AMD Radeon RX 570 vs Intel Arc A350M Comparison

The AMD Radeon RX 570 and Intel Arc A350M occupy different corners of the GPU landscape: one is a mature, end-of-life desktop part from 2017, the other a mobile-first integrated chip from 2022. The recorded benchmark data shows a clear performance gap, but the architectural and feature differences matter just as much for real-world selection. Below, the database walks through where each part wins, what separates them internally, and who should choose which, strictly from the measured numbers and specifications.

Where Each One Wins

The benchmark results are unambiguous: the AMD Radeon RX 570 wins both recorded head-to-head tests, and the win margins are substantial. In Geekbench OpenCL, the RX 570 scores 32,084 against the Arc A350M’s 24,546, a 30.7% advantage. In Geekbench Vulkan, the gap widens further, with the RX 570 at 42,752 versus the Arc A350M’s 24,747, a 72.8% lead. Across all recorded tests, the RX 570 takes 2 wins, the Arc A350M takes 0.

The Arc A350M’s strengths, however, are not in raw compute throughput but in efficiency and feature set. Its 25 W TDP is dramatically lower than the RX 570’s 150 W, making it suitable for thin-and-light laptops where power draw and heat are primary constraints. The Arc A350M also supports DirectX 12 Ultimate (12_2), ray tracing cores (6 of them), and a newer process node, which the RX 570 lacks. For users prioritizing portability, battery life, or modern API features over raw frame rates, the Arc A350M offers a different trade-off, even if the benchmark data does not favor it.

Architecture Differences

The two GPUs are built on fundamentally different foundations. The RX 570 uses the Polaris 20 chip with GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. It packs 5,700 million transistors into a 232 mm² die, yielding a transistor density of 24.6M per mm². The Arc A350M, in contrast, uses the DG2-128 chip with Xe-HPG architecture, built on a 6 nm process at TSMC. It has 7,200 million transistors in a smaller 157 mm² die, achieving a much higher density of 45.9M per mm². This density advantage reflects Intel’s newer manufacturing node, but it does not translate into higher compute scores in the recorded data.

Compute resources differ sharply. The RX 570 has 2,048 shading units, 128 texture mapping units, and 32 ROPs, while the Arc A350M has 768 shading units, 48 TMUs, and 24 ROPs. The RX 570’s raw shading count is nearly three times higher, which explains its lead in OpenCL and Vulkan workloads. The Arc A350M compensates with 6 ray tracing cores, a feature the RX 570 lacks entirely, and a 2:1 FP16 ratio (6.758 TFLOPS) versus the RX 570’s 1:1 FP16 (5.095 TFLOPS), making the Intel part more capable for mixed-precision tasks.

Memory systems diverge as well. The RX 570 uses 4 GB of GDDR5 on a 256-bit bus, delivering 224.0 GB/s of bandwidth. The Arc A350M also has 4 GB, but it is GDDR6 on a 64-bit bus, yielding only 112.0 GB/s. The RX 570’s bandwidth is exactly double, a critical factor for texture-heavy and high-resolution workloads. Clock speeds tell a different story: the RX 570 boosts to 1244 MHz, while the Arc A350M boosts to 2200 MHz, but the Intel part’s higher frequency cannot overcome its fewer cores and narrower memory bus in synthetic benchmarks.

The Verdict

From the data alone, the AMD Radeon RX 570 is the clear compute winner. Its average benchmark score of 28,766 places it at the 74th percentile among all GPUs, while the Arc A350M’s average of 24,647 sits at the 70th percentile. The RX 570’s nearest rivals include the AMD Radeon RX 6800M (average 28,874, delta -0.4%) and the AMD Radeon RX 470 (average 28,996, delta -0.8%), showing it trades blows with much newer and more expensive parts. The Arc A350M’s nearest rivals are the AMD Radeon RX 590 (average 24,744, delta -0.4%) and the NVIDIA RTX A5000 Mobile (average 24,763, delta -0.5%), indicating it performs in a lower tier.

For desktop builders seeking maximum throughput in OpenCL or Vulkan, the RX 570 is the obvious pick. It is 30.7% ahead in OpenCL and 72.8% ahead in Vulkan, with no recorded test where the Arc A350M wins. For laptop buyers, though, the Arc A350M’s 25 W TDP and integrated form factor (IGP slot width) make it the only viable option in thin devices, despite its lower scores. The RX 570 is a dual-slot card requiring a 450 W PSU and a 6-pin power connector, which rules it out for portable systems. The verdict depends on context: raw performance favors AMD, but portability and modern features favor Intel.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 570 has an average benchmark score of 28,766, while the Intel Arc A350M scores 24,647, a difference of roughly 4,100 points.

Q: Does the Intel Arc A350M support ray tracing?

A: Yes, the Arc A350M has 6 ray tracing cores, while the AMD Radeon RX 570 has none listed in the database.

Q: What is the memory bandwidth difference between the two?

A: The AMD Radeon RX 570 offers 224.0 GB/s over a 256-bit bus, exactly double the 112.0 GB/s of the Arc A350M, which uses a 64-bit bus.

Q: Which GPU is more power-efficient?

A: The Intel Arc A350M has a TDP of 25 W, much lower than the AMD Radeon RX 570’s 150 W, making it better suited for laptops.

Q: In which benchmark does the AMD Radeon RX 570 have its largest lead?

A: In Geekbench Vulkan, the RX 570 scores 42,752 versus the Arc A350M’s 24,747, a 72.8% advantage.

Q: Are both GPUs still in production?

A: No, both are listed as end-of-life in the database, though the RX 570 was released in 2017 and the Arc A350M in 2022.

Head-to-Head Benchmarks

The recorded head-to-head results are sparse but decisive. In Geekbench OpenCL, the AMD Radeon RX 570 posts 32,084 points against the Arc A350M’s 24,546, a 30.7% win. This test stresses raw compute throughput across many cores, and the RX 570’s 2,048 shading units simply outmuscle the Arc’s 768. The margin is large enough that no driver or software optimization could realistically close it, given the hardware disparity.

In Geekbench Vulkan, the RX 570’s lead grows to 72.8%, scoring 42,752 versus 24,747. Vulkan is a lower-overhead API that often favors memory bandwidth and core count, both of which favor the RX 570. Its 224.0 GB/s bandwidth and 128 TMUs provide a substantial advantage in draw-call-heavy scenes, while the Arc A350M’s 112.0 GB/s and 48 TMUs lag behind. The RX 570’s pixel rate of 39.81 GPixel/s and texture rate of 159.2 GTexel/s also outpace the Arc A350M’s 52.80 GPixel/s and 105.6 GTexel/s, though the Intel part wins on pixel rate due to its higher boost clock.

The delta percentages tell the full story: a 30.7% lead in OpenCL and a 72.8% lead in Vulkan. The Arc A350M has no recorded wins in any test, and its nearest rival data suggests it is closer to the RX 590 (average 24,744) than to the RX 570. For anyone comparing these two on raw performance, the RX 570 is ahead by a wide margin, with the Vulkan gap being the standout figure.

Specification Differences

The two GPUs differ in nearly every measurable specification. The chip, architecture, and process node are entirely different: Polaris 20 on GCN 4.0 versus DG2-128 on Xe-HPG, with 14 nm versus 6 nm manufacturing. Transistor counts are 5,700 million versus 7,200 million, and die sizes are 232 mm² versus 157 mm², leading to densities of 24.6M and 45.9M per mm², respectively.

Clock speeds: the RX 570 has a base of 1168 MHz and a boost of 1244 MHz, while the Arc A350M has a base of 1150 MHz and a boost of 2200 MHz. Memory: both have 4 GB, but the RX 570 uses GDDR5 at 1750 MHz (7 Gbps effective) on a 256-bit bus, while the Arc A350M uses GDDR6 at 1750 MHz (14 Gbps effective) on a 64-bit bus. Bandwidth is 224.0 GB/s versus 112.0 GB/s.

Compute units: the RX 570 has 2,048 shading units, 128 TMUs, and 32 ROPs, while the Arc A350M has 768 shading units, 48 TMUs, and 24 ROPs. The Intel part adds 6 RT cores, which the AMD part does not have. Pixel rates are 39.81 GPixel/s versus 52.80 GPixel/s, and texture rates are 159.2 GTexel/s versus 105.6 GTexel/s. FP32 performance is 5.095 TFLOPS versus 3.379 TFLOPS, and FP16 is 5.095 TFLOPS (1:1) versus 6.758 TFLOPS (2:1).

Power and physical requirements diverge completely: the RX 570 has a 150 W TDP, a dual-slot form factor, a 6-pin power connector, a 450 W suggested PSU, and a length of 241 mm (9.5 inches). The Arc A350M has a 25 W TDP, an IGP slot width, no power connectors or suggested PSU, and is portable-device dependent. The bus interface is PCIe 3.0 x16 for the RX 570 and PCIe 4.0 x8 for the Arc A350M. Display outputs are 1x DVI, 1x HDMI 2.0b, and 3x DisplayPort 1.4a for the AMD part, while the Intel part is portable-device dependent. API support shows the Arc A350M with DirectX 12 Ultimate (12_2) and Vulkan 1.4, versus the RX 570’s DirectX 12 (12_0) and Vulkan 1.3. Release dates are 2017-04-17 for the RX 570 and 2022-03-29 for the Arc A350M, and only the RX 570 has a launch MSRP of 169 USD.