AMD Radeon R9 M375 vs NVIDIA GeForce GTX 980 Comparison

Where Each One Wins

The recorded data splits these two GPUs into clearly different performance tiers. The AMD Radeon R9 M375 does not win a single head-to-head benchmark in the database. The NVIDIA GeForce GTX 980 wins all two recorded comparisons. That is a clean sweep, but the margin of victory matters more than the count.

In Geekbench OpenCL, the GTX 980 scores 34,676 against the R9 M375's 10,457. That is a 69.8% advantage for NVIDIA. In Geekbench Vulkan, the GTX 980 posts 22,543 versus 9,682, a 57.1% lead. The Vulkan gap is narrower than the OpenCL gap, but both are decisive. No workload category in the database flips the result in favor of the AMD part.

The R9 M375's average benchmark score is 10,070, placing it at the 48th percentile of all GPUs in the database. The GTX 980's average is lower at 8,167, with a 43rd percentile ranking. This apparent contradiction is worth explaining. The GTX 980's average is dragged down by its inclusion of older DirectX 9 and DirectX 10 Passmark tests, where it scores 164 and 53 respectively. These legacy tests are not part of the head-to-head set. In the two modern compute and graphics APIs that both cards share, the NVIDIA part dominates.

The R9 M375's nearest rivals in the database are all within a tight band. The NVIDIA Quadro K5100M sits 0.3% behind, the AMD Radeon Pro 5300M is 0.6% behind, and the NVIDIA GeForce GTX 870M is 1.1% behind. Only the NVIDIA GeForce GTX 950A is ahead, by 2%. This cluster means the R9 M375 is a mid-pack mobile or small desktop part, competitive with other modest GPUs of its era but nowhere near the GTX 980's class.

The GTX 980's nearest rivals are similarly clustered but at a much lower average score level. The GeForce GTX 950M is 0.4% behind, the Radeon R9 M360 is 0.5% behind, and the GeForce 945M is 0.8% behind. The NVIDIA GRID K2 trails by 1.1%. Those rivals are all far below the GTX 980's head-to-head scores. The data indicates the GTX 980's average is suppressed by its legacy test scores, not by a weakness in modern workloads.

Architecture Differences

The two chips come from different architectural lineages and different physical scales. The R9 M375 uses the Tropo chip built on GCN 1.0, AMD's first-generation Graphics Core Next design. The GTX 980 uses the GM204 chip on Maxwell 2.0, NVIDIA's second-generation Maxwell architecture. Both are fabricated on a 28 nm process at TSMC, so the node is identical. The differences come from die size, transistor count, and feature support.

The GTX 980's GM204 packs 5,200 million transistors on a 398 mm² die, giving a transistor density of 13.1 million per square millimeter. The R9 M375's Tropo die is far smaller at 123 mm² with 1,500 million transistors, for a density of 12.2 million per square millimeter. The NVIDIA chip has roughly 3.5 times the transistor count and more than three times the die area. That physical advantage translates directly into more execution resources.

Shader and texture hardware strongly favor NVIDIA. The GTX 980 has 2,048 shading units, 128 texture mapping units, and 64 raster output units. The R9 M375 has 640 shading units, 40 TMUs, and 16 ROPs. In every category, the GTX 980 has more than three times the hardware. Pixel rate is 77.82 GPixel/s versus 16.24 GPixel/s. Texture rate is 155.6 GTexel/s versus 40.60 GTexel/s. FP32 compute is 4.981 TFLOPS versus 1,299.2 GFLOPS.

Memory architecture is another major split. The R9 M375 uses 2 GB of DDR3 on a 128-bit bus, yielding 28.80 GB/s of bandwidth. The GTX 980 uses 4 GB of GDDR5 on a 256-bit bus, yielding 224.4 GB/s. That is nearly eight times the memory bandwidth. Clock speeds also favor NVIDIA: the GTX 980 runs at a base of 1127 MHz and boosts to 1216 MHz, while the R9 M375 runs at 1000 MHz base and 1015 MHz boost. The memory clocks are 1753 MHz (7 Gbps effective) for NVIDIA versus 900 MHz (1800 Mbps effective) for AMD.

API support differs in DirectX version. The GTX 980 supports DirectX 12 (12_1), while the R9 M375 supports DirectX 12 (11_1). Both support OpenGL 4.6. Vulkan versions differ: the GTX 980 reports Vulkan 1.4, the R9 M375 reports Vulkan 1.2.170. The GTX 980 also carries a 165 W TDP, dual-slot cooling, two 6-pin power connectors, and a suggested 450 W power supply. The R9 M375 lists no TDP, no slot width, and no power connector information in the database.

Head-to-Head Benchmarks

The database records two shared benchmarks between these GPUs. Geekbench OpenCL is the larger gap. The GTX 980 scores 34,676 against the R9 M375's 10,457. The delta is -69.8% from the AMD card's perspective, meaning the R9 M375 trails by nearly 70%. In raw terms, the NVIDIA card is about 3.3 times faster in this compute workload. That aligns with the hardware resource ratio: more shaders, more bandwidth, and higher clocks all feed into OpenCL performance.

Geekbench Vulkan narrows the gap but does not change the outcome. The GTX 980 scores 22,543 versus 9,682 for the R9 M375, a 57.1% deficit for AMD. Here the NVIDIA card is roughly 2.3 times faster. The smaller Vulkan gap may reflect driver efficiency or the lower overhead of Vulkan on the older GCN architecture, but the recorded data does not explain the cause. The result is still a decisive NVIDIA win.

The R9 M375's best showing in the database is its Geekbench OpenCL score of 10,457. That is just 4.1% above its own average of 10,070. Its Vulkan score of 9,682 is slightly below its average. The GTX 980, by contrast, shows more spread across its benchmark suite. Its Geekbench OpenCL score of 34,676 is far above its average of 8,167, while its legacy Passmark DirectX 9 score of 164 is far below. This spread is why the GTX 980's percentile ranking is lower than the R9 M375's despite winning every head-to-head test.

Looking only at the head-to-head data, the GTX 980 is the clear winner in both recorded workloads. The R9 M375's nearest rivals cluster near 10,000 average score, which matches its own average. The GTX 980's nearest rivals cluster near 8,100 average score, which reflects its legacy test drag. The head-to-head tests, not the averages, are the better measure of relative modern performance.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 980 wins with a score of 34,676 against the AMD Radeon R9 M375's 10,457, a 69.8% advantage.

Q: Is the R9 M375 competitive in Vulkan?

A: No. The GTX 980 scores 22,543 in Geekbench Vulkan, while the R9 M375 scores 9,682. The AMD card trails by 57.1%.

Q: Why does the GTX 980 have a lower percentile ranking than the R9 M375?

A: The GTX 980 sits at the 43rd percentile with an average score of 8,167, while the R9 M375 sits at the 48th percentile with an average of 10,070. The GTX 980's average is reduced by low legacy Passmark DirectX 9 and DirectX 10 scores of 164 and 53.

Q: How do the memory subsystems compare?

A: The R9 M375 has 2 GB of DDR3 on a 128-bit bus with 28.80 GB/s bandwidth. The GTX 980 has 4 GB of GDDR5 on a 256-bit bus with 224.4 GB/s bandwidth.

Q: Which card has more shading units?

A: The GTX 980 has 2,048 shading units. The R9 M375 has 640 shading units.

Q: Are both cards on the same manufacturing process?

A: Yes, both use TSMC's 28 nm process. The GTX 980 uses the GM204 chip with 5,200 million transistors, and the R9 M375 uses the Tropo chip with 1,500 million transistors.

The Verdict

The data supports a straightforward choice for anyone comparing these two GPUs directly. The NVIDIA GeForce GTX 980 wins every recorded head-to-head benchmark, with margins of 69.8% in OpenCL and 57.1% in Vulkan. It has more than three times the shading units, TMUs, and ROPs. Its memory bandwidth of 224.4 GB/s dwarfs the R9 M375's 28.80 GB/s. Its FP32 compute of 4.981 TFLOPS is roughly 3.8 times the R9 M375's 1,299.2 GFLOPS.

The GTX 980 is also a physically larger card. It measures 267 mm in length, 111 mm in height, and 40 mm in width, with a dual-slot cooler and two 6-pin power connectors. The R9 M375 has no listed dimensions, slot width, or power connectors. The GTX 980 lists a TDP of 165 W and a suggested 450 W power supply. The R9 M375 has no TDP data.

The R9 M375 is not a bad GPU in its own tier. Its average score of 10,070 places it just ahead of the Quadro K5100M by 0.3% and the Radeon Pro 5300M by 0.6%. It trails only the GeForce GTX 950A by 2% among its nearest rivals. For someone limited to that performance class, the R9 M375 is a reasonable mid-pack option. But against the GTX 980, it is outclassed in every measurable way.

The GTX 980's lower percentile ranking and lower average score should not mislead a buyer. Those figures reflect its inclusion of legacy DirectX 9 and DirectX 10 Passmark tests, not its modern compute performance. In the two shared benchmarks, the GTX 980 is the clear and consistent winner. The verdict from the database is unambiguous: choose the GTX 980 for higher performance in modern workloads, and choose the R9 M375 only if the GTX 980's physical size, power requirements, or launch MSRP of 549 USD are unacceptable constraints.

Specification Differences

| Specification | AMD Radeon R9 M375 | NVIDIA GeForce GTX 980 |

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

| Architecture | GCN 1.0 | Maxwell 2.0 |

| Chip | Tropo | GM204 |

| Transistors | 1,500 million | 5,200 million |

| Die Size | 123 mm² | 398 mm² |

| Transistor Density | 12.2M / mm² | 13.1M / mm² |

| Base Clock | 1000 MHz | 1127 MHz |

| Boost Clock | 1015 MHz | 1216 MHz |

| Memory Clock | 900 MHz, 1800 Mbps effective | 1753 MHz, 7 Gbps effective |

| Memory Size | 2 GB | 4 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 256 bit |

| Memory Bandwidth | 28.80 GB/s | 224.4 GB/s |

| Shading Units | 640 | 2048 |

| TMUs | 40 | 128 |

| ROPs | 16 | 64 |

| Pixel Rate | 16.24 GPixel/s | 77.82 GPixel/s |

| Texture Rate | 40.60 GTexel/s | 155.6 GTexel/s |

| FP32 | 1,299.2 GFLOPS | 4.981 TFLOPS |

| TDP | Not listed | 165 W |

| Slot Width | Not listed | Dual-slot |

| Power Connectors | Not listed | 2x 6-pin |

| Suggested PSU | Not listed | 450 W |

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

| Vulkan | 1.2.170 | 1.4 |

| Length | Not listed | 267 mm (10.5 inches) |

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

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

| Display Outputs | Not listed | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 |

| Launch MSRP | Not listed | 549 USD |