AMD Radeon R5 Graphics vs NVIDIA GeForce GT 635M Comparison

The AMD Radeon R5 Graphics and NVIDIA GeForce GT 635M are both legacy mobile graphics solutions, but benchmark data shows they are not close in raw compute performance. The Radeon R5 Graphics, an integrated processor from 2014, holds a decisive lead over the older discrete GeForce GT 635M from 2012, despite the latter having dedicated video memory. In the single available head-to-head benchmark, the AMD part wins outright, and its average score places it in a higher performance tier than the NVIDIA chip.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, and the results are unambiguous. The AMD Radeon R5 Graphics scores 5,183 points, while the NVIDIA GeForce GT 635M scores 3,740 points. That is a 38.6% advantage for the AMD integrated solution. This is a substantial margin, placing the Radeon R5 Graphics nearly 40% ahead of the GeForce GT 635M in compute workloads. This is not a marginal victory; the delta is large enough to classify these parts in different performance segments for OpenCL tasks.

The average benchmark score reinforces this gap. The AMD Radeon R5 Graphics has an average score of 3,883 across its benchmark results, which includes both OpenCL and Vulkan tests. The GeForce GT 635M, with only its OpenCL result available, has an average score of 3,740. While the averages are closer than the OpenCL head-to-head, the AMD part still leads by roughly 3.8% when considering its broader benchmark footprint. The Radeon R5 Graphics also has a Vulkan score of 2,582, a capability the GeForce GT 635M lacks entirely, as it has no Vulkan benchmark result.

The percentile rankings show these are both low-end parts, but the AMD chip sits slightly higher. The Radeon R5 Graphics is in the 23rd percentile of all GPUs, while the GeForce GT 635M is in the 22nd percentile. This one-percentile difference is small, but it aligns with the benchmark data showing the AMD part as the faster of the two.

Looking at nearest rivals, the Radeon R5 Graphics sits between several professional and mobile NVIDIA parts. It trails the NVIDIA Quadro 2000 by 0.4% (3,883 vs 3,898), the Quadro K2000D by 0.9% (3,883 vs 3,919), and the Quadro 2000D by 1.2% (3,883 vs 3,930). It leads the GeForce MX110 by 1.3% (3,883 vs 3,834). This places the AMD IGP in a tight cluster of older discrete GPUs, performing essentially at par with those Quadro models.

The GeForce GT 635M, by contrast, is bracketed by other low-end mobile and integrated parts. It is 0.6% ahead of the Quadro 3000M (3,740 vs 3,718) and the GeForce GT 740M (3,740 vs 3,717), and 1.2% ahead of the GeForce 825M (3,740 vs 3,694). It trails the Intel UHD Graphics 710 by 1.4% (3,740 vs 3,792). The data suggests the GT 635M is competitive with these parts but does not match the Radeon R5 Graphics.

FAQ

Q: Which GPU is faster in OpenCL compute performance?

A: The AMD Radeon R5 Graphics is significantly faster, scoring 5,183 in Geekbench OpenCL versus 3,740 for the NVIDIA GeForce GT 635M. This represents a 38.6% advantage for the AMD part.

Q: Does the GeForce GT 635M support Vulkan?

A: No. The FACT PACK lists Vulkan as "null" for the GeForce GT 635M, and it has no Vulkan benchmark score. In contrast, the AMD Radeon R5 Graphics supports Vulkan 1.2.170 and scores 2,582 in the Geekbench Vulkan test.

Q: How do these GPUs compare to their closest rivals?

A: The Radeon R5 Graphics is nearly identical to the NVIDIA Quadro 2000, trailing by just 0.4% in average score. The GeForce GT 635M is closest to the Quadro 3000M and GeForce GT 740M, leading each by 0.6%.

Q: What is the memory configuration of each GPU?

A: The AMD Radeon R5 Graphics uses system shared memory, with size, type, bus width, and bandwidth all listed as "System Shared" or "System Dependent." The NVIDIA GeForce GT 635M has 2 GB of dedicated DDR3 memory on a 128-bit bus with 28.80 GB/s of bandwidth.

Q: Which GPU has a higher power draw?

A: The NVIDIA GeForce GT 635M has a TDP of 35 W, which is more than double the 15 W TDP of the AMD Radeon R5 Graphics.

Q: Which GPU is newer?

A: The AMD Radeon R5 Graphics was released on September 16, 2014. The NVIDIA GeForce GT 635M was released earlier, on March 21, 2012.

The Verdict

The data makes a clear case for the AMD Radeon R5 Graphics as the superior compute performer. Its 38.6% lead in OpenCL and higher average benchmark score (3,883 vs 3,740) are decisive advantages. Anyone choosing between these two for OpenCL workloads should select the AMD part without hesitation. The Radeon R5 Graphics also offers Vulkan support, giving it a modern API advantage that the GeForce GT 635M cannot match.

The GeForce GT 635M does have one structural advantage: dedicated memory. The NVIDIA part features 2 GB of DDR3 on a 128-bit bus with 28.80 GB/s of bandwidth, whereas the AMD IGP relies on system shared memory with bandwidth that is system dependent. For tasks sensitive to memory latency or bandwidth contention with the CPU, the GT 635M's dedicated frame buffer could be preferable, despite its lower compute throughput.

However, the performance gap is too large to ignore. The Radeon R5 Graphics also achieves this higher performance at less than half the power draw (15 W vs 35 W), making it the more efficient choice. The GeForce GT 635M is an older, less capable part that sits in the 22nd percentile of all GPUs. The Radeon R5 Graphics, while only one percentile higher, delivers dramatically better compute results. For users prioritizing compute performance and efficiency, the AMD Radeon R5 Graphics is the clear pick. The GT 635M only makes sense if dedicated memory is a hard requirement and compute performance is secondary.

Specification Differences

The two GPUs differ across nearly every core specification. The AMD Radeon R5 Graphics has 256 shading units, while the NVIDIA GeForce GT 635M has 96. Both have 16 texture mapping units and 4 raster output units. The pixel rate of the AMD part is 3.032 GPixel/s, compared to 1.900 GPixel/s for NVIDIA. Texture rate is also higher on the AMD side at 12.13 GTexel/s versus 7.600 GTexel/s. FP32 performance shows a similar pattern: 388.1 GFLOPS for AMD versus 182.4 GFLOPS for NVIDIA.

Memory is a major differentiator. The Radeon R5 Graphics uses system shared memory with no dedicated VRAM, while the GT 635M has 2 GB of DDR3 on a 128-bit bus. The NVIDIA part's memory clock is listed as 900 MHz with 1800 Mbps effective, delivering 28.80 GB/s of bandwidth. The AMD part has no dedicated memory clock or bandwidth figures, as both are system dependent.

The process node and physical characteristics differ substantially. AMD uses a 28 nm process at GlobalFoundries, while NVIDIA uses a 40 nm process at TSMC. The AMD chip, codenamed Spectre SL, has 2,410 million transistors on a 245 mm² die. The NVIDIA GF108 chip has 585 million transistors on a 116 mm² die. Transistor density is 9.8M per mm² for AMD and 5.0M per mm² for NVIDIA. Power consumption favors AMD significantly, with a 15 W TDP versus 35 W for NVIDIA.

The bus interface also differs. The AMD Radeon R5 Graphics is an IGP with a system-integrated bus, while the GeForce GT 635M uses PCIe 2.0 x16. Display outputs are motherboard dependent for AMD and portable device dependent for NVIDIA. The NVIDIA part has no power connectors listed, while AMD lists none as well.

Architecture Differences

The architectural gap between these two GPUs is generational. The AMD Radeon R5 Graphics is built on GCN 2.0 architecture, part of the Kaveri generation of integrated processors. The NVIDIA GeForce GT 635M uses the older Fermi architecture from the GeForce 600M generation. AMD's GCN 2.0 is a modern graphics core design that emphasizes compute throughput, which explains its substantial lead in OpenCL benchmarks.

The manufacturing process highlights the age difference. AMD uses a 28 nm node at GlobalFoundries, while NVIDIA uses a 40 nm node at TSMC. The smaller process node allows AMD to pack 2,410 million transistors into a 245 mm² die, compared to NVIDIA's 585 million transistors in 116 mm². This gives the AMD chip a transistor density of 9.8M per mm², nearly double the 5.0M per mm² of the NVIDIA chip.

API support also differs. The AMD Radeon R5 Graphics supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA GeForce GT 635M supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan support listed. This makes the AMD part more future-proof for modern applications that leverage Vulkan.

The memory architecture is fundamentally different. The AMD Radeon R5 Graphics is an IGP that shares system memory, with no dedicated VRAM. The NVIDIA GeForce GT 635M is a discrete-class chip with its own 2 GB frame buffer, even though it is listed as having an IGP slot width. The AMD part's memory bandwidth is system dependent, while the NVIDIA part has a fixed 28.80 GB/s.

In terms of product lineage, the AMD Radeon R5 Graphics succeeds the TeraScale 3 IGP and is succeeded by the GCN 3.0 IGP. The NVIDIA GeForce GT 635M succeeds the GeForce 500M and is succeeded by the GeForce 700M. Both are end-of-life products, but the AMD part is from a later generation with a more advanced architecture and substantially better compute performance per watt.