AMD Radeon R7 M360 vs NVIDIA GeForce 940MX Comparison

The AMD Radeon R7 M360 and NVIDIA GeForce 940MX are both end-of-life mobile graphics solutions from the mid-2010s, built on a 28 nm TSMC process. Benchmark data shows a split decision: the NVIDIA part wins the OpenCL workload, while the AMD part takes the Vulkan test. Their average scores are close enough that real-world performance will depend heavily on the specific application and API being used.

Head-to-Head Benchmarks

The two GPUs split their two head-to-head benchmark comparisons exactly, with each claiming one victory. In the Geekbench OpenCL test, the NVIDIA GeForce 940MX scores 4939, while the AMD Radeon R7 M360 trails with 4638. That translates to a 6.1% advantage for the NVIDIA part. This is the more traditional compute workload, and the 940MX’s lead here is notable but not overwhelming.

The Vulkan benchmark flips the script decisively. The AMD Radeon R7 M360 posts a score of 5223, while the NVIDIA GeForce 940MX manages only 4749. That gives AMD a 10% lead in this test — a larger margin than NVIDIA’s OpenCL advantage. For a modern API like Vulkan, the GCN 3.0 architecture appears to have a distinct edge over Maxwell in this specific workload.

Looking at the broader average benchmark scores, the two cards are nearly inseparable. The R7 M360 averages 4931 across its benchmark suite, while the 940MX averages 4844. That is a difference of roughly 1.8% in favor of AMD. When placed against all GPUs in the database, the R7 M360 sits at the 29th percentile and the 940MX at the 28th — effectively a tie in overall positioning.

The nearest rival data provides additional context. The R7 M360’s closest competitor is the AMD Radeon R7 M265, which scores 4929, a 0% delta. The AMD FirePro W5130M is just 0.6% behind, and the NVIDIA GeForce RTX 5060 Ti 8 GB is also 0.6% behind at 4901. Interestingly, the NVIDIA GeForce GTS 450 trails the R7 M360 by 0.8%. For the 940MX, its nearest rival is the NVIDIA GeForce GTX 560M at 4855, which is 0.2% ahead. The AMD Radeon R6 M255DX is 0.5% ahead, the GTS 450 is 1% ahead, and the RTX 3080 12 GB is 1.1% behind.

The texture and pixel rates tell a mixed story. The 940MX has a higher texture rate at 27.55 GTexel/s versus the R7 M360’s 27.00 GTexel/s — a marginal 2% difference. However, the R7 M360 has a significantly higher pixel rate at 9.000 GPixel/s compared to the 940MX’s 6.888 GPixel/s. That is a 30.7% advantage for AMD in pixel throughput, which can matter in fill-rate-bound scenarios. In raw FP32 compute, the 940MX edges ahead with 881.7 GFLOPS versus 864.0 GFLOPS, a difference of about 2%.

The Verdict

The data presents a nuanced picture. In OpenCL compute, the NVIDIA GeForce 940MX is the stronger choice, delivering a 6.1% higher score. This makes it the better option for applications that rely heavily on OpenCL acceleration. The 940MX also has a slight edge in raw FP32 throughput and texture rate, along with a much higher memory bandwidth of 40.10 GB/s compared to the R7 M360’s 14.40 GB/s — a 178% difference that could affect memory-heavy workloads.

However, the AMD Radeon R7 M360 wins the Vulkan benchmark by a substantial 10% margin. For users running modern Vulkan-based games or applications, the R7 M360 is clearly the better performer. Its pixel rate is also vastly superior, at 30.7% higher than the 940MX, which could benefit certain rendering scenarios. The R7 M360 also has a higher average benchmark score overall.

Which GPU should be selected depends entirely on the target workload. For OpenCL-focused compute tasks, the 940MX is the data-backed pick. For Vulkan workloads and fill-rate-sensitive rendering, the R7 M360 is the winner. Given that both cards are end-of-life and perform within 2% of each other on average, neither is a clear overall champion. The choice should be dictated by the specific API and applications the user intends to run.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R7 M360 has an average benchmark score of 4931, while the NVIDIA GeForce 940MX scores 4844. This gives the R7 M360 an edge of approximately 1.8%.

Q: How does the NVIDIA GeForce 940MX perform in OpenCL compared to the AMD Radeon R7 M360?

A: The 940MX scores 4939 in Geekbench OpenCL, while the R7 M360 scores 4638. This gives the NVIDIA part a 6.1% advantage in this test.

Q: In which benchmark does the AMD Radeon R7 M360 beat the NVIDIA GeForce 940MX?

A: The R7 M360 wins the Geekbench Vulkan test with a score of 5223, compared to the 940MX’s 4749. That is a 10% lead for AMD.

Q: What is the memory bandwidth difference between the two cards?

A: The NVIDIA GeForce 940MX has a memory bandwidth of 40.10 GB/s using GDDR5 memory, while the AMD Radeon R7 M360 has 14.40 GB/s using DDR3 memory. The 940MX’s bandwidth is significantly higher.

Q: Do both GPUs have the same number of ROPs?

A: Yes, both the AMD Radeon R7 M360 and the NVIDIA GeForce 940MX have 8 ROPs.

Q: Which GPU has a higher pixel rate?

A: The AMD Radeon R7 M360 has a pixel rate of 9.000 GPixel/s, while the NVIDIA GeForce 940MX has a pixel rate of 6.888 GPixel/s. The R7 M360 is roughly 30.7% higher.

Specification Differences

The two GPUs differ in several key specifications beyond their benchmark scores. The AMD Radeon R7 M360 has a base clock of 1100 MHz and a boost clock of 1125 MHz, while the NVIDIA GeForce 940MX runs at a base of 795 MHz and a boost of 861 MHz. This means the AMD part has significantly higher clock speeds, though the 940MX compensates with more execution units.

The memory subsystems are notably different. The R7 M360 uses 2 GB of DDR3 memory with a 64-bit bus, running at 900 MHz with 1800 Mbps effective, yielding a bandwidth of 14.40 GB/s. The 940MX also has 2 GB of memory but uses GDDR5, on the same 64-bit bus, at 1253 MHz with 5 Gbps effective, providing 40.10 GB/s of bandwidth — nearly three times higher.

The compute unit counts differ as well. The R7 M360 has 384 shading units, 24 texture mapping units (TMUs), and 8 ROPs. The 940MX has 512 shading units, 32 TMUs, and 8 ROPs. This gives the NVIDIA part a 33% advantage in shading units and TMUs, though the AMD part’s higher clocks narrow the gap in practice.

Power characteristics also diverge. The 940MX has a TDP of 23 W and uses an MXM module form factor with no external power connectors. The R7 M360 has no listed TDP or slot width in the data, but its bus interface is the same as the 940MX: PCIe 3.0 x8. The 940MX’s display outputs are described as "Portable Device Dependent," while no display outputs are listed for the R7 M360.

In terms of API support, the R7 M360 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The 940MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. This means the AMD part supports the higher DirectX feature level, while the NVIDIA part supports a newer Vulkan version.

Architecture Differences

The architectural divide between these two GPUs is significant. The AMD Radeon R7 M360 is built on the GCN 3.0 architecture using the Meso chip, which is part of the "Gem System" generation for R7 M300-series mobile graphics. The NVIDIA GeForce 940MX uses the Maxwell architecture with the GM107 chip, part of the GeForce 900M generation.

Both chips are fabricated on a 28 nm process at TSMC. The AMD chip has 1,550 million transistors on a die size of 125 mm², yielding a transistor density of 12.4M per mm². The NVIDIA chip packs 1,870 million transistors onto a larger 148 mm² die, giving a density of 12.6M per mm². The 940MX’s chip is therefore larger and has more transistors, but the density is nearly identical.

The R7 M360’s GCN 3.0 architecture provides 384 shading units, 24 TMUs, and 8 ROPs. It has a pixel rate of 9.000 GPixel/s, a texture rate of 27.00 GTexel/s, and FP32 performance of 864.0 GFLOPS. It also supports FP16 at 864.0 GFLOPS with a 1:1 ratio. In contrast, the Maxwell-based 940MX has 512 shading units, 32 TMUs, and 8 ROPs. Its pixel rate is 6.888 GPixel/s, texture rate is 27.55 GTexel/s, and FP32 performance is 881.7 GFLOPS. The 940MX has no listed FP16 performance.

The cache hierarchies and memory controllers also reflect the different architectures. The R7 M360 uses DDR3 memory, while the 940MX uses GDDR5, which directly impacts the massive bandwidth difference. The R7 M360’s GCN 3.0 design dates to the Solar System predecessor generation, with Polaris Mobile as its successor. The 940MX’s Maxwell architecture follows GeForce 800M and precedes GeForce 10 Mobile.

Both GPUs are end-of-life products. The R7 M360 was released in May 2015, while the 940MX came later in June 2016. Neither has a launch MSRP listed in the data. The architectural differences — GCN 3.0 versus Maxwell, differing transistor counts, and memory types — explain the benchmark split, with AMD’s newer API support and NVIDIA’s higher execution unit count producing distinct performance profiles across different workloads.