AMD Radeon HD 8750M vs NVIDIA GeForce GTX 760M Comparison

AMD Radeon HD 8750M and NVIDIA GeForce GTX 760M are two mobile graphics solutions from the same 28 nm manufacturing generation, but they target very different performance tiers. The recorded data shows that the AMD part holds a narrow lead in the single shared benchmark test, while the NVIDIA part offers a substantially larger feature set in terms of memory capacity, shader count, and interface width. The analysis below breaks down the benchmark results, architectural differences, and practical use cases based solely on the information in the database.

Head-to-Head Benchmarks

The direct comparison in the database contains a single OpenCL benchmark result. In the Geekbench OpenCL test, the AMD Radeon HD 8750M scores 5970 points, while the NVIDIA GeForce GTX 760M scores 5604 points. This gives the AMD part a victory with a delta of 6.5%. The AMD Radeon HD 8750M is therefore 6.5% ahead of the NVIDIA GeForce GTX 760M in this specific compute workload.

This result is notable because the NVIDIA GPU has significantly more raw hardware resources. The GeForce GTX 760M contains 768 shading units, 64 texture mapping units, and 16 render output units, while the Radeon HD 8750M has 384 shading units, 24 TMUs, and 8 ROPs. Despite having double the shading units and four times the TMUs, the NVIDIA part still trails in this OpenCL benchmark. The database also records a Geekbench Vulkan score for the NVIDIA GeForce GTX 760M of 4868 points, but no comparable Vulkan result exists for the AMD Radeon HD 8750M, so a direct head-to-head comparison on that test is not possible from the recorded data.

The overall benchmark averages reinforce this picture. The AMD Radeon HD 8750M has an average benchmark score of 5970, while the NVIDIA GeForce GTX 760M has an average score of 5236. The difference in averages is driven by the fact that the NVIDIA part includes its lower Vulkan score in its average, whereas the AMD part only has the single OpenCL result. In the head-to-head table, the AMD card wins 1 benchmark and the NVIDIA card wins 0.

Looking at the percentile rankings, the AMD Radeon HD 8750M sits at the 34th percentile of all GPUs in the database, while the NVIDIA GeForce GTX 760M sits at the 31st percentile. This means the AMD part outperforms a slightly larger share of the overall GPU population in the recorded tests.

Where Each One Wins

The AMD Radeon HD 8750M wins the only direct benchmark comparison available. Its OpenCL score of 5970 places it ahead of the NVIDIA GeForce GTX 760M by 6.5%. For users who prioritize compute workloads that rely on OpenCL performance, the data clearly favors the AMD part. The AMD GPU also has a higher boost clock of 825 MHz compared to the NVIDIA GPU's boost clock of 719 MHz, which may contribute to its benchmark advantage despite the smaller hardware configuration.

The NVIDIA GeForce GTX 760M wins in areas that are not directly measured by the head-to-head benchmark but are visible in the specification data. The NVIDIA part has 2 GB of GDDR5 memory compared to the AMD part's 1 GB of DDR3 memory. This translates to more than double the memory bandwidth: 64.13 GB/s for the NVIDIA versus 28.80 GB/s for the AMD. The NVIDIA GPU also has a wider PCIe interface at PCIe 3.0 x16, while the AMD GPU uses PCIe 3.0 x8. These factors suggest the NVIDIA part is better positioned for memory-intensive workloads, even though the recorded OpenCL test does not show an advantage.

The NVIDIA GeForce GTX 760M also has a Vulkan benchmark score of 4868, which is not matched by any recorded Vulkan result for the AMD Radeon HD 8750M. In the Vulkan API, the database only has data for the NVIDIA part, so any application using Vulkan would lack a comparable AMD result in this dataset.

The Verdict

The benchmark data is clear on one point: for the single shared test, the AMD Radeon HD 8750M is the faster GPU. With a 6.5% lead in Geekbench OpenCL, the AMD part delivers better raw compute performance in that specific workload. Its average benchmark score of 5970 also exceeds the NVIDIA part's average of 5236, a difference of approximately 14% in favor of the AMD card.

However, the verdict is not one-sided. The NVIDIA GeForce GTX 760M brings substantially more hardware to the table: 768 shading units versus 384, 64 TMUs versus 24, and 16 ROPs versus 8. It also has twice the memory capacity (2 GB versus 1 GB) and a much faster memory type (GDDR5 versus DDR3), resulting in 64.13 GB/s of bandwidth versus 28.80 GB/s. These specifications would typically indicate a stronger GPU for gaming or rendering workloads, but the recorded OpenCL benchmark does not reflect that expectation.

The database shows that the AMD Radeon HD 8750M wins the only head-to-head test. Users who rely on OpenCL compute performance should choose the AMD part based on this data. Users who need Vulkan support, larger memory capacity, or a wider bus interface would find those features only in the NVIDIA GeForce GTX 760M, but they would have to accept the lower OpenCL score and the lower average benchmark result.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD Radeon HD 8750M scores 5970 in Geekbench OpenCL, which is 6.5% higher than the NVIDIA GeForce GTX 760M's score of 5604.

Q: Does the NVIDIA GeForce GTX 760M have any benchmark result that the AMD card lacks?

A: Yes, the database records a Geekbench Vulkan score of 4868 for the NVIDIA GeForce GTX 760M. No Vulkan score is listed for the AMD Radeon HD 8750M.

Q: What is the memory configuration difference between the two GPUs?

A: The AMD Radeon HD 8750M has 1024 MB of DDR3 memory on a 128-bit bus with 28.80 GB/s bandwidth. The NVIDIA GeForce GTX 760M has 2 GB of GDDR5 memory on a 128-bit bus with 64.13 GB/s bandwidth.

Q: How do the shading unit counts compare?

A: The NVIDIA GeForce GTX 760M has 768 shading units, while the AMD Radeon HD 8750M has 384 shading units. The NVIDIA part also has 64 TMUs and 16 ROPs, compared to 24 TMUs and 8 ROPs on the AMD part.

Q: What are the clock speeds of each GPU?

A: The AMD Radeon HD 8750M has a base clock of 775 MHz and a boost clock of 825 MHz. The NVIDIA GeForce GTX 760M has a base clock of 628 MHz and a boost clock of 719 MHz.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The AMD Radeon HD 8750M is at the 34th percentile, while the NVIDIA GeForce GTX 760M is at the 31st percentile in the database.

Architecture Differences

The two GPUs come from different architectural lineages. The AMD Radeon HD 8750M is built on the GCN 1.0 architecture using the Mars chip, while the NVIDIA GeForce GTX 760M uses the Kepler architecture with the GK106S chip. Both are fabricated on a 28 nm process at TSMC, but the dies differ significantly in size and transistor count.

The AMD Mars chip contains 950 million transistors on a 77 mm² die, resulting in a transistor density of 12.3 million transistors per square millimeter. The NVIDIA GK106S chip is much larger, with 2,540 million transistors on a 221 mm² die, giving a transistor density of 11.5 million per square millimeter. The NVIDIA chip has more than 2.5 times the transistor count of the AMD chip.

The compute configurations reflect these architectural differences. The AMD Radeon HD 8750M has 384 shading units, 24 TMUs, and 8 ROPs. The NVIDIA GeForce GTX 760M has 768 shading units, 64 TMUs, and 16 ROPs. These numbers indicate that the NVIDIA part has double the shader capacity and substantially more texture and pixel processing hardware.

Neither GPU includes dedicated ray tracing or tensor cores, as both predate those technologies in mobile form factors. The API support also differs slightly: the AMD part supports DirectX 12 (11_1) while the NVIDIA part supports DirectX 12 (11_0). Both support OpenGL 4.6, but the Vulkan versions differ, with the AMD card at Vulkan 1.2.170 and the NVIDIA card at Vulkan 1.2.175.

Specification Differences

The most visible specification difference is memory. The AMD Radeon HD 8750M ships with 1024 MB of DDR3 memory running at 900 MHz (1800 Mbps effective), yielding 28.80 GB/s of bandwidth. The NVIDIA GeForce GTX 760M ships with 2 GB of GDDR5 memory running at 1002 MHz (4 Gbps effective), yielding 64.13 GB/s of bandwidth. Both use a 128-bit memory bus, but the faster memory type and higher clock give the NVIDIA part more than double the bandwidth.

The bus interface also differs. The AMD Radeon HD 8750M uses PCIe 3.0 x8, while the NVIDIA GeForce GTX 760M uses PCIe 3.0 x16, offering twice the interface width for data transfers.

Compute rates are significantly higher on the NVIDIA part. The pixel rate is 11.50 GPixel/s versus 6.600 GPixel/s for the AMD card. The texture rate is 46.02 GTexel/s versus 19.80 GTexel/s. The FP32 performance is 1,104.4 GFLOPS for the NVIDIA part versus 633.6 GFLOPS for the AMD part. None of these metrics are directly measured in the head-to-head benchmark, but they indicate the theoretical peak capabilities.

The power profile also differs. The NVIDIA GeForce GTX 760M has a TDP of 55 W and uses an MXM Module form factor with no power connectors. The AMD Radeon HD 8750M has no recorded TDP, slot width, or power connector data in the database. The NVIDIA part's display outputs are listed as "Portable Device Dependent," while the AMD part has no display output information recorded.

The release dates differ by about three months. The AMD Radeon HD 8750M was released on 2013-02-25, while the NVIDIA GeForce GTX 760M was released on 2013-05-29. Both are end-of-life products. The AMD part's predecessor is London and its successor is Gem System, while the NVIDIA part's predecessor is GeForce 600M and its successor is GeForce 800M.