773.

Q: What are the memory specifications of each card?

A: The FirePro M6100 has 2 GB of GDDR5 memory on a 128-bit bus, delivering 96.00 GB/s of bandwidth. The GTX 590 has 1536 MB (1.5 GB) of GDDR5 memory on a much wider 384-bit bus, providing 164.0 GB/s of bandwidth.

Q: Which GPU requires more power?

A: The GTX 590 has a TDP of 365 W and requires both a 750 W suggested power supply and two 8-pin power connectors. The FirePro M6100's TDP is not listed, but as an MXM Module with no power connectors, it is designed for portable workstations and draws power through the module interface.

Q: What is the release timeline for these two products?

A: The GTX 590 was released on March 23, 2011, as part of the GeForce 500 generation, succeeding the GeForce 400 series. The FirePro M6100 arrived on May 26, 2014, in the FirePro Mobile (Mx100) generation, following the FirePro Mobility line and preceding the Radeon Pro Mobile series.

Q: What API support does each GPU offer?

A: The FirePro M6100 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The GTX 590 supports DirectX 12 (11_0) and OpenGL 4.6 but has no Vulkan support listed.

The Verdict

The benchmark data clearly favors the AMD FirePro M6100 for raw compute performance, as it leads the GTX 590 by 4.1% in Geekbench OpenCL. This is a significant result given that the GTX 590 is a dual-GPU desktop flagship with a 365 W TDP and a 279 mm card length, while the FirePro M6100 is a single mobile module. The FirePro M6100 also offers twice the memory capacity (2 GB vs 1536 MB) and modern API support including Vulkan and full DirectX 12.

However, the GTX 590 wins decisively in memory bandwidth with 164.0 GB/s versus 96.00 GB/s, a 71% advantage. It also has more TMUs (64 vs 56) and significantly more ROPs (48 vs 16), which could matter for certain rendering workloads that are pixel-bound rather than compute-bound. The GTX 590 was launched with an MSRP of 699 USD, and its dual-slot, 279 mm physical footprint with 2x 8-pin power connectors marks it as a desktop-only solution. The FirePro M6100's MXM-B (3.0) interface and portable-device-dependent display outputs make it suitable for mobile workstations.

For a builder choosing between these today, the FirePro M6100 is the more sensible pick for OpenCL compute tasks and modern software compatibility, provided the workload fits within its 96.00 GB/s bandwidth envelope. The GTX 590 only makes sense if the workload is heavily bandwidth-starved and you have the power delivery and physical space to accommodate a 365 W dual-slot card.

Head-to-Head Benchmarks

The single available benchmark test, Geekbench OpenCL, shows the FirePro M6100 winning with a score of 13354 against the GTX 590's 12830. The 4.1% delta means the FirePro M6100 is not just marginally ahead; it is meaningfully faster in this compute-oriented test despite being a mobile part with less than half the thermal design power allowance.

Breaking down why the FirePro M6100 wins: it packs 896 shading units into a 160 mm² die fabricated on TSMC's 28 nm node, versus the GTX 590's 512 shading units spread across two GF110 chips on a 520 mm² die at 40 nm. The FirePro M6100's FP32 throughput of 1.971 TFLOPS crushes the GTX 590's 1,244.2 GFLOPS (approximately 1.24 TFLOPS), a 58% advantage in raw floating-point capability. The texture rate also favors the FirePro M6100 at 61.60 GTexel/s versus 38.91 GTexel/s, a 58% lead, reflecting its better per-shader efficiency.

The GTX 590 does have the higher pixel rate at 19.46 GPixel/s versus 17.60 GPixel/s, a 10.6% advantage, which comes from its 48 ROPs versus the FirePro M6100's 16 ROPs. This suggests the GTX 590 could outperform in fill-rate-limited scenarios, but the benchmark data shows that in OpenCL compute, the FirePro M6100's architectural efficiency wins out.

Specification Differences

| Specification | AMD FirePro M6100 | NVIDIA GeForce GTX 590 |

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

| 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 Width | 128 bit | 384 bit |

| Memory Bandwidth | 96.00 GB/s | 164.0 GB/s |

| Shading Units | 896 | 512 |

| TMUs | 56 | 64 |

| ROPs | 16 | 48 |

| Pixel Rate | 17.60 GPixel/s | 19.46 GPixel/s |

| Texture Rate | 61.60 GTexel/s | 38.91 GTexel/s |

| FP32 | 1.971 TFLOPS | 1,244.2 GFLOPS |

| TDP | Not listed | 365 W |

| Slot Width | MXM Module | Dual-slot |

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

| Suggested PSU | Not listed | 750 W |

| Bus Interface | MXM-B (3.0) | PCIe 2.0 x16 |

| Display Outputs | Portable Device Dependent | 3x DVI, 1x mini-DisplayPort |

| Length | Not listed | 279 mm (11 inches) |

| Height | Not listed | 111 mm (4.4 inches) |

| Width | Not listed | 40 mm (1.6 inches) |

| Launch MSRP | Not listed | 699 USD |

Architecture Differences

The FirePro M6100 uses the Emerald chip based on GCN 2.0 architecture, fabricated by TSMC on a 28 nm process. This yields a 160 mm² die with 2,080 million transistors at a density of 13.0 million transistors per square millimeter. The GCN 2.0 design emphasizes compute throughput, which explains its 896 shading units and 1.971 TFLOPS FP32 performance despite a relatively narrow 128-bit memory bus.

The GTX 590 uses the GF110 chip based on Fermi 2.0 architecture, also from TSMC but on an older 40 nm process. The dual-chip design packs 3,000 million transistors onto a massive 520 mm² die, but at a lower density of 5.8 million transistors per square millimeter. Fermi 2.0 was designed for the GeForce 500 generation and prioritizes memory bandwidth and fill rate, as evidenced by the 384-bit bus and 48 ROPs.

The architectural philosophies diverge sharply in memory strategy. The FirePro M6100 pairs its 128-bit bus with 6 Gbps effective GDDR5 to reach 96.00 GB/s, while the GTX 590 uses a 384-bit bus at 3.4 Gbps effective to achieve 164.0 GB/s. The newer GCN 2.0 architecture also brings Vulkan 1.2.170 support and DirectX 12 (12_0), whereas Fermi 2.0 tops out at DirectX 12 (11_0) with no Vulkan support listed. Both support OpenGL 4.6.

Where Each One Wins

AMD FirePro M6100 wins in: Compute workloads, as shown by its 4.1% Geekbench OpenCL lead. Its 1.971 TFLOPS FP32 throughput gives it a 58% advantage over the GTX 590's 1,244.2 GFLOPS. Texture-heavy operations also favor the FirePro M6100, with 61.60 GTexel/s versus 38.91 GTexel/s. It has twice the memory capacity (2 GB vs 1536 MB), which is critical for modern workloads that exceed 1.5 GB. The FirePro M6100's support for Vulkan 1.2.170 and DirectX 12 (12_0) makes it compatible with contemporary software APIs, whereas the GTX 590's DirectX 12 (11_0) and lack of Vulkan limit modern application compatibility. Its MXM-B (3.0) form factor with no power connectors makes it deployable in portable workstations.

NVIDIA GeForce GTX 590 wins in: Memory bandwidth, delivering 164.0 GB/s versus the FirePro M6100's 96.00 GB/s, a 71% advantage that benefits bandwidth-hungry workloads. It also has more TMUs (64 vs 56) and triple the ROPs (48 vs 16), giving it a 10.6% higher pixel rate at 19.46 GPixel/s versus 17.60 GPixel/s. The GTX 590's 384-bit memory bus is a fundamental architectural advantage that cannot be compensated for by clock speeds alone. Its desktop-oriented design with 3x DVI and 1x mini-DisplayPort outputs, plus its 279 mm length and dual-slot footprint, makes it a straightforward installation in full-size desktop cases with appropriate power delivery.