AMD Steam Deck OLED GPU vs Intel Arc A380E Comparison

Head-to-Head Benchmarks

The database records no direct benchmark scores for either the AMD Steam Deck OLED GPU or the Intel Arc A380E. Both entries show an average benchmark score of zero, and the head-to-head benchmark table is empty. Consequently, there are no measured wins for either side in this comparison. The absence of recorded data means that any performance assessment must be derived from the architectural specifications and compute characteristics listed in the database, rather than from empirical test results.

Both GPUs sit at the 50th percentile among all GPUs in the database, indicating that they are positioned near the midpoint of the performance distribution. This percentile ranking is based on the aggregate performance of all recorded GPUs, and with no benchmark scores available for either item, the percentile figure likely reflects their specification-based classification rather than any measured outcomes.

The AMD Steam Deck OLED GPU delivers a peak FP32 throughput of 1.638 TFLOPS, while the Intel Arc A380E reaches 4.096 TFLOPS. This translates to the Intel part offering 2.5 times the single-precision compute throughput of the AMD part. In FP16 calculations, the Intel GPU achieves 8.192 TFLOPS through a 2:1 ratio, compared to the AMD GPU's 3.277 TFLOPS, again a 2.5-fold difference. These figures indicate that the Intel Arc A380E has a substantial raw compute advantage in both precision formats.

Pixel throughput follows the same pattern. The Intel Arc A380E renders at 64.00 GPixel/s, which is exactly 2.5 times the 25.60 GPixel/s of the AMD Steam Deck OLED GPU. Texture fill rates show the identical ratio: 128.0 GTexel/s for Intel versus 51.20 GTexel/s for AMD. These consistent 2.5x ratios across FP32, FP16, pixel, and texture throughput suggest that the architectural scaling between the two parts is uniform, which is expected given that the Intel GPU has exactly double the shading units (1024 versus 512), double the texture mapping units (64 versus 32), and double the render output units (32 versus 16).

Architecture Differences

The two GPUs come from different architectural families. The AMD Steam Deck OLED GPU uses the RDNA 2.0 architecture, built on the Sephiroth chip. The Intel Arc A380E employs the Xe-HPG architecture, based on the DG2-128 chip. Both are fabricated on a 6 nm process at TSMC, but the transistor counts differ significantly. The AMD chip contains 2,400 million transistors on a 131 mm² die, yielding a transistor density of 18.3 million transistors per square millimeter. The Intel chip packs 7,200 million transistors onto a 157 mm² die, achieving a density of 45.9 million transistors per square millimeter. This means the Intel die is approximately 20% larger in area but holds three times the transistor count, resulting in a 2.5 times higher transistor density.

The memory subsystems are fundamentally different. The AMD GPU uses 16 GB of LPDDR5 memory on a 128-bit bus, operating at an effective data rate of 11 Gbps and delivering 176.0 GB/s of bandwidth. The Intel GPU uses 6 GB of GDDR6 memory on a 96-bit bus, running at 15.5 Gbps effective and providing 186.0 GB/s of bandwidth. Despite the narrower bus width, the Intel part achieves slightly higher memory bandwidth due to the faster memory clock. However, the AMD part offers nearly three times the memory capacity.

Ray tracing hardware is present in both GPUs, with each featuring 8 ray tracing cores. The API support differs in the Vulkan version: the AMD GPU supports Vulkan 1.3 while the Intel GPU supports Vulkan 1.4. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6.

The physical characteristics diverge considerably. The AMD Steam Deck OLED GPU has a TDP of 15 W and uses a USB Type-C display output. The Intel Arc A380E has a TDP of 75 W, occupies a single slot, requires no power connectors, and suggests a 250 W power supply. The Intel card uses a PCIe 4.0 x8 bus interface and provides four DisplayPort 2.0 outputs. The AMD GPU's production status is listed as Active, while the Intel part is marked as End-of-life.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The Intel Arc A380E delivers 4.096 TFLOPS of FP32 performance, which is 2.5 times the 1.638 TFLOPS of the AMD Steam Deck OLED GPU. The same 2.5x advantage applies to FP16 throughput, where Intel achieves 8.192 TFLOPS versus AMD's 3.277 TFLOPS.

Q: How do the memory configurations compare?

A: The AMD Steam Deck OLED GPU offers 16 GB of LPDDR5 memory on a 128-bit bus with 176.0 GB/s bandwidth. The Intel Arc A380E provides 6 GB of GDDR6 memory on a 96-bit bus with 186.0 GB/s bandwidth. The AMD part has significantly more capacity, while the Intel part has slightly higher bandwidth.

Q: What is the transistor density difference?

A: The Intel DG2-128 chip packs 7,200 million transistors into a 157 mm² die, yielding 45.9 million transistors per square millimeter. The AMD Sephiroth chip contains 2,400 million transistors on a 131 mm² die, giving a density of 18.3 million per square millimeter. Intel's density is 2.5 times higher.

Q: Do both GPUs support hardware ray tracing?

A: Yes, both GPUs include 8 ray tracing cores. They also both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Intel GPU supports Vulkan 1.4, while the AMD GPU supports Vulkan 1.3.

Q: What are the power requirements for each GPU?

A: The AMD Steam Deck OLED GPU has a TDP of 15 W. The Intel Arc A380E has a TDP of 75 W, requires no external power connectors, and suggests a 250 W power supply.

Q: Which GPU has more display outputs?

A: The Intel Arc A380E provides four DisplayPort 2.0 outputs. The AMD Steam Deck OLED GPU provides a single USB Type-C output.

Specification Differences

| Specification | AMD Steam Deck OLED GPU | Intel Arc A380E |

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

| Architecture | RDNA 2.0 | Xe-HPG |

| Process Node | 6 nm | 6 nm |

| Transistors | 2,400 million | 7,200 million |

| Die Size | 131 mm² | 157 mm² |

| Transistor Density | 18.3M / mm² | 45.9M / mm² |

| Base Clock | 1000 MHz | 2000 MHz |

| Boost Clock | 1600 MHz | 2000 MHz |

| Memory Size | 16 GB | 6 GB |

| Memory Type | LPDDR5 | GDDR6 |

| Memory Bus Width | 128 bit | 96 bit |

| Memory Bandwidth | 176.0 GB/s | 186.0 GB/s |

| Memory Clock | 1375 MHz, 11 Gbps effective | 1937 MHz, 15.5 Gbps effective |

| Shading Units | 512 | 1024 |

| TMUs | 32 | 64 |

| ROPs | 16 | 32 |

| Pixel Rate | 25.60 GPixel/s | 64.00 GPixel/s |

| Texture Rate | 51.20 GTexel/s | 128.0 GTexel/s |

| FP32 | 1.638 TFLOPS | 4.096 TFLOPS |

| FP16 | 3.277 TFLOPS (2:1) | 8.192 TFLOPS (2:1) |

| TDP | 15 W | 75 W |

| Slot Width | Not specified | Single-slot |

| Power Connectors | Not specified | None |

| Suggested PSU | Not specified | 250 W |

| Bus Interface | Not specified | PCIe 4.0 x8 |

| Display Outputs | 1x USB Type-C | 4x DisplayPort 2.0 |

| Vulkan Version | 1.3 | 1.4 |

| Dimensions | 298 mm x 117 mm x 49 mm | 254 mm x 127 mm x 20 mm |

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

| Release Date | 2023-11-08 | 2024-03-31 |

| Predecessor | Not specified | Xe Graphics |

| Successor | Not specified | Battlemage |

Where Each One Wins

The Intel Arc A380E wins decisively in every measured compute and throughput category. Its FP32 output of 4.096 TFLOPS is 2.5 times the AMD part, and the same ratio applies to FP16, pixel fill, and texture fill rates. The Intel GPU also has double the shading units, TMUs, and ROPs, which directly explains the throughput advantage. Its memory bandwidth of 186.0 GB/s edges out the AMD part's 176.0 GB/s, and it operates at a higher base and boost clock of 2000 MHz versus 1000 MHz and 1600 MHz respectively. The Intel GPU also provides four display outputs, supports the newer Vulkan 1.4 API, and offers a denser transistor layout on a slightly larger die.

The AMD Steam Deck OLED GPU wins on memory capacity with 16 GB versus 6 GB, which is a 2.67 times advantage. This capacity difference is substantial for workloads that require large frame buffers or data sets that exceed 6 GB. The AMD part also consumes considerably less power at 15 W versus 75 W, making it more suitable for power-constrained environments. Its physical dimensions are larger in length and width but thicker, while the Intel card is longer but thinner. The AMD GPU remains in active production, whereas the Intel part is end-of-life. The AMD GPU also has a wider memory bus at 128 bit compared to Intel's 96 bit, and it uses LPDDR5 memory rather than GDDR6.

The Verdict

Based strictly on the recorded specifications, the Intel Arc A380E is the higher-performing GPU in raw compute and throughput metrics. Its 2.5x advantage in FP32, FP16, pixel rate, and texture rate, combined with double the shading units, TMUs, and ROPs, makes it the clear choice for workloads that depend on those capabilities. Higher clock speeds, greater memory bandwidth, and support for Vulkan 1.4 further reinforce its position.

The AMD Steam Deck OLED GPU is the appropriate selection when memory capacity is the limiting factor. Its 16 GB of LPDDR5 memory is more than double the Intel part's 6 GB, which matters for applications that require large working sets. Its 15 W power draw is one-fifth of the Intel GPU's 75 W, making it suitable for low-power systems. Its active production status also indicates continued availability.

The data shows a clear dichotomy: the Intel Arc A380E for compute-heavy and throughput-sensitive tasks, and the AMD Steam Deck OLED GPU for capacity-focused and power-sensitive scenarios. Neither GPU has recorded benchmark scores, so these conclusions rest entirely on the architectural specifications in the database. The 50th percentile ranking for both GPUs places them on equal footing in the overall distribution, but the specification analysis reveals that their strengths lie in different areas.