AMD Radeon R7 M360 vs NVIDIA GeForce GTX 980M Comparison

The NVIDIA GeForce GTX 980M and AMD Radeon R7 M360 represent two very different tiers of mobile graphics, separated by a generation and a wide performance gap. The GTX 980M, built on Maxwell 2.0, is a high-end solution that dominates in compute and graphics workloads, while the R7 M360, based on GCN 3.0, is a modest entry-level part. Benchmark data shows the NVIDIA part leading by margins exceeding 200% in every shared test, with architectural and specification differences reinforcing that chasm.

FAQ

Q: How much faster is the NVIDIA GeForce GTX 980M than the AMD Radeon R7 M360 in OpenCL?

A: The GTX 980M scores 23,832 in Geekbench OpenCL, while the R7 M360 scores 4,638. This translates to a delta of 413.8%, meaning the NVIDIA part is over four times faster in that workload.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The GTX 980M sits at the 31st percentile, while the R7 M360 ranks at the 29th percentile. Despite the massive performance gap, both fall in the lower half of the overall GPU distribution.

Q: What is the average benchmark score difference between the two?

A: The GTX 980M has an average benchmark score of 5,308, compared to 4,931 for the R7 M360. The delta is roughly 7.6%, a much smaller gap than the head-to-head tests suggest due to different benchmark sets.

Q: Does the AMD Radeon R7 M360 support any features the GTX 980M lacks?

A: Yes. The R7 M360 supports half-precision FP16 at a 1:1 ratio with FP32 (864.0 GFLOPS each), whereas the GTX 980M lists no FP16 capability. The AMD part also uses a PCIe 3.0 x8 interface, while the NVIDIA card uses MXM-B (3.0).

Q: Which GPU has the higher memory bandwidth?

A: The GTX 980M offers 160.4 GB/s of bandwidth over a 256-bit bus with GDDR5 memory. The R7 M360 provides only 14.40 GB/s over a 64-bit bus with DDR3 memory—a difference of over 11x in favor of the NVIDIA part.

Q: Are both GPUs still in production?

A: No. Both are end-of-life, with the GTX 980M released in October 2014 and the R7 M360 in May 2015. The NVIDIA part’s successor is GeForce 10 Mobile, while AMD’s successor is Polaris Mobile.

Architecture Differences

The GTX 980M is built on NVIDIA’s Maxwell 2.0 architecture with the GM204 chip, fabricated on a 28 nm process at TSMC. It packs 5,200 million transistors into a 398 mm² die, yielding a transistor density of 13.1M per mm². The R7 M360 uses AMD’s GCN 3.0 architecture with the Meso chip, also on TSMC’s 28 nm node, but with only 1,550 million transistors on a 125 mm² die—a density of 12.4M per mm². The NVIDIA chip is over three times larger in transistor count and more than three times larger in die area, reflecting its high-end positioning.

Core configurations diverge sharply. The GTX 980M features 1,536 shading units, 96 texture mapping units (TMUs), and 64 raster operation units (ROPs). The R7 M360 has 384 shading units, 24 TMUs, and just 8 ROPs. This translates to a pixel rate of 72.13 GPixel/s and a texture rate of 108.2 GTexel/s for the NVIDIA part, versus 9.000 GPixel/s and 27.00 GTexel/s for the AMD part. The GTX 980M also delivers 3.462 TFLOPS of FP32 compute, while the R7 M360 manages 864.0 GFLOPS—exactly one quarter of the NVIDIA card’s throughput.

Memory subsystems could not be more different. The GTX 980M uses 8 GB of GDDR5 on a 256-bit bus, reaching 160.4 GB/s. The R7 M360 has 2 GB of DDR3 on a 64-bit bus, capping at 14.40 GB/s. Clock speeds, however, are comparable: the GTX 980M runs at 1038 MHz base and 1127 MHz boost, while the R7 M360 runs at 1100 MHz base and 1125 MHz boost. The AMD part’s memory clock is 900 MHz (1800 Mbps effective), versus 1253 MHz (5 Gbps effective) for the NVIDIA card.

API support differs in DirectX and Vulkan versions. The GTX 980M supports DirectX 12 (12_1) and Vulkan 1.4, while the R7 M360 supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6. The NVIDIA GPU is an MXM Module with no power connectors, while the AMD part uses a PCIe 3.0 x8 interface with no listed slot width or power connector details.

Head-to-Head Benchmarks

The two GPUs share only two benchmark results in the data: Geekbench OpenCL and Geekbench Vulkan. In both, the GTX 980M wins decisively. In OpenCL, the NVIDIA part scores 23,832 against 4,638 for the R7 M360, a 413.8% advantage. That is not a marginal win—it is a fourfold performance gap, reflecting the massive difference in shading units, memory bandwidth, and compute throughput.

In Vulkan, the GTX 980M scores 17,703 versus 5,223, a 238.9% lead. While still dominant, the margin is narrower than in OpenCL, suggesting the AMD part handles the Vulkan workload relatively better. Still, the NVIDIA GPU more than triples the AMD card’s score. Across both tests, the GTX 980M wins 2 out of 2, with the R7 M360 taking zero wins.

Looking at broader benchmark data, the GTX 980M has additional scores in 3DMark Steel Nomad (649), PassMark DirectX 10 (35), DirectX 11 (57), DirectX 12 (31), DirectX 9 (125), G2D (490), G3D (7,338), and GPU Compute (2,816). The R7 M360 has no comparable results in those tests, making the head-to-head comparison limited but unambiguous. The average benchmark score for the GTX 980M is 5,308, while the R7 M360 averages 4,931—a smaller relative gap because the NVIDIA part’s extensive benchmark suite includes lower-scoring API tests.

Specification Differences

The two GPUs differ in nearly every measurable specification. The GTX 980M uses the GM204 chip with Maxwell 2.0 architecture, while the R7 M360 uses the Meso chip with GCN 3.0. Transistor counts are 5,200 million versus 1,550 million, and die sizes are 398 mm² versus 125 mm². The NVIDIA part has 1,536 shading units, 96 TMUs, and 64 ROPs; the AMD part has 384 shading units, 24 TMUs, and 8 ROPs.

Memory capacity is 8 GB GDDR5 versus 2 GB DDR3, with bus widths of 256-bit versus 64-bit. Bandwidth is 160.4 GB/s versus 14.40 GB/s. The GTX 980M’s base clock is 1038 MHz with a 1127 MHz boost; the R7 M360’s base is 1100 MHz with a 1125 MHz boost. Memory clocks are 1253 MHz (5 Gbps effective) versus 900 MHz (1800 Mbps effective). Pixel rates are 72.13 GPixel/s versus 9.000 GPixel/s, and texture rates are 108.2 GTexel/s versus 27.00 GTexel/s.

FP32 compute is 3.462 TFLOPS for the NVIDIA part versus 864.0 GFLOPS for the AMD part. The R7 M360 lists FP16 at 864.0 GFLOPS (1:1), while the GTX 980M has no FP16 figure. DirectX support is 12_1 versus 12_0, Vulkan is 1.4 versus 1.2.170, and the bus interface is MXM-B (3.0) versus PCIe 3.0 x8. The GTX 980M uses an MXM Module slot width with no power connectors; the R7 M360 lists no slot width or power connector details. Release dates are October 2014 versus May 2015, with predecessors GeForce 800M versus Solar System and successors GeForce 10 Mobile versus Polaris Mobile.

The Verdict

The data leaves no ambiguity: the NVIDIA GeForce GTX 980M is the overwhelmingly stronger GPU. It leads by 413.8% in OpenCL and 238.9% in Vulkan, with a 7.6% higher average benchmark score. Its 8 GB GDDR5 memory, 256-bit bus, and 160.4 GB/s bandwidth dwarf the R7 M360’s 2 GB DDR3 and 14.40 GB/s. Any workload involving compute, texturing, or pixel throughput will favor the NVIDIA part by multiples.

The R7 M360 does have one unique trait: FP16 support at 1:1 ratio with FP32, which the GTX 980M lacks entirely. It also uses a more modern PCIe 3.0 x8 interface versus the MXM-B (3.0) standard. But these are narrow technical edges that do not offset a 4x compute deficit. For a user prioritizing raw performance, the GTX 980M is the only choice. For a user needing FP16 compute or a simpler PCIe-based integration, the R7 M360 could be considered, but benchmark results indicate it will deliver a fraction of the GTX 980M’s capability in most tasks.