AMD Radeon R9 M360 vs NVIDIA GeForce GTX 980 Comparison

The NVIDIA GeForce GTX 980 and AMD Radeon R9 M360 are both end-of-life graphics processors, but they serve entirely different segments of the market. The GTX 980, built on the Maxwell 2.0 architecture, is a desktop-class part with a 5,200 million transistor count on a 398 mm² die, while the R9 M360, using GCN 1.0, is a mobile-oriented chip with 1,500 million transistors on a 123 mm² die. Despite this massive gulf in physical resources, the average benchmark scores are remarkably close: the GTX 980 averages 8,167 points, while the R9 M360 averages 8,129 points, a difference of only 0.5%. This near-parity in aggregate scoring, however, masks a stark divergence in individual workloads, where the GTX 980's raw compute power proves dominant.

FAQ

Q: How does the NVIDIA GeForce GTX 980 compare to the AMD Radeon R9 M360 in average benchmark score?

A: The GTX 980 has an average benchmark score of 8,167, while the R9 M360 scores 8,129. This places the GTX 980 just 0.5% ahead, and both cards sit near the 42nd and 43rd percentiles of all GPUs, respectively.

Q: Which card wins in the head-to-head benchmark comparisons?

A: The GTX 980 wins both available head-to-head tests. In Geekbench OpenCL, it scores 34,676 versus 8,211 for the R9 M360, a margin of 322.3%. In Geekbench Vulkan, the GTX 980 scores 22,543 against 8,047, a 180.1% advantage.

Q: What are the architectural foundations of each GPU?

A: The GTX 980 uses the GM204 chip with Maxwell 2.0 architecture, built on a 28 nm process at TSMC. The R9 M360 uses the Tropo chip with GCN 1.0 architecture, also on a 28 nm process at TSMC.

Q: How do the memory subsystems differ between the two cards?

A: Both cards have 4 GB of GDDR5 memory, but the GTX 980 uses a 256-bit bus with 224.4 GB/s bandwidth, while the R9 M360 uses a 128-bit bus with 72.00 GB/s bandwidth. The GTX 980's memory clock is 7 Gbps effective, versus 4.5 Gbps for the R9 M360.

Q: What API levels does each card support?

A: The GTX 980 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R9 M360 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170.

Q: Which card has a higher transistor density?

A: The GTX 980 has a transistor density of 13.1M / mm², while the R9 M360 has 12.2M / mm². Despite the R9 M360's smaller die, the GTX 980 packs a higher density of transistors.

Where Each One Wins

The data presents a clear dichotomy: the GTX 980 wins in raw computational throughput, while the R9 M360's only strength is its relatively competitive aggregate score, which is buoyed by its inclusion in a limited set of benchmark data. The GTX 980's victory in both head-to-head tests is decisive. In Geekbench OpenCL, the GTX 980's 34,676 score is over four times higher than the R9 M360's 8,211. This indicates a massive advantage in compute-heavy tasks like physics simulation, rendering, and general-purpose GPU computing. Similarly, in Geekbench Vulkan, the GTX 980's 22,543 score dwarfs the R9 M360's 8,047, suggesting far superior performance in modern graphics APIs that leverage low-level hardware access.

The R9 M360, however, does not win any of the two head-to-head tests (winsA: 2, winsB: 0). Its only claim to relevance is that its average benchmark score of 8,129 is within 0.5% of the GTX 980's 8,167, which is a statistical artifact of the different test suites available for each card. The GTX 980 has a comprehensive set of benchmarks including 3DMark Steel Nomad DX12, PassMark DX9/10/11/12, and PassMark G2D/G3D, while the R9 M360 only has two Geekbench entries. The R9 M360's wins are therefore not in performance, but in its smaller physical footprint and lower power demands, though the data does not specify TDP or dimensions for the AMD part.

Architecture Differences

The architectural gap between these two GPUs is fundamental. The GTX 980 is built on Maxwell 2.0, an architecture designed for high desktop performance with a focus on efficiency and advanced features like DirectX 12 (12_1) support. It integrates 2,048 shading units, 128 texture mapping units (TMUs), and 64 raster operations pipelines (ROPs), enabling a pixel rate of 77.82 GPixel/s and a texture rate of 155.6 GTexel/s. The R9 M360, in contrast, uses GCN 1.0, AMD's first-generation compute-oriented design, with only 512 shading units, 32 TMUs, and 16 ROPs, yielding a pixel rate of 14.80 GPixel/s and a texture rate of 29.60 GTexel/s.

The transistor counts tell a story of scale: the GTX 980 has 5,200 million transistors versus 1,500 million for the R9 M360. This 3.5x difference in transistor budget translates directly into the GTX 980's 4.981 TFLOPS of FP32 performance, compared to the R9 M360's 947.2 GFLOPS. The GTX 980 also has a higher transistor density at 13.1M / mm² versus 12.2M / mm², indicating a more efficient use of silicon area. The R9 M360's GCN 1.0 architecture supports DirectX 12 (11_1), which is a lower feature level than the GTX 980's 12_1, meaning the AMD card lacks some of the advanced rendering features available on the NVIDIA part.

Specification Differences

The two cards differ across nearly every measurable specification. The GTX 980 has a base clock of 1127 MHz and a boost clock of 1216 MHz, while the R9 M360 runs at 900 MHz base and 925 MHz boost. The GTX 980's memory operates at 1753 MHz (7 Gbps effective) with a 256-bit bus, delivering 224.4 GB/s of bandwidth; the R9 M360's memory is slower at 1125 MHz (4.5 Gbps effective) on a 128-bit bus, providing 72.00 GB/s. The shading units, TMUs, and ROPs are all significantly higher on the GTX 980, as are the pixel and texture rates.

The GTX 980 has a TDP of 165 W and requires a 450 W power supply with dual 6-pin connectors, while the R9 M360 lists no TDP, power connectors, or suggested PSU, which is typical for a mobile part. The GTX 980 is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width, with display outputs of 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The R9 M360 has no listed dimensions or display outputs. The GTX 980 was released on 2014-09-18 with a launch MSRP of 549 USD, while the R9 M360 was released on 2015-05-04 without a launch MSRP.

Head-to-Head Benchmarks

The head-to-head data is limited to two tests, but the results are unambiguous. In Geekbench OpenCL, the GTX 980 scores 34,676 against the R9 M360's 8,211, yielding a delta of 322.3% in favor of NVIDIA. This is the largest win in the comparison and highlights the GTX 980's superior compute capability, which is driven by its 4.981 TFLOPS FP32 throughput versus 947.2 GFLOPS for the AMD card. The OpenCL test is a raw measure of parallel processing power, and the GTX 980's 2,048 shading units simply overwhelm the R9 M360's 512.

In Geekbench Vulkan, the GTX 980 scores 22,543, while the R9 M360 scores 8,047, a delta of 180.1%. While this is a smaller margin than OpenCL, it still represents a dominant victory. The Vulkan test exercises the GPU's ability to handle modern graphics workloads with low overhead. Despite the R9 M360's GCN 1.0 architecture having some compute strengths, its lower Vulkan version support (1.2.170 versus 1.4) and fewer execution resources limit its performance. The GTX 980's higher memory bandwidth (224.4 GB/s versus 72.00 GB/s) also plays a role in this test, as Vulkan workloads often stress memory access patterns.

These two wins give the GTX 980 a 2-0 record in direct comparisons. The aggregate average scores, which place the two cards within 0.5% of each other, are misleading; they are the result of the GTX 980 being tested across a broader range of workloads, including older DirectX 9 and 10 benchmarks, where its scores are lower relative to its modern compute performance. In any scenario that leverages the GTX 980's full compute and memory capabilities, the data shows it is in a completely different performance class from the R9 M360.