AMD Radeon R9 M375 vs Intel Arc A380 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M375 has the higher average score at 10070, while the Intel Arc A380 sits at 8558. Despite this, the Intel card wins both direct head-to-head tests by a wide margin.

Q: How much faster is the Intel Arc A380 in OpenCL performance?

A: In the geekbench_opencl test, the Intel Arc A380 scores 38224 versus the AMD Radeon R9 M375's 10457, a delta of -72.6% from the AMD card's perspective. In practical terms, the Intel card delivers roughly 3.7 times the raw compute score.

Q: Does the AMD Radeon R9 M375 support modern APIs like ray tracing?

A: No. The R9 M375 is built on GCN 1.0 architecture and supports DirectX 12 (11_1) with Vulkan 1.2.170. It has no ray tracing cores. The Intel Arc A380 uses Xe-HPG architecture with DirectX 12 Ultimate (12_2), Vulkan 1.4, and includes 8 dedicated ray tracing cores.

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

A: The AMD Radeon R9 M375 has 2 GB of DDR3 memory on a 128-bit bus with 28.80 GB/s bandwidth. The Intel Arc A380 has 6 GB of GDDR6 memory on a 96-bit bus with 186.0 GB/s bandwidth, which is over six times the memory bandwidth.

Q: Which GPU has a higher pixel fill rate?

A: The Intel Arc A380 has a pixel rate of 65.60 GPixel/s compared to the AMD Radeon R9 M375's 16.24 GPixel/s. This indicates the Intel card can fill over four times as many pixels per second, which matters for high-resolution rendering.

Q: Are both GPUs still in production?

A: No. Both are listed as end-of-life. The AMD card was released on 2015-05-04, and the Intel card followed on 2022-06-13. The AMD card's successor is Polaris Mobile, while Intel's successor is Battlemage.

Architecture Differences

The AMD Radeon R9 M375 is built on the GCN 1.0 architecture using the Tropo chip, manufactured on a 28 nm process at TSMC. It packs 1,500 million transistors into a 123 mm² die, giving a transistor density of 12.2M per mm². This is an older design from the Gem System (R9 M300) generation, and it lacks dedicated ray tracing or tensor cores entirely.

The Intel Arc A380 uses the Xe-HPG architecture with the DG2-128 chip, fabricated on a 6 nm process at the same foundry. It contains 7,200 million transistors on a 157 mm² die, resulting in a transistor density of 45.9M per mm², nearly four times denser than the AMD part. The A380 belongs to the Alchemist (Arc 3) generation and includes 8 ray tracing cores, a feature entirely absent from the R9 M375.

The compute core counts differ substantially. The AMD card has 640 shading units, 40 texture mapping units, and 16 ROPs. The Intel card offers 1024 shading units, 64 TMUs, and 32 ROPs, effectively doubling texture and pixel processing resources. Clock speeds also favor Intel: the A380 runs at a 2000 MHz base and 2050 MHz boost, while the R9 M375 sits at 1000 MHz base and 1015 MHz boost, so the Intel chip operates at roughly double the frequency.

Memory architecture is a generational leap. The R9 M375 uses 2 GB of DDR3 at 900 MHz (1800 Mbps effective) on a 128-bit bus. The A380 uses 6 GB of GDDR6 at 1937 MHz (15.5 Gbps effective) on a 96-bit bus. Despite the narrower bus, the A380 achieves 186.0 GB/s bandwidth versus 28.80 GB/s, a 6.5x advantage. Interface support also differs: AMD uses PCIe 3.0 x16, Intel uses PCIe 4.0 x8.

API support reflects the newer architecture. The R9 M375 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The Arc A380 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, adding hardware ray tracing and mesh shaders through the Ultimate feature set.

Where Each One Wins

The AMD Radeon R9 M375 wins in the aggregate benchmark average, recording 10070 versus the Intel Arc A380's 8558. This places the AMD card at the 48th percentile among all GPUs, while the Intel card sits at the 44th percentile. For users looking at overall database rankings, the R9 M375 edges ahead by roughly 18%.

However, the Intel Arc A380 wins every direct head-to-head comparison available. In geekbench_opencl, it scores 38224 versus 10457, and in geekbench_vulkan, it scores 36736 versus 9682. These are not marginal victories; the Intel card triples or quadruples the AMD card's scores in both compute-oriented tests. The A380 also dominates in theoretical throughput metrics: 4.198 TFLOPS FP32 versus 1,299.2 GFLOPS, 131.2 GTexel/s versus 40.60 GTexel/s, and 65.60 GPixel/s versus 16.24 GPixel/s.

The AMD card wins on efficiency of placement in the database's competitive landscape. Its nearest rivals are the NVIDIA Quadro K5100M (10043, +0.3%), AMD Radeon Pro 5300M (10013, +0.6%), and NVIDIA GeForce GTX 870M (9959, +1.1%), with the NVIDIA GeForce GTX 950A slightly ahead at 10273 (-2.0%). The Intel card's rivals are lower-tier: AMD FirePro W5170M (8595, -0.4%), AMD Radeon HD 8870M (8462, +1.1%), NVIDIA GeForce MX330 (8458, +1.2%), and AMD Radeon 880M (8436, +1.4%).

For legacy software that relies on older OpenGL paths or DirectX 9/10/11, the AMD card's GCN architecture may have more mature driver support. The Intel card shows variable PassMark results across DirectX versions: 73 in DirectX 9, 37 in DirectX 10, 38 in DirectX 11, and 35 in DirectX 12, suggesting inconsistent performance across API generations.

Specification Differences

| Specification | AMD Radeon R9 M375 | Intel Arc A380 |

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

| Architecture | GCN 1.0 | Xe-HPG |

| Process Node | 28 nm | 6 nm |

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

| Die Size | 123 mm² | 157 mm² |

| Transistor Density | 12.2M / mm² | 45.9M / mm² |

| Base Clock | 1000 MHz | 2000 MHz |

| Boost Clock | 1015 MHz | 2050 MHz |

| Memory Clock | 900 MHz (1800 Mbps effective) | 1937 MHz (15.5 Gbps effective) |

| Memory Size | 2 GB | 6 GB |

| Memory Type | DDR3 | GDDR6 |

| Memory Bus Width | 128 bit | 96 bit |

| Memory Bandwidth | 28.80 GB/s | 186.0 GB/s |

| Shading Units | 640 | 1024 |

| TMUs | 40 | 64 |

| ROPs | 16 | 32 |

| RT Cores | None | 8 |

| Pixel Rate | 16.24 GPixel/s | 65.60 GPixel/s |

| Texture Rate | 40.60 GTexel/s | 131.2 GTexel/s |

| FP32 | 1,299.2 GFLOPS | 4.198 TFLOPS |

| FP16 | Not specified | 8.397 TFLOPS (2:1) |

| TDP | Not specified | 75 W |

| Slot Width | Not specified | Dual-slot |

| Power Connectors | Not specified | 1x 8-pin |

| Suggested PSU | Not specified | 250 W |

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

| Display Outputs | Not specified | 1x HDMI 2.1, 3x DisplayPort 2.0 |

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

| Vulkan | 1.2.170 | 1.4 |

| Release Date | 2015-05-04 | 2022-06-13 |

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

The Intel card also has physical dimensions recorded: 222 mm length, 114 mm height, and 42 mm width. The AMD card's dimensions are not specified in the database.

Head-to-Head Benchmarks

Two direct comparisons exist between these GPUs, and the Intel Arc A380 wins both decisively.

In geekbench_opencl, the Intel Arc A380 scores 38224 against the AMD Radeon R9 M375's 10457, a delta of -72.6% when viewed from the AMD side. This means the Intel card achieves roughly 3.66 times the AMD card's OpenCL compute score. OpenCL performance often reflects raw compute throughput, and the A380's 4.198 TFLOPS FP32 versus 1,299.2 GFLOPS aligns with this gap.

In geekbench_vulkan, the Intel Arc A380 scores 36736 against 9682, a delta of -73.6%. The Intel card is about 3.79 times faster here. Vulkan performance benefits from modern architecture features, driver optimization, and higher memory bandwidth, all of which favor the A380. Its 186.0 GB/s memory bandwidth versus 28.80 GB/s is a massive factor in compute-heavy Vulkan workloads.

The aggregate benchmark scores tell a different story. The AMD Radeon R9 M375 averages 10070 across all recorded tests, while the Intel Arc A380 averages 8558. This discrepancy arises because the database includes many tests beyond the two head-to-head ones, and the AMD card's scores are more consistent across its test set. The Intel card's PassMark results are notably uneven: DirectX 9 scores 73, DirectX 10 scores 37, DirectX 11 scores 38, DirectX 12 scores 35, while G3D scores 6252 and G2D scores 610. This variability drags down its average despite strong compute results.

The nearest rival data confirms the AMD card competes in a higher average-score tier. Its closest competitor, the NVIDIA Quadro K5100M, is only 0.3% behind, and the AMD Radeon Pro 5300M is 0.6% behind. The Intel card's closest rival, the AMD FirePro W5170M, is 0.4% ahead, and the AMD Radeon HD 8870M is 1.1% behind. The Intel card's percentile ranking (44th) is below the AMD card's (48th), reflecting this difference in peer performance.

The Verdict

The data presents a clear split. If the priority is raw compute performance, modern API support, and future-proofing, the Intel Arc A380 is the unambiguous choice. It delivers roughly 3.7 times the OpenCL score, 3.8 times the Vulkan score, 3.2 times the FP32 throughput, 6.5 times the memory bandwidth, and includes hardware ray tracing. It also has 6 GB of GDDR6 memory versus 2 GB of DDR3, which matters for texture-heavy workloads and larger datasets.

If the priority is consistency within the database's overall rankings, the AMD Radeon R9 M375 holds a higher average score (10070 versus 8558) and a higher percentile (48th versus 44th). Its nearest rivals are notably stronger, including the NVIDIA Quadro K5100M and AMD Radeon Pro 5300M, whereas the Intel card competes against older or lower-tier parts like the AMD Radeon HD 8870M and NVIDIA GeForce MX330.

The Intel Arc A380 is a seven-year newer design, released in 2022 versus 2015, and it shows in every architectural metric. The 6 nm process, Xe-HPG architecture, and DirectX 12 Ultimate support represent a generational leap. However, its inconsistent PassMark results across DirectX versions suggest that legacy application performance may be uneven.

The AMD Radeon R9 M375 is a 28 nm GCN 1.0 part with no ray tracing, no FP16 support listed, and a narrow 128-bit DDR3 memory interface. It should be considered only for systems where older driver maturity and a higher aggregate score are the deciding factors. For any modern workload involving Vulkan, OpenCL compute, or DirectX 12 Ultimate features, the Intel Arc A380 is the data-backed winner. Users with ray tracing requirements have only one option here, as the AMD card lacks RT cores entirely. The Intel card's 75 W TDP, dual-slot cooler, and single 8-pin power connector also make it a practical drop-in for desktop builds, while the AMD card's power specifications are not recorded in the database.