AMD Radeon HD 8730M vs NVIDIA GeForce GTX 765M Comparison

The GeForce GTX 765M and Radeon HD 8730M are both end-of-life mobile graphics solutions from 2013, built on the same 28 nm TSMC process. Despite their shared vintage, they represent fundamentally different design philosophies from NVIDIA and AMD. The data shows a clear performance hierarchy, with the GTX 765M holding a decisive edge in compute workloads, while the HD 8730M offers a distinct feature set that may appeal to specific use cases.

Head-to-Head Benchmarks

The only direct benchmark comparison available for these two GPUs is the Geekbench OpenCL test, which measures raw compute performance for general-purpose GPU workloads. In this test, the NVIDIA GeForce GTX 765M scores 7176, while the AMD Radeon HD 8730M scores 5955. This translates to a 20.5% advantage for the NVIDIA part, a substantial margin that reflects the underlying hardware differences.

The GTX 765M’s OpenCL score is not just higher than its rival; it also places it in a competitive position within its own performance tier. The data shows the GTX 765M has an average benchmark score of 5501, with its nearest rival being the NVIDIA GeForce MX130 at an average score of 5508, representing a negligible -0.1% delta. This means the GTX 765M’s OpenCL result is a significant outlier on the high side for its class, suggesting it excels particularly well in compute tasks that scale with its shader and texture resources. In contrast, the HD 8730M’s average benchmark score is 5955, which is identical to its OpenCL score, indicating it has no other benchmark results to pull the average up or down.

When looking at the broader competitive landscape, the HD 8730M’s score of 5955 puts it in a tight cluster with several rivals. For instance, the NVIDIA Quadro K620M scores 5957 with a 0% delta, and the AMD Radeon HD 8750M scores 5970, a -0.3% delta. This shows that the HD 8730M is right at the median of its performance peers. The GTX 765M, however, uses its OpenCL score to leapfrog past its typical rivals; its average score of 5501 is only 0.3% behind the AMD Radeon R7 M440 (5483) and 0.6% ahead of the NVIDIA Quadro M4000 (5467). The 20.5% delta in the head-to-head test is therefore not just a minor victory; it represents a full performance class separation between the two in compute-heavy applications.

Where Each One Wins

The GTX 765M wins the only benchmark where both GPUs were tested, so its dominance is clear in the compute domain. The 20.5% lead in OpenCL suggests it is the superior choice for tasks that leverage general-purpose GPU computing, such as video encoding, physics simulations, or data processing. This advantage is likely driven by its substantially higher raw throughput capabilities. This is further supported by the specification data, which shows the GTX 765M has a texture rate of 55.23 GTexel/s compared to the HD 8730M’s 16.80 GTexel/s, and a pixel rate of 13.81 GPixel/s versus 5.600 GPixel/s. These numbers indicate that the NVIDIA part can feed and process data at a much higher rate.

However, the HD 8730M is not without its merits. While it loses in raw compute, its architecture and feature set offer different advantages. The HD 8730M supports DirectX 12 (11_1), while the GTX 765M supports DirectX 12 (11_0). This means the AMD part has a slight edge in API feature level compatibility, potentially offering better support for certain modern game features or rendering techniques. For users with a specific application that relies on a feature present in the 11_1 feature level but not 11_0, the HD 8730M would be the only choice between the two.

Furthermore, the HD 8730M’s lower power consumption and simpler power delivery requirements could make it a more practical option for thin-and-light laptops where thermal headroom is limited. The GTX 765M has a TDP of 75 W and requires an MXM module, which is typically reserved for larger, more powerful gaming notebooks. The HD 8730M, with its PCIe 3.0 x8 interface and no specified TDP, is more likely to be found in a wider range of portable systems. In a pure compute benchmark, the GTX 765M wins decisively, but in a system-level integration context, the HD 8730M’s lower resource demands are its key advantage.

FAQ

Q: Which GPU is faster in OpenCL compute workloads?

A: The NVIDIA GeForce GTX 765M is significantly faster, scoring 7176 in Geekbench OpenCL compared to the AMD Radeon HD 8730M’s 5955. This gives the NVIDIA part a 20.5% performance lead.

Q: How does the GTX 765M compare to its own nearest rivals?

A: The GTX 765M has an average benchmark score of 5501. It is essentially tied with the NVIDIA GeForce MX130 (5508, -0.1%) and the AMD Radeon R7 M440 (5483, 0.3%). Its OpenCL score is far above this average, indicating a strength in compute.

Q: What is the performance context for the Radeon HD 8730M?

A: The HD 8730M’s average benchmark score of 5955 places it in a tight group with the NVIDIA Quadro K620M (5957, 0%) and the AMD Radeon HD 8750M (5970, -0.3%). It performs at the level of these mainstream mobile GPUs.

Q: Do both GPUs support the same level of DirectX?

A: No. The AMD Radeon HD 8730M supports DirectX 12 (11_1), which is a higher feature level than the NVIDIA GeForce GTX 765M’s DirectX 12 (11_0). This could matter for specific rendering features.

Q: Which GPU has higher memory bandwidth?

A: The NVIDIA GeForce GTX 765M has a memory bandwidth of 64.13 GB/s, which is more than double the 28.80 GB/s of the AMD Radeon HD 8730M. This is due to the GTX 765M’s GDDR5 memory type compared to the HD 8730M’s DDR3.

Q: What are the form factor implications for each GPU?

A: The GTX 765M is an MXM Module with a 75 W TDP, indicating it is designed for larger, high-performance laptops. The HD 8730M uses a PCIe 3.0 x8 interface and has no specified TDP or slot width, suggesting it can be integrated into a wider range of portable devices.

Specification Differences

The specification sheets for these two GPUs reveal stark contrasts in their design and intended usage. The NVIDIA GeForce GTX 765M is built on the GK106 chip, while the AMD Radeon HD 8730M uses the Mars chip. The GTX 765M has a base clock of 797 MHz and a boost clock of 863 MHz. In comparison, the HD 8730M operates at a lower base clock of 650 MHz and a boost clock of 700 MHz. The memory configuration also differs significantly: the GTX 765M uses 2 GB of GDDR5 memory with a 128-bit bus, achieving a bandwidth of 64.13 GB/s, whereas the HD 8730M uses 2 GB of DDR3 memory on the same 128-bit bus, resulting in a much lower bandwidth of 28.80 GB/s.

The compute resources are also heavily skewed towards the NVIDIA part. The GTX 765M has 768 shading units, 64 texture mapping units (TMUs), and 16 ROPs. The HD 8730M has half the shading units at 384, only 24 TMUs, and 8 ROPs. This translates to a peak FP32 performance of 1,325.6 GFLOPS for the GTX 765M versus 537.6 GFLOPS for the HD 8730M. The power requirements differ as well, with the GTX 765M having a TDP of 75 W and no power connectors, while the HD 8730M has no TDP listed. The bus interface is also different: the GTX 765M uses MXM-B (3.0), while the HD 8730M uses PCIe 3.0 x8.

Architecture Differences

The architectural divide between these two GPUs is fundamental. The NVIDIA GeForce GTX 765M is based on the Kepler architecture, featuring a transistor count of 2,540 million on a 221 mm² die. This results in a transistor density of 11.5M / mm². In contrast, the AMD Radeon HD 8730M is based on the GCN 1.0 architecture, with 950 million transistors on a much smaller 77 mm² die, achieving a higher transistor density of 12.3M / mm². The GTX 765M’s larger die and higher transistor count are direct contributors to its superior performance, providing more room for compute units, memory controllers, and other logic.

The generation names also differ, with the GTX 765M belonging to the GeForce 700M family and the HD 8730M to AMD’s Solar System (HD 8700M) family. While both are listed as end-of-life, their predecessors and successors are different: the GTX 765M follows the GeForce 600M and precedes the GeForce 800M, while the HD 8730M follows the "London" chip and precedes the "Gem System" platform. In terms of software support, both GPUs support OpenGL 4.6 and Vulkan, but with different versions. The GTX 765M supports Vulkan 1.2.175, while the HD 8730M supports Vulkan 1.2.170. The DirectX support differs as previously noted, with the GTX 765M supporting 12 (11_0) and the HD 8730M supporting 12 (11_1). These architectural and feature-level distinctions define the character of each GPU, with the NVIDIA part focused on raw throughput and the AMD part offering a more power-efficient and feature-complete API package for its era.