AMD Radeon PRO W7900 vs Intel Arc Pro A60 Comparison

FAQ

Q: Which card is faster in the recorded benchmark data?

A: The AMD Radeon PRO W7900 wins both recorded head-to-head tests. It scores 84,379 in Geekbench OpenCL and 137,070 in Geekbench Vulkan, versus 63,485 and 57,166 for the Intel Arc Pro A60 respectively.

Q: How large is the performance gap between the two cards in the Vulkan test?

A: The AMD card leads by 139.8% in Geekbench Vulkan. The Intel card trails significantly, with the AMD card delivering more than double the score.

Q: What is the memory capacity difference?

A: The AMD Radeon PRO W7900 has 48 GB of GDDR6 memory on a 384-bit bus, while the Intel Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus. The AMD card also has 864.0 GB/s of memory bandwidth versus 384.0 GB/s.

Q: Which card has a higher transistor count and larger die?

A: The AMD card uses 57,700 million transistors on a 529 mm² die, while the Intel card uses 11,500 million transistors on a 269 mm² die. The process nodes differ too: 5 nm for AMD versus 6 nm for Intel.

Q: Do both cards support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display outputs differ, though: AMD offers 3x DisplayPort 2.1 and 1x mini-DisplayPort 2.1, while Intel offers 4x DisplayPort 2.0.

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

A: The AMD Radeon PRO W7900 sits at the 94th percentile, while the Intel Arc Pro A60 is at the 88th percentile. The AMD card's average benchmark score is 110,725 versus 60,326 for the Intel card.

Architecture Differences

The AMD Radeon PRO W7900 is built on the RDNA 3.0 architecture with the Navi 31 chip, codenamed Plum Bonito. It uses a 5 nm process from TSMC, packing 57,700 million transistors into a 529 mm² die. The transistor density is 109.1M per mm². In contrast, the Intel Arc Pro A60 uses the Xe-HPG architecture with the DG2-256 chip from the Alchemist Pro Series. It is fabricated on a 6 nm TSMC process, with 11,500 million transistors on a 269 mm² die, giving a density of 42.8M per mm².

The core configurations diverge sharply. The AMD card has 6,144 shading units, 384 texture mapping units, 192 raster output units, and 96 ray tracing cores. The Intel card has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 ray tracing cores. This means the AMD card has three times the shading units, three times the TMUs, and six times the ray tracing cores.

Clock speeds also favor the AMD card. The base clock is 1,760 MHz with a boost of 2,495 MHz, while the Intel card runs at 900 MHz base and 2,050 MHz boost. The memory clocks differ as well: 2,250 MHz (18 Gbps effective) for AMD versus 2,000 MHz (16 Gbps effective) for Intel.

The FP32 compute rates reflect the massive gap in raw horsepower. The AMD card delivers 61.32 TFLOPS of FP32 and 61.32 TFLOPS of FP16 (1:1 ratio). The Intel card produces 8.397 TFLOPS of FP32 and 16.79 TFLOPS of FP16 (2:1 ratio). The AMD card's FP16 performance matches its FP32, whereas Intel doubles its FP16 throughput relative to FP32.

Pixel and texture rates underline the difference: AMD achieves 479.0 GPixel/s and 958.1 GTexel/s, while Intel manages 131.2 GPixel/s and 262.4 GTexel/s. The power envelope is also distinct: the AMD card has a 295 W TDP and requires a 600 W suggested PSU with 2x 8-pin connectors, while the Intel card has a 130 W TDP and a 300 W suggested PSU with no power connectors listed.

Head-to-Head Benchmarks

The recorded head-to-head data contains two tests, and the AMD Radeon PRO W7900 wins both outright. In Geekbench OpenCL, the AMD card scores 84,379 against the Intel Arc Pro A60's 63,485, a delta of 32.9%. In Geekbench Vulkan, the AMD card scores 137,070 against 57,166, a delta of 139.8%.

The OpenCL result shows a solid but not overwhelming lead. A 32.9% advantage means the AMD card is roughly a third faster in this compute workload, which is substantial for professional rendering or simulation tasks that rely on OpenCL acceleration.

The Vulkan result is far more lopsided. A 139.8% delta means the AMD card more than doubles the Intel card's score. This suggests that in Vulkan-based workloads, the AMD card's higher shading unit count, faster clocks, and wider memory bus translate into a dominant performance advantage. The Intel card's 16 ray tracing cores and 2,048 shading units simply cannot keep pace with the AMD card's 96 RT cores and 6,144 shading units.

Looking at the broader benchmark context, the AMD card's average benchmark score is 110,725, placing it at the 94th percentile of all GPUs. Its nearest rivals include the AMD Radeon Pro Vega II at 109,617 (1% slower), the NVIDIA RTX A5500 Mobile at 113,944 (2.8% faster), the AMD Radeon Pro W6600X at 107,342 (3.2% slower), and the NVIDIA Tesla V100 SXM2 16 GB at 114,395 (3.2% faster). The AMD card sits near the top of its performance tier.

The Intel Arc Pro A60, with an average benchmark score of 60,326, sits at the 88th percentile. Its nearest rivals are oddly matched: the NVIDIA GeForce RTX 4090 at 60,347 (0% delta), the AMD Radeon Pro Vega 48 at 60,140 (0.3% faster), the AMD Radeon Pro W6600M at 61,896 (2.5% faster), and the AMD Radeon PRO V710 at 58,657 (2.8% slower). The Intel card's average score is essentially tied with the RTX 4090 in this particular database's average, which highlights how benchmark averages can flatten differences across workloads.

The Verdict

The data is unambiguous: the AMD Radeon PRO W7900 is in a different performance class than the Intel Arc Pro A60. Across both recorded benchmarks, the AMD card leads by 32.9% and 139.8%, respectively. The AMD card also holds a 94th percentile ranking versus the Intel card's 88th, and its average benchmark score of 110,725 is nearly double the Intel card's 60,326.

For users who need maximum compute throughput in OpenCL or Vulkan workloads, the AMD card is the clear choice. Its 48 GB memory capacity and 864.0 GB/s bandwidth are suited for large datasets and high-resolution textures, while its 96 ray tracing cores provide substantial RT acceleration if needed. The 295 W TDP and triple-slot cooler are trade-offs for that performance.

The Intel Arc Pro A60 is the more modest option. With 12 GB of memory, 384.0 GB/s bandwidth, and a 130 W TDP, it fits a single-slot form factor and requires no external power connectors. It is a capable card for lighter professional workloads, but the benchmark results show it trails the AMD card by a wide margin. Its average score of 60,326 places it near the RTX 4090 in the database average, but that is an artifact of averaging across varied tests; in the actual head-to-head tests, the Intel card loses both.

There is no scenario in the recorded data where the Intel card wins. The AMD card wins both head-to-head tests, has a higher percentile, a higher average score, and a larger memory footprint. For professional users prioritizing raw performance, the AMD Radeon PRO W7900 is the only choice based on these measurements.

Specification Differences

| Specification | AMD Radeon PRO W7900 | Intel Arc Pro A60 |

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

| Architecture | RDNA 3.0 | Xe-HPG |

| Process Node | 5 nm | 6 nm |

| Transistors | 57,700 million | 11,500 million |

| Die Size | 529 mm² | 269 mm² |

| Base Clock | 1,760 MHz | 900 MHz |

| Boost Clock | 2,495 MHz | 2,050 MHz |

| Memory Size | 48 GB | 12 GB |

| Memory Bus Width | 384 bit | 192 bit |

| Memory Bandwidth | 864.0 GB/s | 384.0 GB/s |

| Shading Units | 6,144 | 2,048 |

| TMUs | 384 | 128 |

| ROPs | 192 | 64 |

| RT Cores | 96 | 16 |

| FP32 | 61.32 TFLOPS | 8.397 TFLOPS |

| FP16 | 61.32 TFLOPS (1:1) | 16.79 TFLOPS (2:1) |

| Pixel Rate | 479.0 GPixel/s | 131.2 GPixel/s |

| Texture Rate | 958.1 GTexel/s | 262.4 GTexel/s |

| TDP | 295 W | 130 W |

| Slot Width | Triple-slot | Single-slot |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 600 W | 300 W |

| Display Outputs | 3x DP 2.1, 1x mini-DP 2.1 | 4x DP 2.0 |

| Release Date | 2023-05-25 | 2023-06-05 |

| Launch MSRP | 3,999 USD | None listed |

Where Each One Wins

The AMD Radeon PRO W7900 wins every recorded benchmark category. In Geekbench OpenCL, it beats the Intel card by 32.9%, and in Geekbench Vulkan, it wins by 139.8%. This makes it the superior choice for any workload that relies on compute shaders, ray tracing, or large memory buffers. The 48 GB memory capacity and 864.0 GB/s bandwidth are particularly suited for GPU-accelerated rendering, scientific simulation, or machine learning inference with large models.

The Intel Arc Pro A60 has no benchmark wins in the recorded data. However, its specifications suggest a different use case. With a 130 W TDP, single-slot design, and no external power connectors, it can fit into compact workstations or servers where space and power are limited. The 12 GB memory capacity is adequate for moderate texture workloads, and the 4x DisplayPort 2.0 outputs allow for multi-monitor setups. Its FP16 performance of 16.79 TFLOPS (2:1 ratio) is comparatively stronger than its FP32 output, which may benefit certain AI inference tasks that use reduced precision.

For users who need a small, low-power professional GPU with multiple display outputs, the Intel card fits that niche. For users who need maximum compute performance, the AMD card is the only option among these two. The data shows no scenario where the Intel card outperforms the AMD card, so the decision ultimately comes down to power and form factor constraints versus raw performance requirements.