AMD Radeon RX 560 vs NVIDIA GeForce 840M Comparison

NVIDIA GeForce 840M and AMD Radeon RX 560 represent two distinct approaches to mobile and desktop graphics, separated by three years of silicon evolution. The 840M is a low-power notebook part built on the Maxwell architecture, while the RX 560 is a desktop graphics card based on GCN 4.0. The recorded data shows a single head-to-head benchmark result, with the RX 560 delivering a decisive performance advantage. This analysis examines the benchmark scores, architectural differences, and positional data from the database to characterize what each product offers.

Head-to-Head Benchmarks

The database contains one direct comparison test between the NVIDIA GeForce 840M and the AMD Radeon RX 560, using the Geekbench OpenCL workload. In this test, the AMD Radeon RX 560 scored 16,472 points, while the NVIDIA GeForce 840M scored 5,764 points. The delta between the two is 65%, meaning the RX 560 outperforms the 840M by that margin in this specific compute benchmark. This is the only recorded head-to-head result, so the overall win count stands at 0 wins for the 840M and 1 win for the RX 560.

The magnitude of this difference is substantial. An OpenCL score of 16,472 versus 5,764 indicates that the RX 560 completes compute workloads in roughly one third of the time required by the 840M, assuming linear scaling. The 65% delta is not a marginal edge; it places the two products in entirely different performance classes for general-purpose GPU compute tasks. OpenCL performance often correlates with shading throughput, memory bandwidth, and raw execution resource counts, all of which are heavily skewed toward the RX 560 in the recorded specifications.

Looking beyond the head-to-head, the average benchmark scores from the database reinforce the gap, though with a caveat. The 840M has an average benchmark score of 5,322 across its recorded tests, while the RX 560 has an average of 4,569. This appears contradictory at first glance, but the averages are drawn from different test sets. The 840M has two recorded benchmark entries: Geekbench OpenCL at 5,764 and Geekbench Vulkan at 4,880. The RX 560 has nine recorded entries, including multiple Passmark tests with lower scores that pull its average downward. The direct comparison remains the cleaner signal: in the shared OpenCL workload, the RX 560 leads by 65%.

The percentile rankings also tell a nuanced story. The 840M sits at the 31st percentile of all GPUs in the database, while the RX 560 sits at the 26th percentile. These percentiles are based on each product's own average score relative to the full database, not on the head-to-head result. Because the RX 560's average is depressed by its Passmark entries, its percentile appears lower despite its clear win in the direct comparison. Users should interpret the percentile field as a measure of overall recorded performance spread, not as a direct ranking between these two specific parts.

The Verdict

The benchmark data is unambiguous on the central question: the AMD Radeon RX 560 is the faster GPU. Its 65% lead in Geekbench OpenCL over the NVIDIA GeForce 840M is a dominant margin that no other recorded metric contradicts. The RX 560 also brings a larger memory pool, wider memory bus, and more execution resources, all of which support its higher compute score. For any workload that stresses the GPU, the RX 560 is the choice.

The 840M, however, is not without its own positional strengths. It draws only 33 W of power, compared to the RX 560's 75 W, and it is designed as an integrated graphics processor (IGP) with no power connectors, making it suitable for thin and light notebooks. The RX 560 is a dual-slot desktop card with a 250 W suggested power supply and a 170 mm length. These are not comparable physical designs. The 840M exists to provide modest graphics capability inside a portable chassis, while the RX 560 exists to deliver real performance in a desktop tower. The data shows that the RX 560 wins on raw compute, but the 840M wins on integration and power efficiency.

The launch MSRP for the RX 560 was 99 USD. This is the only price data in the database, and it is presented here for reference. The 840M has no recorded launch MSRP in the database.

Where Each One Wins

The AMD Radeon RX 560 wins in every recorded compute benchmark comparison. Its Geekbench OpenCL score of 16,472 is nearly three times the 840M's 5,764. It also has a Geekbench Metal score of 18,941, a test the 840M does not have recorded. The RX 560's Passmark results include a G3D score of 3,671, a G2D score of 485, and a GPU compute score of 1,437. These are not compared directly to 840M scores, but they demonstrate a broad benchmark profile across DirectX 9, 10, 11, and 12. The RX 560's fp32 compute is rated at 2.611 TFLOPS, and its texture fill rate is 81.60 GTexel/s, both far above the 840M's figures of 863.2 GFLOPS and 17.98 GTexel/s. For gaming, rendering, or compute tasks, the RX 560 is the superior part in every measured dimension.

The NVIDIA GeForce 840M wins in the power and form factor categories. Its 33 W TDP is less than half of the RX 560's 75 W figure. It uses DDR3 memory with a 64 bit bus, which is modest in bandwidth but appropriate for an integrated solution. The 840M is classified as an IGP with no power connectors, meaning it can be deployed in systems without additional power delivery. The RX 560, by contrast, is dual-slot, measures 170 mm in length, and requires a suggested power supply of 250 W. The 840M's display outputs are listed as portable device dependent, while the RX 560 offers 1x DVI, 1x HDMI 2.0b, and 1x DisplayPort 1.4a. For a mobile system where power draw and physical footprint are the primary constraints, the 840M is the appropriate part. The 840M also supports Vulkan 1.4, a newer API version than the RX 560's Vulkan 1.3, though both support DirectX 12 and OpenGL 4.6.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD Radeon RX 560 scored 16,472 in Geekbench OpenCL, compared to the NVIDIA GeForce 840M's 5,764, a 65% difference in favor of the RX 560.

Q: How do the memory configurations compare?

A: The RX 560 uses 4 GB of GDDR5 memory on a 128 bit bus with 112.0 GB/s bandwidth. The 840M uses 2 GB of DDR3 memory on a 64 bit bus with 16.02 GB/s bandwidth.

Q: What is the power draw difference?

A: The 840M has a TDP of 33 W, while the RX 560 has a TDP of 75 W. The RX 560 also requires a suggested power supply of 250 W, while the 840M has no power connectors.

Q: Which GPU supports newer graphics APIs?

A: The 840M supports Vulkan 1.4 and DirectX 12 (11_0). The RX 560 supports Vulkan 1.3 and DirectX 12 (12_0). Both support OpenGL 4.6.

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

A: The 840M has an average benchmark score of 5,322 across its recorded tests. The RX 560 has an average of 4,569 across its recorded tests, though the RX 560's average includes several lower Passmark scores that the 840M does not have recorded.

Q: How do the shading units and texture units compare?

A: The RX 560 has 1,024 shading units, 64 texture units, and 16 ROPs. The 840M has 384 shading units, 16 texture units, and 8 ROPs.

Architecture Differences

The two GPUs come from different manufacturers, foundries, and process nodes. The NVIDIA GeForce 840M uses the GM108S chip built on the Maxwell architecture at a 28 nm process node from TSMC. The die contains 1,020 million transistors on a 77 mm² die, giving a transistor density of 13.2 million transistors per mm². The AMD Radeon RX 560 uses the Polaris 21 chip built on GCN 4.0 at a 14 nm process node from GlobalFoundries. Its die contains 3,000 million transistors on a 123 mm² die, giving a transistor density of 24.4 million transistors per mm². The RX 560 packs nearly three times the transistor count into a die that is only about 60% larger, a direct result of the smaller process node.

Clock speeds differ as well. The 840M runs at a base clock of 1029 MHz and a boost clock of 1124 MHz, with memory at 1001 MHz (2 Gbps effective). The RX 560 runs at a base clock of 1175 MHz and a boost clock of 1275 MHz, with memory at 1750 MHz (7 Gbps effective). The RX 560 has higher clocks on both the core and the memory, compounding its architectural advantages.

The execution resource gap is large. The 840M has 384 shading units, 16 texture mapping units, and 8 render output units. The RX 560 has 1,024 shading units, 64 texture units, and 16 ROPs. This translates directly to throughput: the 840M delivers 8.992 GPixel/s pixel rate and 17.98 GTexel/s texture rate, while the RX 560 delivers 20.40 GPixel/s and 81.60 GTexel/s. Floating point performance follows the same pattern, with the 840M rated at 863.2 GFLOPS for fp32 and the RX 560 rated at 2.611 TFLOPS. The RX 560 also has a recorded fp16 rate of 2.611 TFLOPS at a 1:1 ratio, while the 840M has no fp16 figure recorded.

Memory architecture is another major divider. The 840M uses 2 GB of DDR3 on a 64 bit bus, yielding 16.02 GB/s of bandwidth. The RX 560 uses 4 GB of GDDR5 on a 128 bit bus, yielding 112.0 GB/s. That is a sevenfold difference in memory bandwidth, which heavily influences compute and gaming workloads. The 840M's memory clock of 1001 MHz is also far below the RX 560's 1750 MHz.

The physical and electrical designs reflect their intended deployment. The 840M is an IGP with no power connectors, a 33 W TDP, and portable device dependent display outputs. It belongs to the GeForce 800M generation, succeeding the GeForce 700M and preceding the GeForce 900M. The RX 560 is a dual-slot desktop card measuring 170 mm in length, with no power connectors but a 250 W suggested power supply, and display outputs of 1x DVI, 1x HDMI 2.0b, and 1x DisplayPort 1.4a. It belongs to the Polaris (RX 500) generation, succeeding Arctic Islands and preceding Vega. Both products are marked as end-of-life in the database. The 840M was released on 2014-03-11, and the RX 560 was released on 2017-04-17.

The API support shows a split. The 840M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The RX 560 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RX 560 has the higher DirectX feature level, while the 840M has a newer Vulkan version. In the nearest rival comparisons from the database, the 840M sits within 0.7% of the GeForce 940M, 0.3% of the GTX 980M, and 0.1% of the GeForce 930A, while trailing the AMD Radeon R7 M445 by 0.7%. The RX 560 sits within 0.2% of the Intel HD Graphics P530, 0.2% below the Radeon R5 M230, 1.1% below the Quadro M3000M, and 1.3% below the GTX 970M. These tight margins place both products in dense performance clusters, but the head-to-head OpenCL result shows the RX 560 is fundamentally faster than the 840M when both are measured on the same workload.