AMD Radeon R9 M375X vs NVIDIA GeForce GTX 560 Comparison

The NVIDIA GeForce GTX 560 and the AMD Radeon R9 M375X represent two distinct eras of GPU design, with the former built on a 40 nm process for desktop use and the latter a 28 nm mobile-oriented part. Benchmark data shows the GTX 560 holds a clear lead in the single shared test, but the R9 M375X counters with a more modern feature set and different performance characteristics. The GeForce GTX 560 scores 9,058 in Geekbench OpenCL, while the Radeon R9 M375X scores 8,273, a 9.5% difference in favor of the NVIDIA part. This page breaks down where each GPU wins, how their architectures diverge, and what the specification sheet reveals about their respective strengths.

Where Each One Wins

The head-to-head benchmark results are unambiguous: the NVIDIA GeForce GTX 560 wins the only shared test, Geekbench OpenCL, by a 9.5% margin. This makes the GTX 560 the stronger choice for compute workloads that leverage OpenCL, as its score of 9,058 places it in the 45th percentile of all GPUs. In contrast, the AMD Radeon R9 M375X scores 8,273 in the same test, landing in the 43rd percentile. The GTX 560 also has a higher average benchmark score of 9,058 compared to the R9 M375X’s 8,325, reinforcing its overall performance advantage in this dataset.

However, the R9 M375X has a unique win that the GTX 560 cannot match: it features a Geekbench Vulkan score of 8,377. This is significant because the GTX 560 has no Vulkan support listed, meaning the AMD part is the only one of the two capable of running Vulkan-based applications and benchmarks. For users prioritizing modern API compatibility, the R9 M375X is the sole option here. The NVIDIA card’s DirectX support is also more limited, with a version of 12 (11_0) compared to the R9 M375X’s 12 (11_1), giving AMD a slight edge in that API specification as well.

In terms of raw memory capacity, the R9 M375X wins by offering 2 GB of GDDR5, double the 1024 MB found on the GTX 560. This larger frame buffer could be advantageous for texture-heavy workloads or higher-resolution scenarios, even if the GTX 560’s memory bus is wider. The AMD card also supports PCIe 3.0 x16, whereas the NVIDIA part is limited to PCIe 2.0 x16, which could affect bandwidth in systems with newer motherboards.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The NVIDIA GeForce GTX 560 uses the GF114 chip, based on the Fermi 2.0 architecture, manufactured on a 40 nm process at TSMC with 1,950 million transistors on a 332 mm² die. This results in a transistor density of 5.9 million transistors per mm². The AMD Radeon R9 M375X, by contrast, uses the Tropo chip with GCN 1.0 architecture, built on a more advanced 28 nm process, also at TSMC, with 1,500 million transistors on a much smaller 123 mm² die, achieving a higher density of 12.2 million transistors per mm².

Core configuration differs substantially. The GTX 560 packs 336 shading units, 56 texture mapping units (TMUs), and 32 raster operation units (ROPs). The R9 M375X has 640 shading units but only 40 TMUs and 16 ROPs. This means the AMD card has nearly double the shading units but significantly fewer TMUs and half the ROPs. Clock speeds also vary: the GTX 560 runs its memory at 1000 MHz (4 Gbps effective), while the R9 M375X has a base clock of 925 MHz, a boost clock of 1015 MHz, and memory at 1125 MHz (4.5 Gbps effective).

Memory subsystems are a key divergence. The GTX 560 uses a 256-bit memory bus with 128.0 GB/s bandwidth, while the R9 M375X uses a 128-bit bus with 72.00 GB/s bandwidth. Despite the AMD card having more memory, its bandwidth is 43.75% lower. The GTX 560 also has higher pixel rate at 11.34 GPixel/s versus 16.24 GPixel/s for the R9 M375X, and higher texture rate at 45.36 GTexel/s versus 40.60 GTexel/s. In floating-point performance, the R9 M375X leads with 1,299.2 GFLOPS compared to the GTX 560’s 1,088.6 GFLOPS.

FAQ

Q: Which GPU has a higher benchmark score in the shared Geekbench OpenCL test?

A: The NVIDIA GeForce GTX 560 scores 9,058, which is 9.5% higher than the AMD Radeon R9 M375X’s score of 8,273.

Q: Does the AMD Radeon R9 M375X support any API that the GTX 560 does not?

A: Yes, the R9 M375X supports Vulkan version 1.2.170 and has a Geekbench Vulkan score of 8,377, while the GTX 560 has no Vulkan support listed.

Q: How does memory capacity and bandwidth compare between the two cards?

A: The R9 M375X has 2 GB of GDDR5 memory on a 128-bit bus with 72.00 GB/s bandwidth, while the GTX 560 has 1024 MB of GDDR5 on a 256-bit bus with 128.0 GB/s bandwidth.

Q: What are the process node and transistor density differences?

A: The GTX 560 uses a 40 nm process with 1,950 million transistors on a 332 mm² die (5.9M / mm²), while the R9 M375X uses a 28 nm process with 1,500 million transistors on a 123 mm² die (12.2M / mm²).

Q: Which card has more shading units and what is the FP32 performance?

A: The R9 M375X has 640 shading units and 1,299.2 GFLOPS FP32 performance, compared to the GTX 560’s 336 shading units and 1,088.6 GFLOPS.

Specification Differences

| Specification | NVIDIA GeForce GTX 560 | AMD Radeon R9 M375X |

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

| Chip | GF114 | Tropo |

| Architecture | Fermi 2.0 | GCN 1.0 |

| Process Node | 40 nm | 28 nm |

| Transistors | 1,950 million | 1,500 million |

| Die Size | 332 mm² | 123 mm² |

| Transistor Density | 5.9M / mm² | 12.2M / mm² |

| Base Clock | N/A | 925 MHz |

| Boost Clock | N/A | 1015 MHz |

| Memory Clock | 1000 MHz (4 Gbps effective) | 1125 MHz (4.5 Gbps effective) |

| Memory Size | 1024 MB | 2 GB |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 128.0 GB/s | 72.00 GB/s |

| Shading Units | 336 | 640 |

| TMUs | 56 | 40 |

| ROPs | 32 | 16 |

| Pixel Rate | 11.34 GPixel/s | 16.24 GPixel/s |

| Texture Rate | 45.36 GTexel/s | 40.60 GTexel/s |

| FP32 | 1,088.6 GFLOPS | 1,299.2 GFLOPS |

| TDP | 150 W | N/A |

| Slot Width | Dual-slot | N/A |

| Power Connectors | 2x 6-pin | N/A |

| Suggested PSU | 450 W | N/A |

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

| Display Outputs | 2x DVI, 1x mini-HDMI 1.3a | N/A |

| DirectX | 12 (11_0) | 12 (11_1) |

| Vulkan | N/A | 1.2.170 |

| Release Date | 2011-05-16 | 2015-05-04 |

| Launch MSRP | 199 USD | N/A |

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, and it clearly favors the NVIDIA GeForce GTX 560. The GTX 560 achieves a score of 9,058, while the AMD Radeon R9 M375X manages 8,273. This yields a delta of 9.5%, meaning the NVIDIA card is nearly a tenth faster in this compute test. Looking at the nearest rivals for context, the GTX 560 sits close to the NVIDIA TITAN V CEO Edition (9,037, 0.2% slower) and the GeForce GTX 660 (9,022, 0.4% slower), while the R9 M375X is comparable to the NVIDIA Quadro K1200 (8,265, 0.7% slower) and the GeForce GTX 675MX (8,427, 1.2% faster). This data suggests the GTX 560’s lead is consistent with its higher percentile ranking (45th vs. 43rd).

Beyond OpenCL, the R9 M375X posts a Geekbench Vulkan score of 8,377, a result that the GTX 560 cannot produce due to lacking Vulkan support. This is a functional win for AMD, as it expands the range of software the card can run. In terms of theoretical throughput, the R9 M375X’s FP32 figure of 1,299.2 GFLOPS exceeds the GTX 560’s 1,088.6 GFLOPS by roughly 19.3%, but this does not translate into a higher OpenCL score. The GTX 560 compensates with a wider memory bus and higher bandwidth, which often benefits memory-bound workloads. Pixel rate also favors the AMD card (16.24 vs. 11.34 GPixel/s), but texture rate slightly favors NVIDIA (45.36 vs. 40.60 GTexel/s).

The Verdict

The data points to a straightforward recommendation for compute-intensive users: the NVIDIA GeForce GTX 560 delivers a 9.5% higher Geekbench OpenCL score than the AMD Radeon R9 M375X, making it the better performer in that specific workload. Its 128.0 GB/s of memory bandwidth and 256-bit bus provide a substantial advantage over the R9 M375X’s 72.00 GB/s, which likely explains the OpenCL victory despite the AMD card’s higher shading unit count and FP32 throughput. The GTX 560 also carries a launch MSRP of 199 USD, though no similar pricing data exists for the R9 M375X.

However, the R9 M375X is not without merit. It offers Vulkan support (version 1.2.170) and a Vulkan benchmark score of 8,377, which the GTX 560 entirely lacks. Its 2 GB memory capacity is double that of the GTX 560, and its newer 28 nm process node with higher transistor density (12.2M / mm² vs. 5.9M / mm²) suggests better power efficiency potential, even though no TDP is listed for the AMD card. The R9 M375X also supports DirectX 12 (11_1) versus the GTX 560’s 12 (11_0), and PCIe 3.0 x16 versus PCIe 2.0 x16.

For users who need maximum OpenCL compute performance, the GTX 560 is the clear winner based on the 9.5% delta. For those who require Vulkan compatibility, more memory, or a more modern feature set with a smaller die, the R9 M375X is the only choice. The GTX 560’s higher average benchmark score (9,058 vs. 8,325) and better percentile ranking (45th vs. 43rd) reinforce its overall performance edge, but the R9 M375X’s unique Vulkan capability and larger frame buffer give it a distinct niche. Neither card is current production, with the GTX 560 released in 2011 and the R9 M375X in 2015, but the data supports picking the GTX 560 for raw compute and the R9 M375X for API versatility.