AMD Radeon R5 M335 vs NVIDIA GeForce 840M Comparison

Head-to-Head Benchmarks

The recorded data shows a clear overall winner in direct comparisons. The NVIDIA GeForce 840M takes both benchmark tests, securing 2 wins against 0 for the AMD Radeon R5 M335. The margin, however, is not uniform across tests.

In the Geekbench OpenCL test, the GeForce 840M scores 5764 points against 4745 for the Radeon R5 M335. That is a 21.5% advantage, a substantial lead that reflects a large gap in raw compute throughput. The OpenCL benchmark stresses general-purpose GPU workloads, and the NVIDIA part is decisively ahead here.

The Vulkan test tells a much closer story. The GeForce 840M scores 4880, while the Radeon R5 M335 scores 4758. The delta shrinks to just 2.6%. This suggests that when both GPUs are exercised through the Vulkan API, the architectural strengths of the AMD part narrow the gap considerably, even though it still finishes behind. For a low-power mobile GPU pairing, a 2.6% difference is nearly a tie.

Looking at the broader database context, the GeForce 840M has an average benchmark score of 5322, placing it in the 31st percentile of all GPUs. Its nearest rivals in the database include the NVIDIA GeForce 930A at 5317 (0.1% behind), the NVIDIA GeForce GTX 980M at 5308 (0.3% behind), and the AMD Radeon R7 M445 at 5358 (0.7% ahead). The GeForce 840M sits essentially in the middle of a tight cluster.

The Radeon R5 M335 averages 4752, which places it in the 28th percentile. Its nearest rivals include the AMD Radeon R8 M445DX at 4727 (0.5% behind), the AMD Radeon R5 M255 at 4788 (0.7% ahead), and the NVIDIA Quadro P400 at 4684 (1.5% behind). The R5 M335 is also clustered, but at a lower performance tier than the GeForce 840M.

The absolute gap between the two average scores is 570 points, which corresponds to roughly a 12% overall advantage for the NVIDIA part. However, the Vulkan result shows that the AMD GPU can compete when the workload favors its architecture, so the average score alone does not tell the full story.

Architecture Differences

The two GPUs come from different architectural generations. The NVIDIA GeForce 840M uses the GM108S chip built on the Maxwell architecture, part of the GeForce 800M generation. The AMD Radeon R5 M335 uses the Exo chip based on GCN 1.0, part of the Gem System (R5 M300) generation. Both are fabricated on a 28 nm process at TSMC, so the manufacturing node is identical.

The transistor counts differ notably. The NVIDIA chip packs 1,020 million transistors into a die size of 77 mm², yielding a transistor density of 13.2 million per mm². The AMD chip has 690 million transistors on a 56 mm² die, giving a density of 12.3 million per mm². The NVIDIA chip is both larger and denser, which supports its higher shading unit count.

In terms of compute resources, the GeForce 840M has 384 shading units, 16 texture mapping units, and 8 raster operation units. The Radeon R5 M335 has fewer shading units at 320, but more texture units at 20, and the same 8 ROPs. This explains why the texture rate favors the AMD part: 20.60 GTexel/s versus 17.98 GTexel/s for the NVIDIA. Meanwhile, the pixel rate favors NVIDIA, at 8.992 GPixel/s versus 8.240 GPixel/s.

The floating-point performance follows the shading unit count. The GeForce 840M delivers 863.2 GFLOPS of FP32 throughput, while the Radeon R5 M335 delivers 659.2 GFLOPS. That is a 31% raw compute advantage for NVIDIA, which aligns with the large OpenCL delta.

Memory configurations are similar on paper. Both have 2 GB of DDR3 memory on a 64-bit bus. However, the clock speeds differ: the GeForce 840M runs its memory at 1001 MHz (2 Gbps effective), yielding 16.02 GB/s of bandwidth. The Radeon R5 M335 runs memory at 900 MHz (1800 Mbps effective), giving 14.40 GB/s. The NVIDIA part has a 11% bandwidth advantage.

Both GPUs support DirectX 12, but with different feature levels. The GeForce 840M supports DirectX 12 (11_0), while the Radeon R5 M335 supports DirectX 12 (11_1). OpenGL support is identical at 4.6 for both. Vulkan support differs: NVIDIA offers Vulkan 1.4, while AMD offers Vulkan 1.2.170. The higher Vulkan version on the NVIDIA part may partially explain its lead in the Vulkan benchmark, though the small delta suggests the AMD architecture compensates well.

The GeForce 840M lists a base clock of 1029 MHz and a boost clock of 1124 MHz. The Radeon R5 M335 lists no base or boost clock in the database, so a direct clock comparison is not possible. The NVIDIA GPU has a TDP of 33 W; the AMD GPU has no TDP listed. Both use no power connectors and have a PCIe 3.0 x8 bus interface. Both are marked as end-of-life products, with the GeForce 840M released in March 2014 and the Radeon R5 M335 released in October 2015.

FAQ

Q: Which GPU wins the Geekbench OpenCL test, and by how much?

A: The NVIDIA GeForce 840M wins with a score of 5764 against 4745 for the AMD Radeon R5 M335, a 21.5% advantage.

Q: How close is the Vulkan benchmark result?

A: The Vulkan test is much closer. The GeForce 840M scores 4880, and the Radeon R5 M335 scores 4758, a 2.6% gap in favor of NVIDIA.

Q: Which GPU has more shading units?

A: The GeForce 840M has 384 shading units, while the Radeon R5 M335 has 320 shading units.

Q: Do both GPUs use the same manufacturing process?

A: Yes, both are fabricated on a 28 nm process at TSMC. However, the GeForce 840M has a larger die (77 mm²) and more transistors (1,020 million) than the Radeon R5 M335 (56 mm², 690 million).

Q: Which GPU has higher memory bandwidth?

A: The GeForce 840M has higher memory bandwidth at 16.02 GB/s, compared to 14.40 GB/s for the Radeon R5 M335.

Q: What is the average benchmark score for each GPU?

A: The GeForce 840M has an average score of 5322, placing it in the 31st percentile. The Radeon R5 M335 has an average score of 4752, placing it in the 28th percentile.

Specification Differences

| Specification | NVIDIA GeForce 840M | AMD Radeon R5 M335 |

|---|---|---|

| Chip | GM108S | Exo |

| Architecture | Maxwell | GCN 1.0 |

| Generation | GeForce 800M | Gem System (R5 M300) |

| Transistors | 1,020 million | 690 million |

| Die Size | 77 mm² | 56 mm² |

| Transistor Density | 13.2M / mm² | 12.3M / mm² |

| Base Clock | 1029 MHz | Not listed |

| Boost Clock | 1124 MHz | Not listed |

| Memory Clock | 1001 MHz (2 Gbps effective) | 900 MHz (1800 Mbps effective) |

| Memory Bandwidth | 16.02 GB/s | 14.40 GB/s |

| Shading Units | 384 | 320 |

| TMUs | 16 | 20 |

| Pixel Rate | 8.992 GPixel/s | 8.240 GPixel/s |

| Texture Rate | 17.98 GTexel/s | 20.60 GTexel/s |

| FP32 | 863.2 GFLOPS | 659.2 GFLOPS |

| TDP | 33 W | Not listed |

| DirectX | 12 (11_0) | 12 (11_1) |

| Vulkan | 1.4 | 1.2.170 |

| Release Date | 2014-03-11 | 2015-10-20 |

| Predecessor | GeForce 700M | Solar System |

| Successor | GeForce 900M | Polaris Mobile |

| Average Benchmark Score | 5322 | 4752 |

| Percentile | 31 | 28 |

The Verdict

The data points to a straightforward choice for raw compute performance. The NVIDIA GeForce 840M wins both head-to-head benchmarks, has a higher average score (5322 versus 4752), and sits three percentile points higher in the overall GPU distribution. Its FP32 throughput of 863.2 GFLOPS is 31% higher than the Radeon R5 M335's 659.2 GFLOPS, and its memory bandwidth is also superior.

The AMD Radeon R5 M335 does have a texture rate advantage (20.60 GTexel/s versus 17.98 GTexel/s) and a slightly higher DirectX feature level (12 (11_1) versus 12 (11_0)). But in every aggregate benchmark measure, the NVIDIA part comes out ahead.

For users who prioritize OpenCL-heavy workloads, the GeForce 840M is the clear pick. The 21.5% lead in that test is the single largest margin between the two. For Vulkan-based applications, the choice is less decisive, but the GeForce 840M still wins by 2.6%. Given the overall average score gap of about 12%, the GeForce 840M is the stronger performer in this pairing.

Where Each One Wins

The NVIDIA GeForce 840M wins in the following areas:

• OpenCL performance: 5764 versus 4745, a 21.5% lead. This is the dominant win category.
• Vulkan performance: 4880 versus 4758, a smaller but consistent 2.6% lead.
• Raw FP32 compute: 863.2 GFLOPS versus 659.2 GFLOPS.
• Memory bandwidth: 16.02 GB/s versus 14.40 GB/s.
• Pixel rate: 8.992 GPixel/s versus 8.240 GPixel/s.
• Average benchmark score: 5322 versus 4752.
• Transistor count and density: 1,020 million on 77 mm² versus 690 million on 56 mm².
• Higher Vulkan API version: 1.4 versus 1.2.170.

The AMD Radeon R5 M335 wins in the following areas:

• Texture fill rate: 20.60 GTexel/s versus 17.98 GTexel/s, thanks to its 20 TMUs versus 16.
• DirectX feature level: 12 (11_1) versus 12 (11_0). This may offer compatibility with titles requiring the higher feature set.
• Lower power consumption footprint in terms of transistor budget, though no TDP is listed for comparison.
• The Vulkan benchmark gap is narrow enough (2.6%) that for Vulkan-specific workloads, the AMD part is nearly competitive despite the loss.

In practical terms, users should choose the GeForce 840M for compute-heavy tasks and OpenCL applications. The Radeon R5 M335 is only preferable in texture-bound scenarios or when DirectX 11_1 feature support is required, though the data does not quantify how much that support matters in real-world performance.