AMD Radeon R5 M320 vs NVIDIA GeForce 940M Comparison

FAQ

Q: Which GPU is faster in OpenCL workloads?

A: The NVIDIA GeForce 940M leads the AMD Radeon R5 M320 by 19.1% in Geekbench OpenCL, scoring 6018 versus 5051.

Q: How do the two compare in Vulkan performance?

A: The NVIDIA GeForce 940M wins again, posting 4549 versus 4262, a 6.7% advantage in Geekbench Vulkan.

Q: What are the memory configurations?

A: The AMD Radeon R5 M320 has 4 GB of DDR3 on a 64-bit bus with 16.00 GB/s bandwidth, while the NVIDIA GeForce 940M has 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth.

Q: Which card has a higher shading unit count?

A: The NVIDIA GeForce 940M has 512 shading units, while the AMD Radeon R5 M320 has 320 shading units.

Q: Do both cards support DirectX 12?

A: Yes, but at different feature levels: the NVIDIA GeForce 940M supports DirectX 12 (11_0), while the AMD Radeon R5 M320 supports DirectX 12 (11_1).

Q: What is the transistor count difference?

A: The NVIDIA GeForce 940M uses 1,870 million transistors on a 148 mm² die, whereas the AMD Radeon R5 M320 uses 690 million transistors on a 56 mm² die.

Architecture Differences

The two mobile GPUs come from entirely different design philosophies. The NVIDIA GeForce 940M 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, yielding a transistor density of 12.6M per mm². The AMD Radeon R5 M320 uses the older GCN 1.0 architecture with the Jet chip, also on TSMC's 28 nm node, but with just 690 million transistors on a 56 mm² die, a density of 12.3M per mm². The density figures are nearly identical, but the NVIDIA chip is physically much larger and contains far more logic.

The compute resources diverge sharply. The GeForce 940M features 512 shading units, 32 texture mapping units, and 16 raster output units. The Radeon R5 M320 counters with 320 shading units, 20 TMUs, and only 8 ROPs. These raw counts translate directly into throughput: the NVIDIA part achieves 17.57 GPixel/s pixel rate and 35.14 GTexel/s texture rate, while the AMD part manages 6.840 GPixel/s and 17.10 GTexel/s respectively. In FP32 compute, the GeForce 940M delivers 1,124.4 GFLOPS, which is more than double the Radeon's 547.2 GFLOPS.

Clock speeds tell a similar story. The GeForce 940M runs at a base of 1020 MHz with a boost of 1098 MHz, while the Radeon R5 M320 runs at 780 MHz base and 855 MHz boost. Memory clocks also differ: the NVIDIA card uses 900 MHz memory (1800 Mbps effective), and the AMD card uses 1000 MHz memory (2 Gbps effective). Despite the AMD part's higher memory clock, the NVIDIA card's superior architecture and compute resources make up for its lower memory frequency.

API support shows another generational gap. The GeForce 940M supports Vulkan 1.4 and OpenGL 4.6, while the Radeon R5 M320 supports Vulkan 1.2.170 and OpenGL 4.6. Both are rated for DirectX 12, but the AMD card supports feature level 11_1 versus NVIDIA's 11_0. The NVIDIA card uses an MXM-B (3.0) bus interface as an MXM Module, while the AMD card is an IGP with PCIe 3.0 x8.

Head-to-Head Benchmarks

The recorded benchmark data shows a clear winner across both tests. In Geekbench OpenCL, the NVIDIA GeForce 940M scores 6018 against the AMD Radeon R5 M320's 5051. That is a 19.1% delta in NVIDIA's favor. The margin is substantial and reflects the underlying hardware differences: the GeForce 940M has 60% more shading units, 60% more TMUs, double the ROPs, and roughly double the FP32 throughput.

The Geekbench Vulkan test narrows the gap but still favors NVIDIA. The GeForce 940M scores 4549, while the Radeon R5 M320 scores 4262, a 6.7% delta. Vulkan's lower-level API tends to reduce CPU overhead and can equalize some architectural differences, but the Maxwell GPU still maintains a lead. Interestingly, the Radeon's higher memory bandwidth (16.00 GB/s versus 14.40 GB/s) and larger frame buffer (4 GB versus 2 GB) do not translate into a win in either test.

The overall win count is 2 for the NVIDIA GeForce 940M and 0 for the AMD Radeon R5 M320. The average benchmark score for NVIDIA is 5284, while AMD sits at 4657. In the database's percentile ranking, the GeForce 940M places at the 31st percentile of all GPUs, and the Radeon R5 M320 at the 27th percentile. These are both low-end parts, but the NVIDIA card consistently outperforms its AMD counterpart.

Specification Differences

• Chip: GM107 (NVIDIA) versus Jet (AMD)
• Architecture: Maxwell versus GCN 1.0
• Transistors: 1,870 million versus 690 million
• Die Size: 148 mm² versus 56 mm²
• Transistor Density: 12.6M / mm² versus 12.3M / mm²
• Base Clock: 1020 MHz versus 780 MHz
• Boost Clock: 1098 MHz versus 855 MHz
• Memory Clock: 900 MHz (1800 Mbps effective) versus 1000 MHz (2 Gbps effective)
• Memory Size: 2 GB versus 4 GB
• Memory Bandwidth: 14.40 GB/s versus 16.00 GB/s
• Shading Units: 512 versus 320
• TMUs: 32 versus 20
• ROPs: 16 versus 8
• Pixel Rate: 17.57 GPixel/s versus 6.840 GPixel/s
• Texture Rate: 35.14 GTexel/s versus 17.10 GTexel/s
• FP32: 1,124.4 GFLOPS versus 547.2 GFLOPS
• TDP: 75 W versus not specified
• Slot Width: MXM Module versus IGP
• Bus Interface: MXM-B (3.0) versus PCIe 3.0 x8
• DirectX Support: 12 (11_0) versus 12 (11_1)
• Vulkan Support: 1.4 versus 1.2.170
• Release Date: 2015-03-12 versus 2015-05-04

Where Each One Wins

The NVIDIA GeForce 940M wins in every benchmark category recorded. In OpenCL, its 19.1% advantage is decisive, making it the preferred choice for compute-oriented tasks like OpenCL-accelerated applications, video encoding, and GPU-assisted rendering. The Vulkan win, though smaller at 6.7%, still matters for modern game engines that use this API. The higher pixel rate (17.57 GPixel/s versus 6.840 GPixel/s) and texture rate (35.14 GTexel/s versus 17.10 GTexel/s) suggest better performance in fill-rate-bound scenarios, which often occur in games at lower resolutions or with post-processing effects.

The AMD Radeon R5 M320 does have a few theoretical advantages. It offers 4 GB of memory versus 2 GB, which can help in workloads that exceed the 2 GB frame buffer limit, such as high-resolution textures or certain compute buffers. Its memory bandwidth is slightly higher at 16.00 GB/s versus 14.40 GB/s. It also supports a slightly higher DirectX feature level (11_1 versus 11_0), which could matter for specific DirectX 11.1 features in niche applications. However, none of these advantages produced a measurable win in the recorded benchmarks.

For gaming, the NVIDIA card's higher shading unit count and clock speeds translate to more raw rasterization and shading throughput. The AMD card's lower power draw is not specified, but its IGP form factor suggests it may be easier to integrate into thin notebooks. The NVIDIA card's MXM module form factor, at 75 W TDP, indicates a more substantial cooling requirement.

The Verdict

The benchmark data is unambiguous. The NVIDIA GeForce 940M outperforms the AMD Radeon R5 M320 in both recorded tests, with a 19.1% lead in OpenCL and a 6.7% lead in Vulkan. Its average benchmark score of 5284 versus 4657 represents a 13.5% overall advantage. The NVIDIA card belongs to the GeForce 900M generation, released in March 2015, while the AMD part came from the Gem System (R5 M300) generation, released in May 2015. Both are now end-of-life products.

Buyers seeking a laptop GPU for gaming or compute should choose the NVIDIA GeForce 940M without hesitation. Its 512 shading units, 32 TMUs, and 16 ROPs provide a solid foundation for entry-level 1080p gaming at modest settings. The AMD Radeon R5 M320 might appeal to users who need more than 2 GB of video memory, as it offers 4 GB, but the performance deficit in all measured workloads makes it the weaker option. The database's nearest rivals for the NVIDIA card include the NVIDIA GeForce GTX 980M (within 0.4%), GeForce 930A (0.6% behind), and GeForce 840M (0.7% behind), all of which cluster closely around the 940M's performance level. The AMD card's nearest rivals, such as the NVIDIA Quadro P400 and GeForce GTX 970M, sit within 0.6% to 0.8% of its score, confirming its position in the lower tier of mobile GPUs.

For any user prioritizing compute performance, gaming frame rates, or API compatibility, the NVIDIA GeForce 940M is the clear choice. The AMD Radeon R5 M320 only makes sense if the larger 4 GB frame buffer is a hard requirement and the performance loss is acceptable. Based on the recorded data, the verdict is straightforward: NVIDIA wins on every measurable axis.