AMD Radeon Pro W6600M vs Intel Arc Pro A60 Comparison

The AMD Radeon Pro W6600M and Intel Arc Pro A60 are two professional mobile and workstation graphics solutions that target similar workloads but approach them from very different architectural directions. Benchmark data shows a near-total split in performance depending on the API used, with each card claiming a decisive victory in one of the two tested scenarios. The Radeon Pro W6600M posts an average benchmark score of 61,896, placing it in the 89th percentile of all GPUs, while the Arc Pro A60 averages 60,326, sitting in the 88th percentile. Their head-to-head results reveal that neither card is universally faster; instead, the choice hinges on which applications and APIs dominate a given workflow.

Head-to-Head Benchmarks

The most striking finding from the head-to-head data is the complete divergence in results across the two Geekbench tests. In the OpenCL test, the Intel Arc Pro A60 scores 63,485, while the AMD Radeon Pro W6600M manages 56,140. That is an 11.6% deficit for the AMD card, a substantial margin that suggests Intel’s architecture has a clear advantage in OpenCL compute workloads. The Arc Pro A60’s higher shading unit count and texture rate likely contribute to this lead, though the exact cause cannot be isolated from the available data.

However, the Vulkan benchmark tells the opposite story. The Radeon Pro W6600M scores 67,652, compared to the Arc Pro A60’s 57,166. This represents an 18.3% lead for AMD—an even larger margin than Intel’s OpenCL win. The Vulkan result is particularly impressive for the Radeon, as it indicates that AMD’s RDNA 2.0 architecture handles modern graphics APIs with greater efficiency. This split is unusual; most GPU comparisons show one card winning across all APIs, but here the two cards are essentially trading blows based on software stack preferences.

Looking at the average benchmark scores, the Radeon Pro W6600M’s 61,896 average is 2.6% higher than the Arc Pro A60’s 60,326, according to the nearestRivals data. Interestingly, the Intel card’s own rival list shows it trailing the AMD card by 2.5% (deltaPct of -2.5), confirming the same relative standing. This small overall advantage for AMD is driven entirely by its dominant Vulkan performance, which outweighs Intel’s OpenCL win in the averaging calculation.

The nearestRivals data provides additional context. The Radeon Pro W6600M sits just 0.3% behind the AMD Radeon 8050S (62,108) and 2.6% ahead of the NVIDIA GeForce RTX 4090 (60,347). For the Intel card, the RTX 4090 is listed as a 0% delta rival, meaning the Arc Pro A60 and RTX 4090 have nearly identical average scores—a remarkable result for a professional card against a flagship consumer GPU. Both cards also closely track the AMD Radeon Pro Vega 48, with the Radeon Pro W6600M 2.9% ahead and the Arc Pro A60 0.3% ahead of that older workstation part.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The AMD Radeon Pro W6600M uses the Navi 23 chip based on RDNA 2.0 architecture, manufactured on a 7 nm process at TSMC. The Intel Arc Pro A60 employs the DG2-256 chip with Xe-HPG architecture, also from TSMC but on a more advanced 6 nm node. Despite the smaller process, Intel’s die is larger at 269 mm² compared to AMD’s 237 mm², and Intel packs slightly more transistors—11,500 million versus 11,060 million. This results in a lower transistor density for Intel (42.8M per mm²) compared to AMD (46.7M per mm²), suggesting AMD achieves better packing efficiency on its mature 7 nm process.

Core counts differ significantly. The Arc Pro A60 features 2,048 shading units, 128 texture mapping units, and 64 ROPs, while the Radeon Pro W6600M has 1,792 shading units, 112 TMUs, and 64 ROPs. Intel’s card therefore has 14.3% more shading units and TMUs, which helps explain its OpenCL lead. However, the ray tracing core counts flip the script: AMD includes 28 RT cores, while Intel has only 16. This 75% advantage for AMD in RT hardware may be a factor in its Vulkan superiority, though the benchmark data does not specifically test ray tracing.

Clock speeds also diverge. The Radeon Pro W6600M has a base clock of 1224 MHz and a boost of 2034 MHz, while the Arc Pro A60 starts lower at 900 MHz base but boosts slightly higher to 2050 MHz. The AMD card’s higher base clock suggests better sustained performance in power-constrained scenarios, but the Intel card’s higher boost clock gives it a peak advantage. Memory configurations are notably different: the Radeon Pro W6600M uses 8 GB of GDDR6 on a 128-bit bus, yielding 224.0 GB/s of bandwidth, while the Arc Pro A60 offers 12 GB of GDDR6 on a 192-bit bus, achieving 384.0 GB/s. Intel’s memory bandwidth is 71.4% higher, which is a substantial advantage for bandwidth-hungry compute tasks.

Power and physical design are also distinct. The Radeon Pro W6600M is rated at 90 W TDP and is an IGP (integrated graphics processor) with no power connectors, designed for mobile workstations. The Arc Pro A60 consumes 130 W, is a single-slot card, and requires a 300 W suggested PSU, indicating it is intended for desktop or larger chassis configurations. Both use PCIe 4.0 x16 interfaces, but the AMD card’s display outputs are portable device dependent, while the Intel card offers four DisplayPort 2.0 outputs.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro W6600M averages 61,896, which is 2.6% higher than the Intel Arc Pro A60’s 60,326 average.

Q: Why does the Intel Arc Pro A60 win the OpenCL benchmark?

A: The Arc Pro A60 scores 63,485 in OpenCL versus 56,140 for the Radeon Pro W6600M, an 11.6% lead. This likely stems from its higher shading unit count (2,048 vs 1,792) and greater memory bandwidth (384.0 GB/s vs 224.0 GB/s).

Q: How does the AMD card achieve its Vulkan victory?

A: The Radeon Pro W6600M scores 67,652 in Vulkan compared to 57,166 for the Arc Pro A60, an 18.3% advantage. The AMD card’s 28 ray tracing cores versus Intel’s 16 may contribute, as may architectural efficiencies in RDNA 2.0.

Q: Is the Intel Arc Pro A60 more power-hungry?

A: Yes, the Arc Pro A60 has a 130 W TDP, while the Radeon Pro W6600M is rated at 90 W. The Intel card also requires a 300 W suggested PSU, whereas the AMD card needs no power connectors.

Q: Which GPU has more memory?

A: The Intel Arc Pro A60 offers 12 GB of GDDR6, compared to 8 GB on the AMD Radeon Pro W6600M. Intel also has a wider 192-bit bus versus 128-bit, giving it 384.0 GB/s bandwidth versus 224.0 GB/s.

Q: How do these cards compare to the NVIDIA GeForce RTX 4090?

A: The Radeon Pro W6600M is 2.6% ahead of the RTX 4090, while the Arc Pro A60 matches it exactly (0% delta). Both professional cards are remarkably competitive against that flagship consumer GPU in average scores.

Specification Differences

| Specification | AMD Radeon Pro W6600M | Intel Arc Pro A60 |

|---|---|---|

| Architecture | RDNA 2.0 | Xe-HPG |

| Process Node | 7 nm | 6 nm |

| Transistors | 11,060 million | 11,500 million |

| Die Size | 237 mm² | 269 mm² |

| Transistor Density | 46.7M / mm² | 42.8M / mm² |

| Base Clock | 1224 MHz | 900 MHz |

| Boost Clock | 2034 MHz | 2050 MHz |

| Memory Size | 8 GB | 12 GB |

| Memory Bus Width | 128 bit | 192 bit |

| Memory Bandwidth | 224.0 GB/s | 384.0 GB/s |

| Shading Units | 1,792 | 2,048 |

| TMUs | 112 | 128 |

| RT Cores | 28 | 16 |

| Pixel Rate | 130.2 GPixel/s | 131.2 GPixel/s |

| Texture Rate | 227.8 GTexel/s | 262.4 GTexel/s |

| FP32 Performance | 7.290 TFLOPS | 8.397 TFLOPS |

| FP16 Performance | 14.58 TFLOPS (2:1) | 16.79 TFLOPS (2:1) |

| TDP | 90 W | 130 W |

| Slot Width | IGP | Single-slot |

| Suggested PSU | None | 300 W |

| Display Outputs | Portable Device Dependent | 4x DisplayPort 2.0 |

| Production Status | End-of-life | Active |

| Release Date | 2021-06-07 | 2023-06-05 |

The Verdict

The data presents a clear but conditional picture. For applications that leverage Vulkan—common in modern games and some professional visualization tools—the AMD Radeon Pro W6600M is the stronger choice, delivering an 18.3% performance advantage. Its 28 RT cores and higher base clock of 1224 MHz make it particularly suited to ray-traced workloads and sustained compute under the 90 W TDP envelope. The AMD card also has a slight overall average score edge (2.6%) and a higher percentile ranking (89th versus 88th).

For OpenCL-centric workflows—which include many scientific computing, machine learning, and video processing tasks—the Intel Arc Pro A60 dominates with an 11.6% lead. Its 2,048 shading units, 384.0 GB/s memory bandwidth, and 12 GB of VRAM provide raw compute and memory capacity that the AMD card cannot match. The Intel card’s 8.397 TFLOPS FP32 performance versus 7.290 TFLOPS for AMD further reinforces its raw compute advantage.

The production status is a deciding factor for long-term deployments. The Radeon Pro W6600M is end-of-life, released in June 2021, while the Arc Pro A60 is active and was released in June 2023. Purchasing an end-of-life product carries risks regarding driver updates and long-term support, even if its performance profile remains competitive.

Where Each One Wins

AMD Radeon Pro W6600M wins in:

• Vulkan-based applications, with an 18.3% higher score (67,652 vs 57,166)
• Ray tracing workloads, thanks to 28 RT cores versus 16 on Intel
• Mobile and power-constrained environments, with a 90 W TDP and no power connectors
• Overall average benchmark performance, at 61,896 versus 60,326
• Lower power consumption scenarios where the 130 W TDP of the Intel card is prohibitive

Intel Arc Pro A60 wins in:

• OpenCL compute tasks, scoring 63,485 versus 56,140 (11.6% lead)
• Memory-intensive applications, offering 12 GB VRAM and 384.0 GB/s bandwidth
• Raw shading throughput, with 2,048 units and a texture rate of 262.4 GTexel/s
• Peak FP32 performance at 8.397 TFLOPS versus 7.290 TFLOPS
• Longevity and support, as an active product versus the AMD card’s end-of-life status
• Multi-display setups, with four DisplayPort 2.0 outputs versus portable device dependent outputs