AMD Radeon HD 8750M vs NVIDIA GeForce 940M Comparison

Head-to-Head Benchmarks

The recorded data shows a single direct comparison between these two mobile graphics processors: the GeekBench OpenCL test. In that benchmark, the NVIDIA GeForce 940M scored 6018 points, while the AMD Radeon HD 8750M scored 5970 points. This gives the NVIDIA part a narrow 0.8% advantage in the head-to-head matchup, a margin that is essentially negligible in real-world terms. The GeForce 940M claims the only win in this direct comparison, but the performance gap is so small that it falls within typical run-to-run variance for OpenCL workloads.

The average benchmark score tells a slightly different story. The HD 8750M holds an average score of 5970 across its recorded benchmark runs, while the GeForce 940M averages 5284 points. This difference is notable: the AMD part maintains a 13% higher average score when all recorded benchmarks are considered. However, the GeForce 940M's average is pulled down by its additional Vulkan benchmark result of 4549 points, which is significantly lower than its OpenCL score. When comparing only the shared OpenCL test, the two GPUs are effectively tied.

Looking at the percentile rankings, the HD 8750M sits at the 34th percentile among all GPUs in the database, while the GeForce 940M sits at the 31st percentile. This indicates that the AMD part outperforms a slightly larger share of the overall GPU landscape, even though its direct head-to-head loss is marginal. The nearest rivals for the HD 8750M include the NVIDIA Quadro K4000 with an average score of 5982 (a 0.2% lead over the AMD part), the Quadro K620M at 5957 (0.2% behind), the Radeon HD 8730M at 5955 (0.3% behind), and the Quadro K4000M at 5986 (0.3% ahead). These four competitors all fall within a narrow 31-point band, confirming that the HD 8750M performs right at the center of a tightly clustered group.

For the GeForce 940M, its nearest rivals are quite different in character. The GeForce GTX 980M averages 5308 points, a 0.4% advantage over the 940M. The GeForce 930A scores 5317 (0.6% ahead), the GeForce 840M scores 5322 (0.7% ahead), and the GeForce GTX 760M scores 5236, which is 0.9% behind the 940M. Notably, the 940M's average of 5284 places it below all but one of these rivals, and the GTX 980M's presence in this list highlights how the 940M's average score is dragged down by its Vulkan result. The OpenCL-only score of 6018 would place the 940M far above all of these rivals, but the database average reflects the full benchmark suite.

The key takeaway from the head-to-head data is that these two GPUs are nearly identical in OpenCL performance. The 0.8% delta is far smaller than the differences seen between other mobile GPU pairings in the database. What separates them is the breadth of the benchmark results: the GeForce 940M has a second recorded result in Vulkan that substantially lowers its average, while the HD 8750M has no Vulkan result recorded at all.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce 940M scores 6018 in GeekBench OpenCL, while the AMD Radeon HD 8750M scores 5970. The NVIDIA part leads by 0.8% in this specific test.

Q: Why does the GeForce 940M have a lower average benchmark score despite winning the head-to-head?

A: The GeForce 940M has two recorded benchmarks: an OpenCL score of 6018 and a Vulkan score of 4549. Its average of 5284 reflects both results. The HD 8750M has only the OpenCL score of 5970, so its average equals that single result.

Q: How do these GPUs compare to their nearest rivals in the database?

A: The HD 8750M's nearest rivals are all within 0.3% of its score, including the Quadro K4000 (5982), Quadro K4000M (5986), Quadro K620M (5957), and Radeon HD 8730M (5955). The GeForce 940M's nearest rivals range from 0.9% behind (GTX 760M at 5236) to 0.7% ahead (GeForce 840M at 5322).

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

A: The AMD Radeon HD 8750M ranks at the 34th percentile, while the NVIDIA GeForce 940M ranks at the 31st percentile. The AMD part outperforms a slightly larger share of the entire GPU database.

Q: Are these GPUs still in production?

A: Both are end-of-life products. The HD 8750M was released on 2013-02-25, and the GeForce 940M was released on 2015-03-12.

Q: Do both GPUs support the same DirectX version?

A: No. The HD 8750M supports DirectX 12 (11_1), while the GeForce 940M supports DirectX 12 (11_0). Both support OpenGL 4.6, but their Vulkan support differs: the HD 8750M supports Vulkan 1.2.170, while the GeForce 940M supports Vulkan 1.4.

Where Each One Wins

AMD Radeon HD 8750M wins on:

• Average benchmark score: 5970 versus 5284 for the GeForce 940M, a 13% advantage when all recorded results are averaged.
• Overall percentile ranking: 34th percentile versus 31st, meaning it outperforms a larger fraction of all GPUs in the database.
• Memory bandwidth: 28.80 GB/s versus 14.40 GB/s for the NVIDIA part, a 2x advantage despite the AMD part's narrower application of that bandwidth.
• Memory bus width: 128-bit versus 64-bit, which directly contributes to the bandwidth advantage.

NVIDIA GeForce 940M wins on:

• OpenCL head-to-head: 6018 versus 5970, a 0.8% margin.
• Shader throughput: 1,124.4 GFLOPS FP32 versus 633.6 GFLOPS for the AMD part, a 77% advantage in raw compute capacity.
• Pixel throughput: 17.57 GPixel/s versus 6.600 GPixel/s, a 2.7x advantage in fill rate.
• Texture throughput: 35.14 GTexel/s versus 19.80 GTexel/s, a 77% advantage.
• Memory capacity: 2 GB versus 1 GB, doubling the available framebuffer.

The win distribution favors the NVIDIA part in raw throughput metrics, while the AMD part holds the advantage in memory bandwidth and the aggregate benchmark average. For workloads that depend on fill rate and compute shaders, the GeForce 940M has clear headroom. For workloads that are memory-bandwidth bound, the HD 8750M's wider bus provides an edge.

Specification Differences

The two GPUs differ significantly in their core configurations. The HD 8750M features 384 shading units, 24 texture mapping units, and 8 raster output units. The GeForce 940M counters with 512 shading units, 32 texture mapping units, and 16 raster output units. In every count, the NVIDIA part has more processing elements, with 33% more shaders, 33% more TMUs, and double the ROPs.

Clock speeds also favor the NVIDIA part. The HD 8750M runs at a base clock of 775 MHz with a boost of 825 MHz. The GeForce 940M runs at a base of 1020 MHz and boosts to 1098 MHz, representing a 32% higher base clock and a 33% higher boost clock. Memory clocks are identical at 900 MHz with 1800 Mbps effective, but the memory configurations diverge sharply. The HD 8750M uses 1024 MB of DDR3 on a 128-bit bus, yielding 28.80 GB/s of bandwidth. The GeForce 940M uses 2048 MB of DDR3 on a 64-bit bus, yielding only 14.40 GB/s. The AMD part has double the bandwidth but half the capacity.

The bus interface also differs. The HD 8750M connects via PCIe 3.0 x8, while the GeForce 940M uses an MXM-B (3.0) interface. The GeForce 940M has a rated TDP of 75 W and uses an MXM Module slot with no power connectors. The HD 8750M has no TDP, slot width, or power connector data recorded. The GeForce 940M lists "Portable Device Dependent" for its display outputs, while the HD 8750M has no display output data.

Architecture Differences

The AMD Radeon HD 8750M is built on the GCN 1.0 architecture, specifically using the Mars chip. It is fabricated on a 28 nm process at TSMC, with 950 million transistors on a 77 mm² die, giving a transistor density of 12.3M per mm². It belongs to the Solar System generation, specifically the HD 8700M series, and its predecessor is London with the successor being Gem System.

The NVIDIA GeForce 940M uses the Maxwell architecture with the GM107 chip. It is also fabricated on a 28 nm process at TSMC, but with 1,870 million transistors on a 148 mm² die, giving a transistor density of 12.6M per mm². It belongs to the GeForce 900M generation, with the GeForce 800M as its predecessor and GeForce 10 Mobile as its successor.

The transistor density is nearly identical between the two, at 12.3M versus 12.6M per mm², but the GeForce 940M packs roughly double the transistors (1,870 million versus 950 million) into nearly double the die area (148 mm² versus 77 mm²). This reflects the Maxwell architecture's emphasis on more, smaller compute units compared to GCN 1.0's design.

API support differs in DirectX and Vulkan versions. The HD 8750M supports DirectX 12 (11_1) and Vulkan 1.2.170, while the GeForce 940M supports DirectX 12 (11_0) and Vulkan 1.4. Both support OpenGL 4.6. The Vulkan version difference is notable: the GeForce 940M supports a more recent Vulkan specification, which may matter for newer applications that require newer API features.

Neither GPU has ray tracing cores or tensor cores recorded in the database. Neither lists FP16 performance, indicating both are primarily FP32-oriented designs from their respective generations.

The Verdict

The benchmark data presents a nuanced picture for these two end-of-life mobile GPUs. In the direct OpenCL comparison, the NVIDIA GeForce 940M edges out the AMD Radeon HD 8750M by 0.8%, a margin that is statistically insignificant. However, the HD 8750M holds a 13% higher average benchmark score when all recorded results are considered, and it ranks at the 34th percentile versus the 940M's 31st percentile.

For users prioritizing raw compute throughput, the GeForce 940M is clearly superior: it delivers 1,124.4 GFLOPS versus 633.6 GFLOPS, with double the pixel rate and 77% higher texture rate. This makes it the better choice for GPU-accelerated compute tasks, image processing, and games that rely heavily on shader performance. Its 2 GB of memory also provides more headroom for higher-resolution textures and larger datasets.

For users prioritizing memory bandwidth, the HD 8750M is the stronger option. Its 128-bit bus delivers 28.80 GB/s of bandwidth, exactly double the 940M's 14.40 GB/s. This matters for bandwidth-sensitive workloads such as certain physics simulations, video processing, and memory-bound rendering paths. The HD 8750M also holds a better aggregate benchmark record, suggesting more consistent performance across a broader set of tests.

The GeForce 940M's Vulkan 1.4 support is a forward-looking advantage over the HD 8750M's Vulkan 1.2.170, though the HD 8750M counters with DirectX 12 (11_1) versus the 940M's DirectX 12 (11_0). The NVIDIA part also carries a defined 75 W TDP and MXM Module form factor, making it easier to integrate into systems with known power budgets.

The verdict is straightforward: if the workload is compute-heavy and memory capacity matters, choose the GeForce 940M. If the workload is memory-bandwidth-bound and average benchmark performance is the priority, the HD 8750M is the safer pick. Given the near-tie in OpenCL scores and the HD 8750M's higher average, the AMD part offers the more balanced overall record, while the GeForce 940M offers superior peak throughput and a more modern API stack.