Intel Arc A380E x2 vs Intel Arc Graphics 24EU Comparison

Intel Arc A380E x2 and Intel Arc Graphics 24EU occupy opposite ends of the integrated and discrete graphics spectrum, yet both carry the Arc branding. The A380E x2 is a dual-GPU configuration built on the DG2-128 chip, while the 24EU is an integrated graphics processor embedded in the Arrow Lake-S die. The recorded data shows a substantial performance gulf, but the comparison reveals more than just a raw speed difference.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two parts. The only available measurement for the Intel Arc Graphics 24EU is a 3DMark Steel Nomad DX12 score of 733. That score places the 24EU at the 3rd percentile of all GPUs in the database, indicating it sits near the very bottom of the performance distribution.

The Arc A380E x2 has no recorded benchmark scores in the database, so a direct numerical comparison is not possible from the recorded data. What can be established is the theoretical compute ceiling. The A380E x2 delivers 4.096 TFLOPS of FP32 throughput per GPU, while the 24EU manages 768.0 GFLOPS. That is a 5.33x difference in raw shader throughput, assuming both are running at their respective boost clocks.

The nearest rivals for the 24EU provide context for its standing. The Intel Arc Graphics 32EU and 64EU both score exactly 733, a 0% delta. The AMD Radeon HD 6470M scores 723, which is 1.4% lower than the 24EU. The NVIDIA GeForce GT 415M scores 751, putting it 2.4% above the 24EU. These rivals are all low-end or legacy parts, which reinforces the 24EU's position in the lowest performance tier.

The A380E x2 configuration, with two DG2-128 chips, would theoretically double the resources of a single A380E. Each chip provides 1024 shading units, 64 TMUs, and 32 ROPs. Across two GPUs, that would sum to 2048 shading units, 128 TMUs, and 64 ROPs. The 24EU, by contrast, offers 192 shading units, 12 TMUs, and 6 ROPs. The resource disparity is massive, though the A380E x2's dual-GPU topology would require software support to scale efficiently.

Architecture Differences

The two parts use different architectures, process nodes, and chip designs. The A380E x2 is built on Xe-HPG architecture under the Alchemist generation, specifically the Arc 3 tier. The 24EU uses Xe-LPG architecture under the Arc Graphics (Arrow Lake) generation. Both are Intel designs, but the underlying GPU microarchitectures are distinct.

The process nodes differ sharply. The A380E x2 uses TSMC's 6 nm process, while the 24EU uses TSMC's 3 nm process. The 24EU's die is the Arrow Lake-S package, which contains 17,800 million transistors across 243 mm². The A380E's DG2-128 chip contains 7,200 million transistors on a 157 mm² die. Transistor density favors the newer process: 73.3M transistors per mm² for the 24EU's die versus 45.9M for the DG2-128. The A380E x2 configuration uses two separate chips, so the total transistor count across both GPUs would be 14,400 million, still below the 24EU's integrated die, but the comparison is not apples-to-apples because the Arrow Lake-S die also contains CPU cores.

Clock behavior differs substantially. The A380E x2 runs at a fixed 2000 MHz base and boost clock. The 24EU has a 300 MHz base clock and a 2000 MHz boost clock. The wide clock range on the 24EU indicates aggressive power management, ramping up only under load. The A380E x2's constant 2000 MHz suggests it is designed to sustain full speed continuously.

Memory architecture is a defining difference. The A380E x2 uses 6 GB of GDDR6 per GPU on a 96-bit bus, delivering 186.0 GB/s of bandwidth per chip. The 24EU uses system shared memory, with bandwidth listed as system dependent. The discrete memory on the A380E x2 provides dedicated bandwidth that does not compete with CPU memory traffic, while the 24EU must share the system memory controller.

Ray tracing support also separates them. The A380E x2 includes 8 ray tracing cores per GPU. The 24EU lists no ray tracing cores. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical, but hardware ray tracing capability is exclusive to the A380E x2 in this comparison.

Where Each One Wins

The A380E x2 wins on every measurable compute and graphics resource category. It has more shading units, more TMUs, more ROPs, dedicated memory, ray tracing hardware, and a higher fixed clock. Its pixel rate is 64.00 GPixel/s per GPU, compared to 12.00 GPixel/s for the 24EU. Texture rate is 128.0 GTexel/s per GPU versus 24.00 GTexel/s. These are 5.33x advantages in both rasterization throughput categories, mirroring the FP32 difference.

The 24EU wins in power efficiency at the package level. Its TDP is 65 W, while the A380E x2 is rated at 130 W per GPU. A dual-GPU configuration would draw 260 W total, four times the 24EU's power envelope. The 24EU also requires no power connectors and no additional slot width, as it is an integrated processor. The A380E x2 needs a 1x 6-pin power connector per GPU and occupies a single slot per card.

The 24EU wins on process technology. The 3 nm node with 73.3M transistors per mm² represents a newer manufacturing generation than the 6 nm node used by the A380E x2. This does not translate into performance advantages in the recorded data, but it indicates the 24EU benefits from a more advanced fabrication process.

The 24EU also wins on availability. Its production status is active, while the A380E x2 is end-of-life. The 24EU was released on 2024-10-23, and the A380E was released on 2024-03-31. For new system designs, the 24EU is the only one of the two still in production.

The Verdict

The data indicates the Intel Arc A380E x2 is the far more capable graphics solution. Its FP32 throughput of 4.096 TFLOPS per GPU, dedicated 6 GB GDDR6 memory per GPU, and ray tracing hardware place it in a different performance class than the 24EU. The 24EU's 768.0 GFLOPS and 3rd percentile ranking confirm it is positioned at the entry level of the GPU performance spectrum.

The 24EU is suitable for systems where the GPU is a secondary consideration. Its 65 W TDP, integrated form factor, and shared memory architecture make it a low-power option for basic display output and light graphics workloads. The 3rd percentile score of 733 in 3DMark Steel Nomad DX12 puts it in the same bracket as the Arc Graphics 32EU and 64EU, with a 0% delta, and just 1.4% above the AMD Radeon HD 6470M.

The A380E x2 is the choice for workloads that demand sustained graphics throughput. Its fixed 2000 MHz clock, dedicated memory bandwidth of 186.0 GB/s per GPU, and 8 ray tracing cores per GPU provide the hardware foundation for more demanding rendering tasks. The end-of-life production status is a practical consideration, but the recorded specifications show it is the stronger performer by every compute metric.

The power requirement is the primary trade-off. The A380E x2's 130 W TDP per GPU, 300 W suggested PSU, and 1x 6-pin power connector per GPU represent a significant system integration cost. The 24EU's 65 W TDP and zero additional power requirements make it nearly free to integrate into an Arrow Lake-S platform.

FAQ

Q: How does the Intel Arc Graphics 24EU compare to its nearest rivals in the database?

A: The 24EU scores 733 in 3DMark Steel Nomad DX12, matching the Intel Arc Graphics 32EU and 64EU exactly (0% delta). It is 1.4% faster than the AMD Radeon HD 6470M (723) and 2.4% slower than the NVIDIA GeForce GT 415M (751).

Q: Does the Intel Arc A380E x2 support ray tracing?

A: Yes. The A380E x2 includes 8 ray tracing cores per DG2-128 chip. The Intel Arc Graphics 24EU lists no ray tracing cores.

Q: What memory does each GPU use?

A: The A380E x2 uses 6 GB of GDDR6 per GPU on a 96-bit bus with 186.0 GB/s bandwidth per GPU. The 24EU uses system shared memory with system dependent bandwidth.

Q: Are both GPUs based on the same architecture?

A: No. The A380E x2 uses Xe-HPG architecture (Alchemist, Arc 3 generation). The 24EU uses Xe-LPG architecture (Arc Graphics, Arrow Lake generation).

Q: Which GPU has the higher clock speed?

A: Both have a 2000 MHz boost clock. The A380E x2 also has a 2000 MHz base clock, while the 24EU has a 300 MHz base clock.

Q: What is the power consumption difference?

A: The A380E x2 is rated at 130 W TDP per GPU with a 300 W suggested PSU. The 24EU is rated at 65 W TDP and requires no power connectors.

Specification Differences

| Specification | Intel Arc A380E x2 | Intel Arc Graphics 24EU |

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

| Architecture | Xe-HPG | Xe-LPG |

| Generation | Alchemist (Arc 3) | Arc Graphics (Arrow Lake) |

| Process Node | 6 nm | 3 nm |

| Transistors | 7,200 million | 17,800 million |

| Die Size | 157 mm² | 243 mm² |

| Transistor Density | 45.9M / mm² | 73.3M / mm² |

| Base Clock | 2000 MHz | 300 MHz |

| Memory | 6 GB GDDR6 | System Shared |

| Memory Bus | 96 bit | System Shared |

| Memory Bandwidth | 186.0 GB/s | System Dependent |

| Shading Units | 1024 | 192 |

| TMUs | 64 | 12 |

| ROPs | 32 | 6 |

| Ray Tracing Cores | 8 | None |

| Pixel Rate | 64.00 GPixel/s | 12.00 GPixel/s |

| Texture Rate | 128.0 GTexel/s | 24.00 GTexel/s |

| FP32 | 4.096 TFLOPS | 768.0 GFLOPS |

| FP16 | 8.192 TFLOPS (2:1) | 1.536 TFLOPS (2:1) |

| TDP | 130 W | 65 W |

| Slot Width | Single-slot | IGP |

| Power Connectors | 1x 6-pin | None |

| Suggested PSU | 300 W | None |

| Bus Interface | PCIe 4.0 x8 | Ring Bus |

| Display Outputs | 8x mini-DisplayPort 2.0 | Motherboard Dependent |

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

| Release Date | 2024-03-31 | 2024-10-23 |

| Predecessor | Xe Graphics | HD Graphics |

| Successor | Battlemage | None |