AMD Radeon R9 M360 vs NVIDIA GeForce GTX 675MX Comparison

The NVIDIA GeForce GTX 675MX and AMD Radeon R9 M360 are both end-of-life mobile graphics solutions, but they represent different design philosophies and performance tiers. The data shows a clear overall winner in raw compute, with the GTX 675MX holding a 30.6% lead in the only shared benchmark, yet each card exhibits distinct architectural strengths that influence where it fits best. The GTX 675MX posts an average benchmark score of 8427 against the R9 M360’s 8129, placing the NVIDIA part at the 43rd percentile of all GPUs and the AMD part at the 42nd, a narrow overall gap that belies the larger single-test delta.

Head-to-Head Benchmarks

The sole direct comparison available is the Geekbench OpenCL test, and it is decisive. The NVIDIA GeForce GTX 675MX scores 10723, while the AMD Radeon R9 M360 scores 8211. This translates to a 30.6% advantage for the NVIDIA card, a substantial margin that indicates the GTX 675MX delivers roughly a third more compute throughput in this workload. This is not a marginal victory; it is a dominant one. The R9 M360’s score of 8211 puts it closer to its own nearest rivals — the NVIDIA GeForce GTX 950M (8135, a 0.1% deficit) and the NVIDIA GeForce 945M (8099, a 0.4% advantage) — than it does to the GTX 675MX.

Looking at the broader context, the GTX 675MX’s average score of 8427 aligns it with a cluster of competitors including the AMD Radeon 880M (8436, deltaPct -0.1%), the NVIDIA GeForce MX330 (8458, -0.4%), and the AMD Radeon HD 8870M (8462, -0.4%). The R9 M360, with its 8129 average, sits near the NVIDIA GeForce GTX 980 (8167, -0.5%) and the NVIDIA GRID K2 (8080, +0.6%). The head-to-head result shows the GTX 675MX winning the only test where both are present; the R9 M360 has no benchmark victories in this comparison. The win count stands at 1 for NVIDIA and 0 for AMD, making the performance hierarchy unambiguous in this single metric.

Architecture Differences

The two GPUs are built on the same 28 nm process node at TSMC, but their internal designs diverge sharply. The GTX 675MX uses the GK104 chip under NVIDIA’s Kepler architecture, packing 3,540 million transistors into a 294 mm² die. The R9 M360, by contrast, uses AMD’s Tropo chip with GCN 1.0 architecture, holding just 1,500 million transistors on a much smaller 123 mm² die. The transistor density is nearly identical — 12.0 million per mm² for the NVIDIA part versus 12.2 million per mm² for the AMD — but the sheer scale of the Kepler chip gives it a massive resource advantage.

That resource gap shows up in every compute unit count. The GTX 675MX has 960 shading units, 80 texture mapping units, and 32 ROPs, while the R9 M360 has 512 shading units, 32 TMUs, and just 16 ROPs. The NVIDIA part has nearly double the shading units and five times the TMUs, which directly explains its higher texture rate of 52.32 GTexel/s versus the AMD’s 29.60 GTexel/s. Pixel rate tells a different story: the R9 M360 achieves 14.80 GPixel/s, slightly ahead of the GTX 675MX’s 13.08 GPixel/s, thanks to its higher boost clock of 925 MHz versus the NVIDIA’s unspecified base clock. The R9 M360’s FP32 throughput of 947.2 GFLOPS trails the GTX 675MX’s 1,255.7 GFLOPS, a 32.6% deficit that mirrors the OpenCL benchmark result.

Memory configuration is another major split. The GTX 675MX comes with 2 GB of GDDR5 on a 256-bit bus, yielding 115.2 GB/s of bandwidth. The R9 M360 doubles capacity to 4 GB but pairs it with a 128-bit bus, cutting bandwidth to 72.00 GB/s. The memory clock also favors NVIDIA: 3.6 Gbps effective versus the AMD’s 4.5 Gbps effective, though the wider bus compensates. The R9 M360 uses a PCIe 3.0 x16 interface, while the GTX 675MX uses an MXM-B (3.0) module slot, reflecting their different intended chassis. API support is close: both offer DirectX 12 (with NVIDIA at 11_0 and AMD at 11_1), OpenGL 4.6, and Vulkan versions within 0.005 of each other.

Where Each One Wins

The GTX 675MX wins outright in compute-heavy workloads. Its 30.6% OpenCL lead and higher FP32 rate make it the stronger choice for general-purpose GPU compute, rendering, or any task that saturates shading units and texture units. The data shows it also leads in texture throughput (52.32 vs 29.60 GTexel/s) and memory bandwidth (115.2 vs 72.00 GB/s), which benefits large texture fetches and high-resolution filtering. For users running OpenCL-accelerated applications, the GTX 675MX is categorically faster.

The R9 M360 has specific, narrower advantages. Its 4 GB frame buffer is double the NVIDIA’s 2 GB, which can matter for workloads that exceed 2 GB of video memory, even if the bus is narrower. Its higher pixel rate (14.80 vs 13.08 GPixel/s) gives it an edge in fill-rate-bound scenarios, such as simple rasterization at moderate resolutions. The R9 M360 also carries a higher boost clock (925 MHz) and a more capable DirectX 12 feature level (11_1 versus 11_0), which may offer better compatibility with certain modern API features. In the benchmark data, however, the R9 M360 does not win any head-to-head test; its strengths are theoretical or situational rather than demonstrated in the sole available comparison.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 675MX has an average benchmark score of 8427, while the AMD Radeon R9 M360 scores 8129, a difference of 298 points in NVIDIA’s favor.

Q: How much faster is the GTX 675MX in OpenCL?

A: The GTX 675MX scores 10723 in Geekbench OpenCL versus 8211 for the R9 M360, giving the NVIDIA card a 30.6% advantage in that test.

Q: Does the R9 M360 have any benchmark win over the GTX 675MX?

A: No. In the head-to-head data, the R9 M360 has zero wins, while the GTX 675MX has one win (OpenCL). The AMD card does not beat the NVIDIA card in any recorded test.

Q: What is the memory capacity difference between the two?

A: The R9 M360 has 4 GB of GDDR5 memory, which is double the 2 GB found on the GTX 675MX. However, the GTX 675MX has a 256-bit bus providing 115.2 GB/s bandwidth, versus the R9 M360’s 128-bit bus at 72.00 GB/s.

Q: Which GPU has more shading units?

A: The GTX 675MX has 960 shading units, compared to 512 on the R9 M360, giving the NVIDIA part an 87.5% higher count.

Q: Are both GPUs the same process node?

A: Yes, both are fabricated on a 28 nm process at TSMC. The GTX 675MX uses a 294 mm² die with 3,540 million transistors, while the R9 M360 uses a 123 mm² die with 1,500 million transistors.

The Verdict

The data points to the NVIDIA GeForce GTX 675MX as the superior performer in raw compute. Its 30.6% OpenCL lead, higher FP32 throughput (1,255.7 vs 947.2 GFLOPS), and doubled texture rate make it the pick for anyone prioritizing processing power. The GTX 675MX also holds a higher percentile rank (43rd vs 42nd) and a higher average score (8427 vs 8129). The R9 M360’s only quantitative advantages are its 4 GB memory capacity, higher pixel rate (14.80 vs 13.08 GPixel/s), and a slightly better DirectX feature level — none of which translate to a win in the recorded benchmark.

Choose the GTX 675MX if your priority is maximum compute performance, texture-heavy workloads, or higher memory bandwidth. Choose the R9 M360 if you specifically need the larger 4 GB frame buffer for capacity-bound tasks, or if you value its higher pixel rate and boost clock. The benchmark results do not support choosing the AMD card for speed; its appeal rests entirely on memory size and fill-rate characteristics. For general-purpose use, the GTX 675MX is the data-backed winner.

Specification Differences

| Specification | NVIDIA GeForce GTX 675MX | AMD Radeon R9 M360 |

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

| Chip | GK104 | Tropo |

| Architecture | Kepler | GCN 1.0 |

| Process Node | 28 nm | 28 nm |

| Transistors | 3,540 million | 1,500 million |

| Die Size | 294 mm² | 123 mm² |

| Transistor Density | 12.0M / mm² | 12.2M / mm² |

| Memory Size | 2 GB | 4 GB |

| Memory Type | GDDR5 | GDDR5 |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 115.2 GB/s | 72.00 GB/s |

| Shading Units | 960 | 512 |

| TMUs | 80 | 32 |

| ROPs | 32 | 16 |

| Pixel Rate | 13.08 GPixel/s | 14.80 GPixel/s |

| Texture Rate | 52.32 GTexel/s | 29.60 GTexel/s |

| FP32 Performance | 1,255.7 GFLOPS | 947.2 GFLOPS |

| TDP | 100 W | Not specified |

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

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

| Vulkan Version | 1.2.175 | 1.2.170 |

| Release Date | 2012-09-30 | 2015-05-04 |

| Generation | GeForce 600M | Gem System (R9 M300) |

| Predecessor | GeForce 500M | Solar System |

| Successor | GeForce 700M | Polaris Mobile |