Intel Arc A310 vs Intel UHD Graphics 750 Comparison

Intel Arc A310 and Intel UHD Graphics 750 occupy entirely different tiers of the GPU spectrum, yet both sit at the 40th percentile of all GPUs according to the benchmark database. The Arc A310 is a discrete entry-level solution based on the Xe-HPG architecture, while the UHD 750 is an integrated graphics processor embedded in Rocket Lake CPUs. Despite the UHD 750’s lower absolute scores, the data reveals a surprisingly narrow overall performance gap, though the Arc A310 dominates in compute-heavy workloads.

Head-to-Head Benchmarks

The head-to-head comparison between these two GPUs is limited to two benchmarks, and the Intel Arc A310 wins both decisively. In Geekbench OpenCL, the Arc A310 scores 30,607 points against the UHD 750’s 6,743 points, yielding a delta of 353.9% in favor of the discrete card. This is not a marginal victory; it is a four-fold increase in raw compute throughput, reflecting the Arc A310’s dedicated memory interface and higher shader count.

The Vulkan results tell a similar story, though with a slightly narrower margin. The Arc A310 posts 28,964 points, while the UHD 750 manages 8,138 points, resulting in a 255.9% delta. This indicates that even in a modern low-level graphics API, the discrete solution maintains a commanding lead. The UHD 750’s scores are not negligible—they represent functional 1080p-capable performance for light gaming—but they are firmly in a different class than the Arc A310.

Looking at the broader benchmark averages, the picture becomes more nuanced. The Arc A310’s average benchmark score is 7,550, while the UHD 750 trails at 7,441, a difference of just 1.4%. This is striking: the head-to-head benchmarks show a massive gap, yet the aggregate data suggests near-parity. The explanation lies in the benchmark suite composition. The Arc A310 has only nine recorded benchmarks, while the UHD 750 has just two. The PassMark G3D score for the Arc A310 is 5,433, and its PassMark GPU Compute score is 2,157, both of which are moderate. The UHD 750 lacks these specific PassMark entries, so its average is driven solely by the two Geekbench tests. Consequently, the average score comparison favors the integrated GPU more than raw performance would suggest.

The nearest rivals data reinforces this disparity. The Arc A310’s closest competitor is the AMD Radeon R7 250, with an average score of 7,557, just 0.1% higher. It also sits within 1% of the NVIDIA GeForce GTX 1650 (7,472), which is remarkable for a low-power discrete card. Meanwhile, the UHD 750’s nearest rival is the AMD Radeon HD 8850M, with a delta of -0.1%, and it is 1.4% behind the Arc A310 in the same comparison. This suggests that while the UHD 750 is competitive with older entry-level discrete GPUs, it cannot match the Arc A310 in sustained compute tasks.

Architecture Differences

The architectural chasm between these two GPUs is vast. The Arc A310 is built on the Xe-HPG architecture, manufactured on a 6 nm process at TSMC, with a die size of 157 mm² and 7,200 million transistors. This yields a transistor density of 45.9 million per square millimeter. In contrast, the UHD 750 uses Intel’s Generation 12.1 architecture, fabricated on a 14 nm+++ process at Intel’s own foundries. While the UHD 750’s transistor count and die size are not listed, the process node difference alone—14 nm versus 6 nm—explains the vast disparity in feature density and power efficiency.

The Arc A310 features 768 shading units, 32 texture mapping units, and 16 raster operations pipelines. It also includes 6 dedicated ray tracing cores, a feature entirely absent from the UHD 750. The integrated GPU offers 256 shading units, 16 TMUs, and 8 ROPs, which is exactly one-third of the Arc A310’s shader count and half its TMU/ROP counts. This directly translates to the pixel and texture rates: the Arc A310 achieves 28.00 GPixel/s and 56.00 GTexel/s, while the UHD 750 manages 10.40 GPixel/s and 20.80 GTexel/s. The Arc A310 is 2.7x faster in pixel throughput and 2.7x faster in texture throughput.

Memory architecture further separates the two. The Arc A310 uses 4 GB of GDDR6 memory on a 64-bit bus, delivering 124.0 GB/s of bandwidth. The UHD 750 relies on system shared memory, with bus width and bandwidth listed as "System Shared" and "System Dependent," respectively. This is a critical disadvantage for the integrated GPU, as it must compete with the CPU for memory bandwidth, whereas the Arc A310 has dedicated high-speed VRAM. The Arc A310’s memory clock is 1937 MHz (15.5 Gbps effective), while the UHD 750’s memory clock is simply "System Shared."

Clock speeds also differ dramatically. The Arc A310 runs at a flat 1750 MHz for both base and boost, with no game clock listed. The UHD 750 has a base clock of 300 MHz and a boost of 1300 MHz. While the UHD 750’s boost is close to the Arc A310’s sustained clock, the integrated GPU cannot hold that frequency under sustained load due to thermal and power constraints inherent to iGPUs. The FP32 compute figures illustrate the gap clearly: the Arc A310 delivers 2.688 TFLOPS, while the UHD 750 produces 665.6 GFLOPS (0.6656 TFLOPS). The Arc A310 is 4.04x faster in single-precision floating-point performance.

The Verdict

From the data, the choice between these two GPUs is clear for most use cases. The Intel Arc A310 is the superior performer in every head-to-head benchmark, with a 353.9% lead in OpenCL and a 255.9% lead in Vulkan. It offers dedicated GDDR6 memory, ray tracing support, and a modern 6 nm process, all within a 30 W TDP. The UHD 750, by contrast, is a 15 W integrated solution with no ray tracing, no dedicated memory, and a 14 nm process. If raw compute or gaming performance is the priority, the Arc A310 is the only rational choice.

However, the UHD 750 has one undeniable advantage: it is integrated into the CPU. It requires no additional slot, no power connectors, and its bus interface is a Ring Bus, meaning there is zero incremental cost or complexity. The Arc A310, while low-profile, still requires a PCIe 4.0 x8 slot and a 200 W suggested PSU. For a system builder seeking a compact, low-power office PC or media center, the UHD 750’s performance—while 1.4% lower on average—is sufficient for 2D workloads and light 3D acceleration, with zero extra hardware.

The percentile ranking is identical at 40 for both, which indicates they occupy the same tier in the database’s overall distribution. Yet the average benchmark scores tell a different story. The Arc A310’s 7,550 average is 1.4% higher than the UHD 750’s 7,441, but this small delta masks the fact that the Arc A310 is 353.9% faster in OpenCL. The UHD 750’s average is inflated by the lack of PassMark scores, which tend to pull the Arc A310 down. In practice, the Arc A310 is the better GPU for any task that stresses the GPU, while the UHD 750 is only preferable when system integration and power draw are paramount.

Specification Differences

The following specifications differ between the Intel Arc A310 and Intel UHD Graphics 750:

• Chip: DG2-128 vs Rocket Lake
• Architecture: Xe-HPG vs Generation 12.1
• Generation: Alchemist (Arc 3) vs HD Graphics (Rocket Lake)
• Process Node: 6 nm (TSMC) vs 14 nm+++ (Intel)
• Foundry: TSMC vs Intel
• Transistors: 7,200 million vs not listed
• Die Size: 157 mm² vs not listed
• Transistor Density: 45.9M / mm² vs not listed
• Base Clock: 1750 MHz vs 300 MHz
• Boost Clock: 1750 MHz vs 1300 MHz
• Memory Clock: 1937 MHz (15.5 Gbps effective) vs System Shared
• Memory Size: 4 GB GDDR6 vs System Shared
• Memory Type: GDDR6 vs System Shared
• Memory Bus Width: 64 bit vs System Shared
• Memory Bandwidth: 124.0 GB/s vs System Dependent
• Shading Units: 768 vs 256
• TMUs: 32 vs 16
• ROPs: 16 vs 8
• RT Cores: 6 vs not listed
• Pixel Rate: 28.00 GPixel/s vs 10.40 GPixel/s
• Texture Rate: 56.00 GTexel/s vs 20.80 GTexel/s
• FP32: 2.688 TFLOPS vs 665.6 GFLOPS
• FP16: 5.376 TFLOPS (2:1) vs 1,331.2 GFLOPS (2:1)
• TDP: 30 W vs 15 W
• Slot Width: Single-slot vs IGP
• Power Connectors: None vs not listed
• Suggested PSU: 200 W vs not listed
• Bus Interface: PCIe 4.0 x8 vs Ring Bus
• Display Outputs: 4x mini-DisplayPort 2.0 vs Motherboard Dependent
• DirectX Support: 12 Ultimate (12_2) vs 12 (12_1)
• Release Date: 2022-10-11 vs 2021-03-29
• Predecessor: Xe Graphics vs not listed
• Successor: Battlemage vs not listed

FAQ

Q: Which GPU has higher raw compute performance?

A: The Intel Arc A310 is far ahead, with 2.688 TFLOPS FP32 versus the UHD 750’s 665.6 GFLOPS, a 4.04x difference. In Geekbench OpenCL, the Arc A310 scores 30,607 versus 6,743, a 353.9% delta.

Q: Does the Intel UHD Graphics 750 support ray tracing?

A: No. The UHD 750 has no ray tracing cores listed, while the Arc A310 includes 6 dedicated RT cores and supports DirectX 12 Ultimate (12_2). The UHD 750 only supports DirectX 12 (12_1).

Q: How do the memory systems compare?

A: The Arc A310 uses 4 GB of GDDR6 on a 64-bit bus with 124.0 GB/s bandwidth. The UHD 750 uses system shared memory with system-dependent bandwidth, which is a major limitation for memory-heavy workloads.

Q: Are these GPUs in the same performance percentile?

A: Yes, both are in the 40th percentile of all GPUs. However, the Arc A310 has an average benchmark score of 7,550 versus 7,441 for the UHD 750, a 1.4% difference.

Q: Which GPU is more power-efficient?

A: The UHD 750 has a lower TDP at 15 W versus the Arc A310’s 30 W. However, the Arc A310 delivers over 4x the FP32 performance, so it is far more efficient per watt of compute.

Q: What is the release date difference?

A: The Intel UHD Graphics 750 was released on 2021-03-29, while the Intel Arc A310 came later on 2022-10-11. Both are now end-of-life products.