Intel Arc Pro A60 vs NVIDIA CMP 30HX Comparison

NVIDIA CMP 30HX and Intel Arc Pro A60 occupy different corners of the GPU landscape, with the former a Turing-based mining part and the latter a contemporary Xe-HPG workstation card. The data shows the NVIDIA card wins both head-to-head benchmarks, but the Intel part counters with superior specifications and modern features, making it the more balanced choice for general-purpose computing.

The Verdict

The Intel Arc Pro A60 is the pick for users needing a functional display output, modern API support, and higher raw compute throughput. The NVIDIA CMP 30HX, with no display outputs and a PCIe 1.0 x4 interface, is strictly a computation-focused accelerator. The Arc Pro A60 offers 12 GB of GDDR6 memory versus 6 GB on the CMP 30HX, and its 8.397 TFLOPS FP32 performance exceeds the CMP 30HX’s 5.027 TFLOPS by roughly 67%. However, benchmark results tell a different story: the CMP 30HX wins the Geekbench OpenCL test with 65199 points versus 63485 (a 2.7% lead) and dominates the Vulkan test with 62484 versus 57166 (a 9.3% lead). So, while the Intel part has superior theoretical specs, the NVIDIA part actually performs better in these specific workloads. The Arc Pro A60 is the sensible recommendation for a working GPU with modern display connectivity and ongoing production status; the CMP 30HX is a specialized compute card for those who do not need video output and can work around its legacy bus interface.

Architecture Differences

The NVIDIA CMP 30HX is built on the Turing architecture using the TU116 chip, fabricated on a 12 nm process at TSMC. It packs 6,600 million transistors on a 284 mm² die, yielding a transistor density of 23.2M per mm². The Intel Arc Pro A60 uses the Xe-HPG architecture with the DG2-256 chip, manufactured on a 6 nm process, also at TSMC. This chip contains 11,500 million transistors on a 269 mm² die, giving it a much higher density of 42.8M per mm². The Intel part is a generation newer, released in June 2023 versus February 2021 for the NVIDIA card, and its production status is Active while the CMP 30HX is End-of-life.

Memory configurations differ significantly. The CMP 30HX has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s bandwidth. The Arc Pro A60 doubles capacity to 12 GB of GDDR6 on the same 192-bit bus width, achieving 384.0 GB/s. Clock speeds also diverge: the CMP 30HX has a higher base clock at 1530 MHz but a lower boost clock at 1785 MHz, while the Arc Pro A60 starts at 900 MHz base and boosts to 2050 MHz. The NVIDIA card’s memory runs at 1750 MHz (14 Gbps effective), whereas the Intel card’s memory operates at 2000 MHz (16 Gbps effective).

Compute resources are dramatically different. The CMP 30HX has 1408 shading units, 88 TMUs, and 48 ROPs, with no ray tracing or tensor cores. The Arc Pro A60 features 2048 shading units, 128 TMUs, 64 ROPs, and 16 ray tracing cores. This translates to a pixel rate of 85.68 GPixel/s and texture rate of 157.1 GTexel/s for the NVIDIA card, versus 131.2 GPixel/s and 262.4 GTexel/s for the Intel card. FP16 performance shows the same pattern: the CMP 30HX delivers 10.05 TFLOPS (2:1), while the Arc Pro A60 reaches 16.79 TFLOPS (2:1).

Power and physical characteristics also differ. The CMP 30HX has a 125 W TDP with a dual-slot cooler and requires one 8-pin power connector. The Arc Pro A60 has a slightly higher 130 W TDP but uses a single-slot design and requires no external power connector. Both suggest a 300 W power supply. The NVIDIA card measures 229 mm in length, 111 mm in height, and 35 mm in width; the Intel card’s dimensions are not provided.

Head-to-Head Benchmarks

The Geekbench OpenCL test shows the NVIDIA CMP 30HX scoring 65199 points against the Intel Arc Pro A60’s 63485 points, a 2.7% margin in favor of NVIDIA. This is a modest win, and the data indicates both cards sit in the same performance tier. The CMP 30HX’s closest rival is the AMD Radeon RX 9060 XT LP with an average score of 63830 (0% delta), while the Arc Pro A60’s nearest competitor is the NVIDIA GeForce RTX 4090 with an average of 60347 (0% delta). Notably, the CMP 30HX outperforms the Arc Pro A60 in this test, but the Arc Pro A60’s average benchmark score of 60326 is lower than its OpenCL score, suggesting the Vulkan test drags down its overall average.

The Geekbench Vulkan test reveals a larger gap. The CMP 30HX scores 62484 points, while the Arc Pro A60 manages only 57166 points, giving NVIDIA a 9.3% advantage. This is the decisive benchmark victory for the CMP 30HX. The Vulkan delta is over three times larger than the OpenCL delta, indicating the NVIDIA architecture handles this workload significantly better. The CMP 30HX wins both head-to-head tests (2 wins, 0 losses), but the Arc Pro A60’s superior specifications suggest it should be faster on paper—the benchmark data contradicts the spec sheet.

Looking at percentile rankings, the CMP 30HX sits at the 89th percentile of all GPUs, while the Arc Pro A60 sits at the 88th percentile. This one-percentile difference is small, reflecting the narrow performance gap in the benchmarks. The CMP 30HX’s average benchmark score is 63842, which is 5.8% higher than the Arc Pro A60’s 60326. In terms of nearest rivals, the CMP 30HX is closely matched with the AMD Radeon RX 9060 XT LP (63830, 0% delta) and the AMD Radeon RX 7600M (63775, 0.1% delta). The Arc Pro A60’s rivals include the AMD Radeon Pro Vega 48 (60140, 0.3% delta) and the AMD Radeon Pro W6600M (61896, -2.5% delta).

Specification Differences

The two GPUs differ on nearly every specification field. The process node is 12 nm for NVIDIA versus 6 nm for Intel, with transistor counts of 6,600 million versus 11,500 million. Die size is similar—284 mm² versus 269 mm²—but transistor density is nearly double on the Intel part (42.8M / mm² versus 23.2M / mm²). Memory capacity is 6 GB versus 12 GB, while bandwidth is 336.0 GB/s versus 384.0 GB/s. Shading units number 1408 versus 2048, TMUs 88 versus 128, and ROPs 48 versus 64. The Intel card adds 16 ray tracing cores; the NVIDIA card has none.

Clock speeds differ: base clock is 1530 MHz versus 900 MHz, but boost clock is 1785 MHz versus 2050 MHz. Memory clock is 1750 MHz (14 Gbps effective) versus 2000 MHz (16 Gbps effective). Pixel rate is 85.68 GPixel/s versus 131.2 GPixel/s, and texture rate is 157.1 GTexel/s versus 262.4 GTexel/s. FP32 performance is 5.027 TFLOPS versus 8.397 TFLOPS, and FP16 is 10.05 TFLOPS versus 16.79 TFLOPS (both 2:1).

Power consumption is close: 125 W versus 130 W TDP, with both suggesting a 300 W PSU. The NVIDIA card is dual-slot with one 8-pin connector; the Intel card is single-slot with no power connector. Bus interface is a major differentiator: PCIe 1.0 x4 on the NVIDIA card versus PCIe 4.0 x16 on the Intel card. Display outputs are absent on the CMP 30HX, while the Arc Pro A60 offers 4x DisplayPort 2.0. DirectX support is 12 (12_1) for NVIDIA versus 12 Ultimate (12_2) for Intel; both support OpenGL 4.6 and Vulkan 1.4. The NVIDIA card was released on 2021-02-24 with a launch MSRP of 799 USD, while the Intel card released on 2023-06-05 with no launch MSRP provided.

FAQ

Q: Which GPU has better raw compute specifications?

A: The Intel Arc Pro A60 has significantly higher specs: 2048 shading units versus 1408, 8.397 TFLOPS FP32 versus 5.027 TFLOPS, and 12 GB memory versus 6 GB. It also has 16 ray tracing cores, which the NVIDIA CMP 30HX lacks entirely.

Q: Why does the NVIDIA CMP 30HX win benchmarks despite having weaker specifications?

A: The benchmark data shows the CMP 30HX leading by 2.7% in Geekbench OpenCL (65199 vs 63485) and 9.3% in Geekbench Vulkan (62484 vs 57166). The reasons are not stated in the data, but the results consistently favor NVIDIA across both tests.

Q: Can the NVIDIA CMP 30HX be used for display output?

A: No. The CMP 30HX has no display outputs, making it unsuitable for standard desktop use. The Intel Arc Pro A60, by contrast, has 4x DisplayPort 2.0 outputs.

Q: How do their bus interfaces differ?

A: The CMP 30HX uses PCIe 1.0 x4, a legacy interface that severely limits data transfer speeds. The Arc Pro A60 uses PCIe 4.0 x16, a modern high-bandwidth interface. This could affect performance in bandwidth-sensitive workloads despite the benchmark results.

Q: Which GPU is more power-efficient?

A: The CMP 30HX has a 125 W TDP, while the Arc Pro A60 has a 130 W TDP—a negligible 5 W difference. Both recommend a 300 W power supply, but the Intel card requires no external power connector, while the NVIDIA card needs one 8-pin connector.

Q: What is the performance percentile ranking for each GPU?

A: The CMP 30HX ranks at the 89th percentile of all GPUs with an average benchmark score of 63842. The Arc Pro A60 ranks at the 88th percentile with an average score of 60326, placing both in the upper tier of GPU performance.