AMD Radeon Pro 570 vs Intel Arc A370M Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro 570 leads with an average benchmark score of 33207, compared to the Intel Arc A370M's 29175.

Q: How do the two GPUs compare in OpenCL performance?

A: The Intel Arc A370M wins the OpenCL test with a score of 29676, while the AMD Radeon Pro 570 scores 27702. That is a 6.7% advantage for Intel.

Q: Which GPU performs better in Vulkan workloads?

A: The AMD Radeon Pro 570 dominates in Vulkan, scoring 31974 versus the Intel Arc A370M's 28673. This represents an 11.5% lead for AMD.

Q: What are the process node differences between the two chips?

A: The AMD Radeon Pro 570 uses a 14 nm process from GlobalFoundries, while the Intel Arc A370M uses a 6 nm process from TSMC.

Q: What is the power draw difference?

A: The AMD Radeon Pro 570 has a TDP of 150 W, while the Intel Arc A370M has a TDP of 35 W. Intel's solution draws significantly less power.

Q: When were these GPUs released?

A: The AMD Radeon Pro 570 was released on June 4, 2017, and the Intel Arc A370M was released on March 29, 2022.

Architecture Differences

The AMD Radeon Pro 570 is built on GCN 4.0 architecture with the Ellesmere chip, manufactured on a 14 nm process at GlobalFoundries. It packs 5,700 million transistors into a 232 mm² die, yielding a transistor density of 24.6 million per square millimeter. The chip uses a PCIe 3.0 x16 interface.

The Intel Arc A370M uses Xe-HPG architecture with the DG2-128 chip, built on a 6 nm process at TSMC. It integrates 7,200 million transistors into a smaller 157 mm² die, achieving a much higher transistor density of 45.9 million per square millimeter. The bus interface is PCIe 4.0 x8.

Memory configurations differ substantially. AMD pairs its 4 GB GDDR5 memory with a 256 bit bus, delivering 217.0 GB/s of bandwidth. Intel also has 4 GB, but uses GDDR6 on a 64 bit bus, resulting in 112.0 GB/s. The wider bus on the AMD part gives it roughly double the memory bandwidth despite using older memory technology.

Compute resources tell a mixed story. The AMD Radeon Pro 570 has 1792 shading units, 112 texture mapping units, and 32 render output units. It has no dedicated ray tracing cores. The Intel Arc A370M has 1024 shading units, 64 TMUs, and 32 ROPs, but it includes 8 ray tracing cores. Intel's card supports DirectX 12 Ultimate (12_2), while AMD's card only reaches DirectX 12 (12_0). Vulkan support also differs: Intel lists Vulkan 1.4, AMD lists Vulkan 1.3.

Clock speeds are notably different. The AMD card runs at a 1000 MHz base and 1105 MHz boost. Intel starts at 1550 MHz base and boosts to 2050 MHz. Memory clocks also differ: AMD runs at 1695 MHz (6.8 Gbps effective), Intel at 1750 MHz (14 Gbps effective).

FP16 throughput reveals an architectural split. AMD delivers 3.960 TFLOPS in FP16 with a 1:1 ratio to FP32, meaning no dedicated half-precision acceleration. Intel delivers 8.397 TFLOPS FP16 with a 2:1 ratio, indicating dedicated half-precision hardware.

Where Each One Wins

The AMD Radeon Pro 570 wins in Vulkan scenarios. Its score of 31974 in the Vulkan test is the stronger result from either card across any test. This makes it the better choice for Vulkan-based games and compute workloads that rely on this API. The 11.5% delta over the Intel card is substantial in real-world terms.

The Intel Arc A370M wins in OpenCL workloads. Its score of 29676 outperforms AMD's 27702 by 6.7%. OpenCL is still common in professional applications, video encoding tools, and some scientific computing stacks, so this is a meaningful advantage for Intel.

Beyond raw API performance, the Intel card has architectural advantages that matter in specific use cases. The inclusion of 8 ray tracing cores means DirectX 12 Ultimate titles with ray tracing effects can run, something the AMD card cannot do at all. The 2:1 FP16 throughput also gives Intel a strong edge in AI inference and other half-precision workloads.

The AMD card counters with raw memory bandwidth. At 217.0 GB/s versus 112.0 GB/s, AMD has nearly double the bandwidth. This helps in bandwidth-sensitive tasks like high-resolution texture streaming and certain compute kernels.

Power efficiency is a clear win for Intel. At 35 W TDP versus 150 W, Intel delivers competitive performance at a fraction of the power draw. This makes the Arc A370M far better suited for thin-and-light laptops where thermals and battery life matter.

Specification Differences

| Specification | AMD Radeon Pro 570 | Intel Arc A370M |

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

| Process Node | 14 nm | 6 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 5,700 million | 7,200 million |

| Die Size | 232 mm² | 157 mm² |

| Transistor Density | 24.6M / mm² | 45.9M / mm² |

| Base Clock | 1000 MHz | 1550 MHz |

| Boost Clock | 1105 MHz | 2050 MHz |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus Width | 256 bit | 64 bit |

| Memory Bandwidth | 217.0 GB/s | 112.0 GB/s |

| Shading Units | 1792 | 1024 |

| TMUs | 112 | 64 |

| ROPs | 32 | 32 |

| RT Cores | None | 8 |

| FP32 | 3.960 TFLOPS | 4.198 TFLOPS |

| FP16 | 3.960 TFLOPS (1:1) | 8.397 TFLOPS (2:1) |

| TDP | 150 W | 35 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| DirectX Support | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan Support | 1.3 | 1.4 |

| Release Date | 2017-06-04 | 2022-03-29 |

Head-to-Head Benchmarks

The two cards split their direct comparisons exactly one win each. In the OpenCL test, the Intel Arc A370M posts 29676 against the AMD Radeon Pro 570's 27702, a 6.7% margin. This is Intel's best result and shows the Xe-HPG architecture handling compute workloads efficiently.

In the Vulkan test, the AMD Radeon Pro 570 delivers a decisive 31974 score versus Intel's 28673, an 11.5% advantage. This is the largest delta between the two cards in any benchmark. AMD's GCN architecture, despite its age, demonstrates strong Vulkan driver maturity and execution.

Looking at broader positioning, the AMD card's average score of 33207 places it in the 78th percentile of all GPUs in the database. Its nearest rivals are the NVIDIA GeForce RTX 3050 Mobile (33170, only 0.1% behind), the NVIDIA T550 Mobile (33161, 0.1% behind), the NVIDIA P104-100 (32982, 0.7% behind), and the NVIDIA T600 Mobile (32849, 1.1% behind). This is a tight cluster, meaning the Radeon Pro 570 sits right at the edge of mainstream mobile gaming performance.

The Intel Arc A370M's average score of 29175 places it in the 74th percentile. Its nearest rivals are the AMD Radeon RX Vega M GH (29197, just 0.1% ahead), the AMD FirePro W8000 (29211, 0.1% ahead), the AMD Radeon RX 470 (28996, 0.6% behind), and the AMD Radeon RX 6800M (28874, 1% behind). Intel sits in a slightly lower performance tier, roughly 12% below the AMD card's average.

The head-to-head results show that API choice matters more than raw hardware here. The AMD card has higher peak scores and a better average, but the Intel card is no slouch in OpenCL. If a workload runs primarily on OpenCL, Intel's card is the better pick despite its lower average.

The Verdict

The data points to a clear split decision. For Vulkan-based workloads, the AMD Radeon Pro 570 is the superior choice. Its 11.5% lead in Vulkan and higher overall average score (33207 versus 29175) make it the stronger all-round performer. The 78th percentile ranking versus Intel's 74th confirms this: AMD sits in a higher tier.

For OpenCL-heavy applications, the Intel Arc A370M wins. Its 6.7% advantage in OpenCL, combined with a drastically lower 35 W TDP, makes it the smarter pick for laptops where power efficiency is critical. The 150 W TDP of the AMD card is a serious drawback in mobile form factors.

Consider the age difference. The AMD card launched in 2017, the Intel card in 2022. Despite the five-year gap, AMD still holds the average score advantage. This speaks to the solid fundamentals of GCN 4.0 in certain APIs. However, Intel's modern architecture brings features AMD cannot match: 8 ray tracing cores, DirectX 12 Ultimate support, and FP16 at 2:1 throughput.

Buyers who prioritize raw compute in Vulkan or need maximum memory bandwidth (217.0 GB/s) should pick the AMD Radeon Pro 570. Users who need OpenCL performance, ray tracing capability, or minimal power draw should choose the Intel Arc A370M. The Intel card also offers PCIe 4.0 connectivity, which may matter in newer systems.

The AMD card's nearest rivals are all NVIDIA mobile parts, clustering within 1.1% of its score. This suggests it competes at the level of an RTX 3050 Mobile. The Intel card's rivals are mostly AMD desktop and mobile parts from various generations, putting it in a different competitive segment. Neither card is a clear winner across all metrics; the right choice depends entirely on the target workload and platform constraints.