AMD Radeon RX 560 vs NVIDIA GeForce 940MX Comparison

The NVIDIA GeForce 940MX and AMD Radeon RX 560 represent two very different approaches to mobile and compact graphics, separated by a generation of process technology and a fundamental shift in performance targets. The data shows a clear hierarchy, with the RX 560 delivering dramatically higher raw compute throughput, while the 940MX focuses on minimal power draw for thin-and-light portables. This analysis breaks down the architectural split, benchmark deltas, and practical use cases based strictly on the provided specifications.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce 940MX has a higher average benchmark score of 4844, compared to the AMD Radeon RX 560’s 4569. However, this aggregate number is skewed by the fact that the RX 560 was tested in more benchmarks, including DirectX 9-12 and compute tests, where its scores are low relative to its OpenCL result.

Q: How large is the performance gap in the shared OpenCL benchmark?

A: In the Geekbench OpenCL test, the AMD Radeon RX 560 scores 16472, which is 70% higher than the NVIDIA GeForce 940MX’s 4939. The deltaPct of -70 indicates the 940MX trails by that margin in this specific head-to-head test.

Q: What is the difference in memory bandwidth?

A: The AMD Radeon RX 560 offers 112.0 GB/s of bandwidth across a 128-bit bus, while the NVIDIA GeForce 940MX is limited to 40.10 GB/s on a 64-bit bus. This is a 2.8x advantage for the RX 560, which directly impacts texture-heavy workloads.

Q: Which GPU has a higher transistor density?

A: The AMD Radeon RX 560, built on GlobalFoundries' 14 nm process, achieves a transistor density of 24.4M / mm². The NVIDIA GeForce 940MX, using TSMC's 28 nm node, has a density of only 12.6M / mm².

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12, but at different feature levels. The NVIDIA GeForce 940MX supports DirectX 12 (11_0), while the AMD Radeon RX 560 supports DirectX 12 (12_0), which is the full-featured version.

Q: What is the physical size difference between the two cards?

A: The AMD Radeon RX 560 is a dual-slot card with a length of 170 mm (6.7 inches). The NVIDIA GeForce 940MX is an MXM Module, meaning its dimensions are portable-device dependent and not specified as a standalone card.

Architecture Differences

The architectural divide between these two GPUs is stark. The NVIDIA GeForce 940MX is built on the Maxwell architecture, using the GM107 chip manufactured by TSMC on a 28 nm process. It packs 1,870 million transistors into a 148 mm² die. In contrast, the AMD Radeon RX 560 uses the GCN 4.0 architecture with the Polaris 21 chip, fabricated by GlobalFoundries on a more advanced 14 nm process. This allows AMD to fit 3,000 million transistors into a smaller 123 mm² die, resulting in a significantly higher transistor density of 24.4M / mm² versus 12.6M / mm².

The core configuration differences are substantial. The RX 560 features 1024 shading units, 64 texture mapping units (TMUs), and 16 raster output units (ROPs). The 940MX is cut down to 512 shading units, 32 TMUs, and only 8 ROPs. This 2:1 ratio in every major compute block explains the massive throughput disparity. Clock speeds also favor AMD: the RX 560 runs at a base of 1175 MHz and boosts to 1275 MHz, while the 940MX operates at a modest 795 MHz base and 861 MHz boost.

Memory architecture reinforces the gap. The RX 560 comes with 4 GB of GDDR5 on a 128-bit interface, delivering 112.0 GB/s. The 940MX has just 2 GB of GDDR5 on a 64-bit bus, yielding only 40.10 GB/s. Both use PCIe 3.0 x8, but the RX 560 offers full DirectX 12 (12_0) support, whereas the 940MX is limited to DirectX 12 (11_0). The RX 560 also supports FP16 compute at a 1:1 ratio with FP32, while the 940MX lists no FP16 capability. Notably, the RX 560’s TDP is 75 W versus the 940MX’s 23 W, reflecting the performance-per-watt trade-off.

Head-to-Head Benchmarks

The only direct head-to-head benchmark available is Geekbench OpenCL, and it is a decisive victory for the AMD Radeon RX 560. The RX 560 scores 16472, while the NVIDIA GeForce 940MX manages only 4939, resulting in a deltaPct of -70 for the NVIDIA part. This means the RX 560 is roughly 3.3 times faster in this compute-oriented workload, which aligns with its 2x shader count, higher clocks, and 2.8x memory bandwidth.

Beyond the shared test, the RX 560’s additional benchmarks show a mixed profile. Its Passmark G3D score is 3671, which is respectable for a card of its class, but its DirectX-specific scores are surprisingly low: 57 in DirectX 9, 25 in DirectX 11, 21 in DirectX 12, and 16 in DirectX 10. The 940MX has no equivalent DirectX scores in the data, so a direct comparison is impossible, but the RX 560’s OpenCL dominance is the standout metric. The 940MX does hold a slight edge in average benchmark score (4844 vs 4569), but this is misleading because the RX 560’s lower Passmark scores drag its average down despite its superior OpenCL result.

The nearest rival data provides context. The 940MX sits at the 28th percentile of all GPUs, with its closest competitor being the NVIDIA GeForce GTX 560M (avg score 4855, deltaPct -0.2). The RX 560, at the 26th percentile, is closely matched with the AMD Radeon R5 M230 (4577, -0.2) and Intel HD Graphics P530 (4560, 0.2). This shows that while the RX 560 wins the head-to-head decisively, both cards occupy the lower-midrange tier of the overall GPU landscape.

The Verdict

The data is unambiguous: the AMD Radeon RX 560 is the substantially more powerful GPU. In the only shared benchmark, it outperforms the NVIDIA GeForce 940MX by 70%, and its architectural advantages in shading units, TMUs, ROPs, memory bus width, and bandwidth are overwhelming. The RX 560 is the choice for anyone needing actual gaming or compute performance in a compact, dual-slot form factor.

However, the NVIDIA GeForce 940MX has its own niche. With a TDP of just 23 W versus 75 W, it is designed for ultra-portable laptops where battery life and thermals are paramount. Its MXM Module form factor and lack of power connectors make it suitable for thin devices. The 940MX also holds a slight edge in average benchmark score (4844 vs 4569) and a higher percentile ranking (28th vs 26th), though this is a statistical artifact of the benchmark mix rather than a real performance win.

For a builder choosing between these two, the decision hinges on the system’s power budget. If the chassis can accommodate a 75 W dual-slot card, the RX 560 is the clear winner, offering 4 GB of VRAM and GTX-class compute. If the goal is a low-power mobile solution, the 940MX is the only viable option, despite its significant performance deficit. The RX 560’s launch MSRP of 99 USD indicates its intended position as an entry-level discrete card, while the 940MX has no listed MSRP due to its OEM-oriented MXM design.

Specification Differences

• Process Node: 28 nm (TSMC) vs 14 nm (GlobalFoundries)
• Transistors: 1,870 million vs 3,000 million
• Die Size: 148 mm² vs 123 mm²
• Transistor Density: 12.6M / mm² vs 24.4M / mm²
• Base Clock: 795 MHz vs 1175 MHz
• Boost Clock: 861 MHz vs 1275 MHz
• Memory Clock: 1253 MHz (5 Gbps effective) vs 1750 MHz (7 Gbps effective)
• Memory Size: 2 GB vs 4 GB
• Memory Bus Width: 64 bit vs 128 bit
• Memory Bandwidth: 40.10 GB/s vs 112.0 GB/s
• Shading Units: 512 vs 1024
• TMUs: 32 vs 64
• ROPs: 8 vs 16
• Pixel Rate: 6.888 GPixel/s vs 20.40 GPixel/s
• Texture Rate: 27.55 GTexel/s vs 81.60 GTexel/s
• FP32: 881.7 GFLOPS vs 2.611 TFLOPS
• FP16: None vs 2.611 TFLOPS (1:1)
• TDP: 23 W vs 75 W
• Slot Width: MXM Module vs Dual-slot
• Suggested PSU: None vs 250 W
• Display Outputs: Portable Device Dependent vs 1x DVI, 1x HDMI 2.0b, 1x DisplayPort 1.4a
• DirectX Support: 12 (11_0) vs 12 (12_0)
• Vulkan Support: 1.4 vs 1.3
• Release Date: 2016-06-27 vs 2017-04-17
• Predecessor: GeForce 800M vs Arctic Islands
• Successor: GeForce 10 Mobile vs Vega

Where Each One Wins

NVIDIA GeForce 940MX:

• Power Efficiency: With a 23 W TDP, it draws less than a third of the RX 560’s 75 W, making it ideal for ultrabooks and thin-and-light laptops.
• Vulkan API Support: It supports Vulkan 1.4, which is a newer version than the RX 560’s Vulkan 1.3, potentially offering better compatibility with the latest Vulkan extensions.
• Average Benchmark Score: Its average score of 4844 edges out the RX 560’s 4569, though this is due to the specific benchmark suite rather than raw performance.

AMD Radeon RX 560:

• Compute Performance: The Geekbench OpenCL score of 16472 crushes the 940MX’s 4939, making it the clear choice for GPGPU workloads.
• Memory Capacity and Bandwidth: The 4 GB frame buffer and 112.0 GB/s bandwidth allow it to handle modern games and high-resolution textures, while the 940MX’s 2 GB and 40.10 GB/s will bottleneck quickly.
• DirectX 12 (12_0) Support: Full DirectX 12 feature level support means better compatibility with modern titles that use advanced rendering features.
• Pixel and Texture Fill Rates: At 20.40 GPixel/s and 81.60 GTexel/s, the RX 560 offers roughly 3x the fill rates of the 940MX, directly translating to higher frame rates.
• FP16 Compute: The 1:1 FP16 ratio allows for accelerated machine learning and certain compute tasks, which the 940MX lacks entirely.