AMD Radeon R7 350 vs Intel Arc A380 Comparison

Where Each One Wins

The benchmark data splits cleanly between these two cards, and the Intel Arc A380 wins every recorded head-to-head test. The database lists two shared benchmarks, Geekbench OpenCL and Geekbench Vulkan, and the Arc A380 takes both. There is no recorded test where the AMD Radeon R7 350 comes out ahead. That makes the use-case split simple: if the workload runs on either card, the Arc A380 is the stronger pick based on raw scores, while the R7 350 remains relevant only in scenarios where its particular feature set or physical design matters more than performance.

Look at the compute results first. In Geekbench OpenCL, the Arc A380 scores 38,224 against 7,792 for the R7 350, a delta of 390.6% in favor of Intel. In Geekbench Vulkan, the Arc A380 scores 36,736 against 7,057, a delta of 420.6%. These are not narrow margins. The Arc A380 is nearly five times faster in Vulkan compute and nearly five times faster in OpenCL compute, according to these recorded measurements. For anyone running GPU compute tasks that scale well across shading units, the Arc A380 is the obvious choice.

The R7 350 does have its own profile. It is a single-slot card with no power connectors and a 55 W TDP, which makes it a simpler drop-in for older or smaller systems. It also uses a PCIe 3.0 x16 interface, which is more universally compatible with older motherboards than the Arc A380's PCIe 4.0 x8. But those are physical and interface advantages, not performance wins. In every measured benchmark, the Arc A380 dominates.

The Arc A380's additional benchmark results, which the R7 350 lacks entirely in the database, reinforce the split. The Arc A380 records a PassMark G3D score of 6,252, a PassMark GPU Compute score of 2,762, and a 3DMark Steel Nomad DX12 score of 808. The R7 350 has no comparable entries in these tests, so the database cannot confirm how it would fare. But the absence of data does not change the conclusion: in the tests where both cards were measured, the Arc A380 wins by a wide margin.

Architecture Differences

The two cards come from different eras and different design philosophies. The Intel Arc A380 uses the DG2-128 chip built on the Xe-HPG architecture, part of the Alchemist generation (Arc 3). It is manufactured on a 6 nm process at TSMC, with 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9 million per mm². The AMD Radeon R7 350 uses the Cape Verde chip on the GCN 1.0 architecture, part of the Pirate Islands generation (R7 300). It is built on a 28 nm process at TSMC, with 1,500 million transistors on a 123 mm² die, giving a transistor density of 12.2 million per mm². The process gap is enormous: 6 nm versus 28 nm, which explains much of the performance difference and the transistor density gap.

The compute resources differ sharply. The Arc A380 has 1,024 shading units, 64 texture mapping units, 32 ROPs, and 8 ray tracing cores. The R7 350 has 512 shading units, 32 TMUs, and 16 ROPs, with no ray tracing cores at all. That is exactly double the shading units, double the TMUs, double the ROPs, and the addition of ray tracing hardware in the Arc A380. The FP32 throughput tells the same story: 4.198 TFLOPS for the Arc A380 versus 819.2 GFLOPS for the R7 350. The Arc A380 also lists FP16 at 8.397 TFLOPS (2:1), while the R7 350 has no FP16 entry.

Memory architecture is another major divider. The Arc A380 comes with 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The R7 350 has 2 GB of GDDR5 on a 128-bit bus, delivering 72.00 GB/s. The Arc A380 has three times the capacity and over 2.5 times the bandwidth, even though its bus is narrower. The memory clock difference is also notable: the Arc A380 runs at 1937 MHz with 15.5 Gbps effective, while the R7 350 runs at 1125 MHz with 4.5 Gbps effective.

API support favors the Arc A380 as well. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The R7 350 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The Arc A380's DirectX 12_2 feature level and newer Vulkan version mean it can handle modern graphics features that the R7 350 cannot, including ray tracing. The physical design also differs: the Arc A380 is a dual-slot card, 222 mm long, 114 mm tall, and 42 mm wide, with a 1x 8-pin power connector. The R7 350 is a single-slot card, 168 mm long, with no power connectors. Both share a 250 W suggested PSU.

FAQ

Q: Which card is faster in Geekbench OpenCL?

A: The Intel Arc A380 scores 38,224, while the AMD Radeon R7 350 scores 7,792. The Arc A380 is 390.6% ahead.

Q: Does the AMD Radeon R7 350 support ray tracing?

A: No. The R7 350 has no ray tracing cores listed. The Intel Arc A380 has 8 ray tracing cores.

Q: How much memory does each card have?

A: The Intel Arc A380 has 6 GB of GDDR6 on a 96-bit bus. The AMD Radeon R7 350 has 2 GB of GDDR5 on a 128-bit bus.

Q: What is the TDP of each card?

A: The Intel Arc A380 is rated at 75 W and requires a 1x 8-pin power connector. The AMD Radeon R7 350 is rated at 55 W and requires no power connectors.

Q: Which card has a higher transistor density?

A: The Intel Arc A380 has a transistor density of 45.9 million per mm², compared to 12.2 million per mm² for the AMD Radeon R7 350.

Q: Are both cards end-of-life?

A: Yes. The Intel Arc A380 was released on 2022-06-13 and is marked end-of-life. The AMD Radeon R7 350 was released on 2016-07-05 and is also marked end-of-life.

Specification Differences

The table below only lists fields where the two cards differ, based on the recorded data.

| Specification | Intel Arc A380 | AMD Radeon R7 350 |

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

| Chip | DG2-128 | Cape Verde |

| Architecture | Xe-HPG | GCN 1.0 |

| Generation | Alchemist (Arc 3) | Pirate Islands (R7 300) |

| Process node | 6 nm | 28 nm |

| Transistors | 7,200 million | 1,500 million |

| Die size | 157 mm² | 123 mm² |

| Transistor density | 45.9M / mm² | 12.2M / mm² |

| Memory clock | 1937 MHz, 15.5 Gbps effective | 1125 MHz, 4.5 Gbps effective |

| Memory size | 6 GB | 2 GB |

| Memory type | GDDR6 | GDDR5 |

| Memory bus | 96 bit | 128 bit |

| Memory bandwidth | 186.0 GB/s | 72.00 GB/s |

| Shading units | 1024 | 512 |

| TMUs | 64 | 32 |

| ROPs | 32 | 16 |

| Ray tracing cores | 8 | None |

| Pixel rate | 65.60 GPixel/s | 12.80 GPixel/s |

| Texture rate | 131.2 GTexel/s | 25.60 GTexel/s |

| FP32 | 4.198 TFLOPS | 819.2 GFLOPS |

| FP16 | 8.397 TFLOPS (2:1) | None |

| TDP | 75 W | 55 W |

| Slot width | Dual-slot | Single-slot |

| Power connectors | 1x 8-pin | None |

| Bus interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| Display outputs | 1x HDMI 2.1, 3x DisplayPort 2.0 | 1x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 |

| DirectX | 12 Ultimate (12_2) | 12 (11_1) |

| Vulkan | 1.4 | 1.2.170 |

| Length | 222 mm (8.7 inches) | 168 mm (6.6 inches) |

| Release date | 2022-06-13 | 2016-07-05 |

| Predecessor | Xe Graphics | Volcanic Islands |

| Successor | Battlemage | Arctic Islands |

| Launch MSRP | 149 USD | None |

Head-to-Head Benchmarks

The database records two shared benchmarks between the Intel Arc A380 and the AMD Radeon R7 350. The Arc A380 wins both, and the margins are extreme.

In Geekbench OpenCL, the Arc A380 scores 38,224. The R7 350 scores 7,792. That is a delta of 390.6% in favor of the Arc A380. For context, the Arc A380's nearest rival in the database by average score is the AMD FirePro W5170M at 8,595, a delta of -0.4%, meaning the Arc A380 is essentially tied with that mobile workstation card. The R7 350's nearest rival by average score is the Intel UHD Graphics 750 at 7,441, a delta of -0.2%. The Arc A380's OpenCL score is roughly five times the R7 350's, which places it in a completely different performance class.

In Geekbench Vulkan, the Arc A380 scores 36,736. The R7 350 scores 7,057. That is a delta of 420.6%. This is the single largest margin in the head-to-head set. The Arc A380's Vulkan score is more than five times the R7 350's. Even the Arc A380's own nearest rivals, which sit within 1.4% of its average score, do not approach this level of separation from the R7 350.

Beyond the shared tests, the Arc A380 has additional benchmark entries that the R7 350 lacks. The Arc A380 records a PassMark G3D score of 6,252, a PassMark GPU Compute score of 2,762, a 3DMark Steel Nomad DX12 score of 808, and PassMark DirectX scores of 73 (DX9), 38 (DX11), 37 (DX10), and 35 (DX12). Its PassMark G2D score is 610. The R7 350 has no entries for any of these tests, so a direct comparison is not possible. But the pattern from the shared tests is unambiguous: the Arc A380's compute and graphics throughput dwarf the R7 350's.

The average benchmark scores in the database reinforce the verdict. The Arc A380 has an average benchmark score of 8,558 and sits at the 44th percentile of all GPUs. The R7 350 has an average benchmark score of 7,425 and sits at the 40th percentile. The Arc A380 is 15.3% higher in average score, even though its nearest rivals cluster tightly around it: the FirePro W5170M at 8,595 (-0.4%), the Radeon HD 8870M at 8,462 (+1.1%), the GeForce MX330 at 8,458 (+1.2%), and the Radeon 880M at 8,436 (+1.4%). The R7 350's nearest rivals are the UHD Graphics 750 at 7,441 (-0.2%), the Radeon HD 8850M at 7,447 (-0.3%), the GeForce GTX 1650 at 7,472 (-0.6%), and the Arc A310 at 7,550 (-1.7%). The two cards do not even compete in the same neighborhood.

The Verdict

The data points to one conclusion: the Intel Arc A380 is the faster card in every measured category. It wins both shared benchmarks by margins of 390.6% and 420.6%. It has double the shading units, double the TMUs, double the ROPs, and adds ray tracing hardware. It has 6 GB of GDDR6 memory against 2 GB of GDDR5, and it delivers 186.0 GB/s of bandwidth against 72.00 GB/s. Its FP32 throughput of 4.198 TFLOPS is over five times the R7 350's 819.2 GFLOPS. Its average benchmark score is 8,558 against 7,425, and its 44th percentile rank beats the R7 350's 40th.

Who should pick the Intel Arc A380? Anyone who wants the higher-performing GPU, has a PCIe 4.0 x8 slot, can accommodate a dual-slot 222 mm card with a 1x 8-pin power connector, and wants modern API support including DirectX 12 Ultimate and Vulkan 1.4. The launch MSRP is 149 USD. The card also has a successor, Battlemage, and its predecessor is Xe Graphics.

Who should pick the AMD Radeon R7 350? The case is narrower. It is a single-slot card with no power connectors, a 55 W TDP, and a 168 mm length, which makes it easier to install in compact or legacy systems. It uses PCIe 3.0 x16, which works with older motherboards without issue. It also has a DVI output, which the Arc A380 lacks. But the performance gap is so large that these physical advantages only matter for very specific builds where space, power delivery, or display output compatibility outweigh speed. The R7 350's predecessor is Volcanic Islands and its successor is Arctic Islands, but the recorded data shows it is firmly outclassed by the Arc A380 in compute and graphics workloads.