AMD Radeon HD 6850 X2 vs AMD Radeon R5 M335 Comparison

Head-to-Head Benchmarks

The recorded benchmark data shows a single head-to-head comparison between these two GPUs, and it is decisive. In the Geekbench OpenCL test, the AMD Radeon R5 M335 scores 4,745 points, while the AMD Radeon HD 6850 X2 manages 3,977 points. That is a 19.3% advantage for the R5 M335. This is not a marginal win; it is a substantial margin that places the newer mobile chip clearly ahead of the older dual-GPU desktop card in raw compute workloads.

The R5 M335’s average benchmark score across all tests is 4,752, which sits at the 28th percentile of all GPUs in the database. The HD 6850 X2, by comparison, has an average score of 3,977, placing it at the 24th percentile. While both are in the lower half of the performance spectrum, the R5 M335’s percentile ranking is measurably higher. In the OpenCL test specifically, the delta between them is 19.3%, which is a much larger gap than what separates the R5 M335 from its own nearest rivals. For instance, the R5 M335 is only 0.5% ahead of the AMD Radeon R8 M445DX (4,727 points) and 0.7% behind the AMD Radeon R5 M255 (4,788 points). The HD 6850 X2, meanwhile, is nearly tied with the NVIDIA Quadro K2000 (3,964 points, 0.3% difference) and the NVIDIA GeForce 830M (3,957 points, 0.5% difference). This context shows that the R5 M335 is not just beating the HD 6850 X2; it is doing so by a margin that is far larger than the typical differences seen among closely ranked GPUs.

The single benchmark win for the R5 M335 is the only recorded victory, with zero wins for the HD 6850 X2. However, the absence of additional test data means the comparison rests entirely on this one OpenCL result. The data available does not include Vulkan scores for the HD 6850 X2, even though the R5 M335 has a recorded Vulkan score of 4,758. This asymmetry limits the scope of the comparison, but the one test that does exist is unambiguous: the R5 M335 is faster in compute performance.

Architecture Differences

The architectural gap between these two GPUs is vast, and it explains the benchmark results. The R5 M335 uses the GCN 1.0 architecture, built on a 28 nm process node at TSMC. The HD 6850 X2 uses the older TeraScale 2 architecture, built on a 40 nm process node, also at TSMC. The process shrink alone is significant: 28 nm versus 40 nm means denser transistors and better power characteristics for the newer chip. The R5 M335 packs 690 million transistors into a die size of 56 mm², resulting in a transistor density of 12.3 million per mm². The HD 6850 X2, by contrast, has 1,700 million transistors spread across a 255 mm² die, yielding a density of just 6.7 million per mm². The R5 M335 is nearly twice as dense, a direct consequence of the newer manufacturing process.

The chip designs themselves differ fundamentally. The R5 M335 uses the "Exo" chip, while the HD 6850 X2 uses "Barts." The R5 M335 features 320 shading units, 20 texture mapping units, and 8 raster output units. The HD 6850 X2 has 960 shading units, 48 TMUs, and 32 ROPs. Despite having fewer shading units, TMUs, and ROPs, the R5 M335 still wins in compute benchmarks. This reflects the efficiency gains of GCN 1.0 over TeraScale 2. The R5 M335 also supports newer APIs: DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The HD 6850 X2 is limited to DirectX 11.2 (11_0) and OpenGL 4.4, with no Vulkan support at all. This means the R5 M335 is compatible with modern software environments, while the HD 6850 X2 is stuck in an older generation.

Memory technology also differs sharply. The R5 M335 uses 2 GB of DDR3 memory on a 64-bit bus, delivering 14.40 GB/s of bandwidth. The HD 6850 X2 uses 2 GB of GDDR5 memory on a 256-bit bus, delivering 134.4 GB/s of bandwidth. That is a massive bandwidth advantage for the HD 6850 X2, roughly 9 times higher, yet it does not translate into a compute win. The R5 M335 compensates with a higher memory clock in effective terms: 1800 Mbps effective versus 4.2 Gbps effective for the HD 6850 X2, though the bus width difference dominates. The R5 M335’s pixel rate is 8.240 GPixel/s and its texture rate is 20.60 GTexel/s. The HD 6850 X2 posts 25.60 GPixel/s and 38.40 GTexel/s, respectively. The HD 6850 X2 is clearly superior in rasterization throughput, but the OpenCL benchmark measures general compute, where the R5 M335’s architecture is more efficient.

Power and physical characteristics diverge as well. The R5 M335 has no specified TDP, uses no power connectors, and is described as "Portable Device Dependent" for display outputs. It is a mobile-oriented chip. The HD 6850 X2, on the other hand, has a TDP of 254 W, requires dual-slot cooling, uses 2x 8-pin power connectors, and demands a 600 W suggested power supply. It is a desktop card with 2x DVI, 1x HDMI 1.3a, and 1x DisplayPort 1.1 outputs. The HD 6850 X2 also uses a PCIe 2.0 x16 interface, while the R5 M335 uses PCIe 3.0 x8. The R5 M335’s release date is 2015-10-20, while the HD 6850 X2 came out earlier on 2011-09-18. Both are end-of-life, but the R5 M335 is four years newer.

FAQ

Q: Which GPU wins in the Geekbench OpenCL test?

A: The AMD Radeon R5 M335 wins with a score of 4,745, beating the AMD Radeon HD 6850 X2’s 3,977 by 19.3%.

Q: Does the HD 6850 X2 have any benchmark wins over the R5 M335?

A: No. The database records zero wins for the HD 6850 X2 and one win for the R5 M335 in the head-to-head comparison.

Q: What is the architectural difference between the two?

A: The R5 M335 uses GCN 1.0 on a 28 nm process, while the HD 6850 X2 uses TeraScale 2 on a 40 nm process. The R5 M335 supports DirectX 12, OpenGL 4.6, and Vulkan 1.2.170, whereas the HD 6850 X2 only supports DirectX 11.2, OpenGL 4.4, and no Vulkan.

Q: Which GPU has more shading units?

A: The HD 6850 X2 has 960 shading units, compared to 320 for the R5 M335. Despite this, the R5 M335 performs better in OpenCL compute.

Q: How does memory bandwidth compare?

A: The HD 6850 X2 offers 134.4 GB/s of bandwidth over a 256-bit bus, while the R5 M335 offers 14.40 GB/s over a 64-bit bus. The HD 6850 X2 has far more bandwidth.

Q: What are the power requirements for each?

A: The HD 6850 X2 has a TDP of 254 W, requires 2x 8-pin power connectors, and a 600 W suggested power supply. The R5 M335 has no specified TDP and uses no power connectors.

Specification Differences

The following fields differ between the two GPUs:

• Architecture: GCN 1.0 (R5 M335) vs TeraScale 2 (HD 6850 X2)
• Chip: Exo (R5 M335) vs Barts (HD 6850 X2)
• Process Node: 28 nm (R5 M335) vs 40 nm (HD 6850 X2)
• Transistors: 690 million (R5 M335) vs 1,700 million (HD 6850 X2)
• Die Size: 56 mm² (R5 M335) vs 255 mm² (HD 6850 X2)
• Transistor Density: 12.3M / mm² (R5 M335) vs 6.7M / mm² (HD 6850 X2)
• Memory Type: DDR3 (R5 M335) vs GDDR5 (HD 6850 X2)
• Memory Bus Width: 64 bit (R5 M335) vs 256 bit (HD 6850 X2)
• Memory Bandwidth: 14.40 GB/s (R5 M335) vs 134.4 GB/s (HD 6850 X2)
• Memory Clock (effective): 1800 Mbps (R5 M335) vs 4.2 Gbps (HD 6850 X2)
• Shading Units: 320 (R5 M335) vs 960 (HD 6850 X2)
• TMUs: 20 (R5 M335) vs 48 (HD 6850 X2)
• ROPs: 8 (R5 M335) vs 32 (HD 6850 X2)
• Pixel Rate: 8.240 GPixel/s (R5 M335) vs 25.60 GPixel/s (HD 6850 X2)
• Texture Rate: 20.60 GTexel/s (R5 M335) vs 38.40 GTexel/s (HD 6850 X2)
• FP32: 659.2 GFLOPS (R5 M335) vs 1.536 TFLOPS (HD 6850 X2)
• TDP: Not specified (R5 M335) vs 254 W (HD 6850 X2)
• Slot Width: Not specified (R5 M335) vs Dual-slot (HD 6850 X2)
• Power Connectors: None (R5 M335) vs 2x 8-pin (HD 6850 X2)
• Suggested PSU: Not specified (R5 M335) vs 600 W (HD 6850 X2)
• Bus Interface: PCIe 3.0 x8 (R5 M335) vs PCIe 2.0 x16 (HD 6850 X2)
• Display Outputs: Portable Device Dependent (R5 M335) vs 2x DVI, 1x HDMI 1.3a, 1x DisplayPort 1.1 (HD 6850 X2)
• DirectX Support: 12 (11_1) (R5 M335) vs 11.2 (11_0) (HD 6850 X2)
• OpenGL Support: 4.6 (R5 M335) vs 4.4 (HD 6850 X2)
• Vulkan Support: 1.2.170 (R5 M335) vs Not supported (HD 6850 X2)
• Release Date: 2015-10-20 (R5 M335) vs 2011-09-18 (HD 6850 X2)
• Predecessor: Solar System (R5 M335) vs Evergreen (HD 6850 X2)
• Successor: Polaris Mobile (R5 M335) vs Southern Islands (HD 6850 X2)
• Average Benchmark Score: 4,752 (R5 M335) vs 3,977 (HD 6850 X2)
• Percentile vs All GPUs: 28 (R5 M335) vs 24 (HD 6850 X2)

The Verdict

The data points to a clear winner for compute workloads: the AMD Radeon R5 M335. Its 19.3% lead in OpenCL performance is substantial, and it carries a higher average benchmark score (4,752 vs 3,977) and a higher percentile ranking (28th vs 24th). The R5 M335 also brings modern API support, including Vulkan and DirectX 12, which the HD 6850 X2 lacks entirely. For anyone running current software that relies on these interfaces, the R5 M335 is the only viable option.

The HD 6850 X2, however, is not without merits in its own right. It has dramatically higher memory bandwidth (134.4 GB/s vs 14.40 GB/s), more shading units (960 vs 320), and superior pixel and texture rates. In rasterization-heavy tasks, such as classic gaming at lower resolutions, the HD 6850 X2 could theoretically excel. But the recorded benchmark data does not include such tests, and the only measured metric favors the R5 M335.

For a user prioritizing compute performance, modern API compatibility, and low power requirements, the R5 M335 is the logical pick. For a user with a desktop system that can handle a 254 W TDP and a 600 W power supply, the HD 6850 X2 offers raw bandwidth and throughput that the R5 M335 cannot match, but it is obsolete in terms of software support. The verdict from the database is unambiguous: the R5 M335 wins the head-to-head, and the HD 6850 X2 should be considered only for legacy use cases where its specific strengths apply.