Intel Arc A380E x2 vs Intel Arc Pro B390 Comparison

FAQ

Q: What are the core architectural differences between the Intel Arc A380E x2 and the Intel Arc Pro B390?

A: The A380E x2 uses the DG2-128 chip based on the Xe-HPG architecture from the Alchemist generation, built on a 6 nm process at TSMC. The Pro B390 uses the Panther Lake chip based on the Xe3-LPG architecture from the Arc Graphics-WM generation, built on a 3 nm process at Intel.

Q: How do the two GPUs compare in terms of memory configuration?

A: The A380E x2 has 6 GB of dedicated GDDR6 memory on a 96-bit bus with 186.0 GB/s bandwidth. The Pro B390 uses System Shared memory, with bandwidth listed as System Dependent and no dedicated VRAM.

Q: Which GPU has higher FP32 compute performance?

A: The Pro B390 delivers 7.680 TFLOPS FP32, which is 87.5% higher than the A380E x2's 4.096 TFLOPS. The Pro B390 also leads in FP16 with 15.36 TFLOPS versus 8.192 TFLOPS.

Q: What are the physical form factor differences?

A: The A380E x2 is a single-slot discrete card measuring 265 mm in length, 127 mm in height, and 20 mm in width, requiring a 1x 6-pin power connector and a 300 W suggested PSU. The Pro B390 is an IGP (integrated graphics processor) with no power connectors and dimensions listed as not applicable.

Q: How do the GPU clock speeds compare?

A: The A380E x2 has a base and boost clock of 2000 MHz with memory clocked at 1937 MHz (15.5 Gbps effective). The Pro B390 has a 300 MHz base clock and a 2500 MHz boost clock, with system shared memory.

Q: What is the production status of each GPU?

A: The A380E x2 is listed as end-of-life and was released on 2024-03-31. The Pro B390 is listed as active and was released on 2026-01-26.

Architecture Differences

The two Intel GPUs represent distinctly different architectural generations and implementation strategies. The Intel Arc A380E x2 is built on the DG2-128 chip, which uses the Xe-HPG architecture from the Alchemist generation, specifically the Arc 3 tier. This is a discrete GPU design manufactured on a 6 nm process at TSMC, containing 7,200 million transistors on a 157 mm² die, resulting in a transistor density of 45.9M per mm². The chip is a mature Alchemist design that has reached end-of-life status, with its predecessor being Xe Graphics and its successor being Battlemage.

The Intel Arc Pro B390 uses the Panther Lake chip, based on the Xe3-LPG architecture from the Arc Graphics-WM generation. This is a fundamentally newer design manufactured on a 3 nm process at Intel's own foundry. The database does not record transistor count, die size, or transistor density for this chip, indicating that these details may not have been disclosed or measured at the time of data collection. The Pro B390 is an integrated graphics processor (IGP), meaning it shares system memory and is designed to be embedded within a portable device rather than installed as a discrete card.

The architectural differences extend to the execution resources. The A380E x2 has 1,024 shading units, 64 texture mapping units, and 32 raster output units, along with 8 ray tracing cores. The Pro B390 has 1,536 shading units, which is 50% more, but fewer TMUs at 48 and fewer ROPs at 24. It has 12 ray tracing cores, a 50% increase over the A380E x2. This configuration suggests the Pro B390 prioritizes compute and ray tracing throughput over texture and pixel processing.

The A380E x2 uses a PCIe 4.0 x8 bus interface, while the Pro B390 uses an IGP bus interface, meaning it communicates directly with the system rather than through a PCIe slot. The display outputs also differ significantly: the A380E x2 provides 8x mini-DisplayPort 2.0 connections, while the Pro B390's display outputs are listed as Portable Device Dependent, reflecting its integration into mobile or compact systems.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so the API feature set is identical. The power characteristics differ substantially, with the A380E x2 rated at 130 W TDP requiring external power, while the Pro B390 is rated at 80 W TDP with no power connectors needed.

Head-to-Head Benchmarks

The database records no head-to-head benchmark results between the Intel Arc A380E x2 and the Intel Arc Pro B390, and neither GPU has individual benchmark scores or nearest rival data in the records. The wins tally shows zero for both sides. Without measured performance data, the analysis must rely on the architectural and specification differences recorded in the database.

The most significant computed advantage for the Pro B390 lies in raw compute throughput. Its FP32 rating of 7.680 TFLOPS represents an 87.5% increase over the A380E x2's 4.096 TFLOPS. In FP16, the Pro B390's 15.36 TFLOPS is also 87.5% higher than the 8.192 TFLOPS of the A380E x2. These figures indicate that for compute-heavy workloads such as machine learning inference, scientific simulation, or general-purpose GPU computing, the Pro B390 should deliver substantially higher throughput per clock cycle, assuming the architectural efficiency is comparable.

The A380E x2 counters in the rasterization and texture processing domains. Its pixel rate of 64.00 GPixel/s exceeds the Pro B390's 60.00 GPixel/s by 6.7%. Its texture rate of 128.0 GTexel/s exceeds the Pro B390's 120.0 GTexel/s by 6.7%. These margins are modest but consistent, suggesting that the A380E x2 maintains a slight edge in traditional graphics rasterization workloads where pixel fill and texture filtering are the primary bottlenecks.

Memory bandwidth favors the A380E x2 decisively. The discrete card provides 186.0 GB/s of dedicated GDDR6 bandwidth, whereas the Pro B390 depends on system shared memory with bandwidth listed as System Dependent. In practice, integrated graphics typically achieve lower effective memory bandwidth than dedicated VRAM due to contention with the CPU and other system components. The A380E x2's 6 GB of dedicated memory also provides a predictable capacity for graphics workloads, while the Pro B390's shared memory allocation depends entirely on the host system configuration.

Clock behavior differs in a way that could affect real-world performance. The A380E x2 maintains a constant 2000 MHz base and boost clock, meaning its performance envelope is predictable under sustained load. The Pro B390 has a 300 MHz base clock and a 2500 MHz boost clock, a wide dynamic range that suggests aggressive power management. Under sustained heavy loads, the Pro B390 may not sustain its maximum boost clock indefinitely, potentially narrowing the compute advantage in extended workloads.

The thermal and power constraints further shape the comparison. The A380E x2 has a 130 W TDP and requires a 300 W suggested PSU, while the Pro B390 has an 80 W TDP and requires no external power. For systems with strict power budgets, the Pro B390's lower power draw may allow it to maintain higher sustained clocks in a thermally constrained chassis, while the A380E x2's higher power envelope could enable consistent performance in a desktop with adequate cooling.

Specification Differences

| Specification | Intel Arc A380E x2 | Intel Arc Pro B390 |

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

| Chip | DG2-128 | Panther Lake |

| Architecture | Xe-HPG | Xe3-LPG |

| Generation | Alchemist (Arc 3) | Arc Graphics-WM (Panther Lake) |

| Process Node | 6 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 7,200 million | Unknown |

| Die Size | 157 mm² | Unknown |

| Transistor Density | 45.9M / mm² | Not recorded |

| Base Clock | 2000 MHz | 300 MHz |

| Boost Clock | 2000 MHz | 2500 MHz |

| Memory Clock | 1937 MHz (15.5 Gbps effective) | System Shared |

| Memory Size | 6 GB GDDR6 | System Shared |

| Memory Bus Width | 96 bit | System Shared |

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

| Shading Units | 1024 | 1536 |

| TMUs | 64 | 48 |

| ROPs | 32 | 24 |

| Ray Tracing Cores | 8 | 12 |

| Pixel Rate | 64.00 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 128.0 GTexel/s | 120.0 GTexel/s |

| FP32 | 4.096 TFLOPS | 7.680 TFLOPS |

| FP16 | 8.192 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 130 W | 80 W |

| Slot Width | Single-slot | IGP |

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

| Suggested PSU | 300 W | Not recorded |

| Bus Interface | PCIe 4.0 x8 | IGP |

| Display Outputs | 8x mini-DisplayPort 2.0 | Portable Device Dependent |

| Dimensions | 265 mm x 127 mm x 20 mm | Not recorded |

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

| Release Date | 2024-03-31 | 2026-01-26 |

| Predecessor | Xe Graphics | HD Graphics-WM |

| Successor | Battlemage | Not recorded |

The Verdict

The database presents two GPUs with fundamentally different design philosophies and target use cases. The Intel Arc A380E x2 is a discrete, end-of-life Alchemist card with dedicated memory and a fixed power envelope. The Intel Arc Pro B390 is an active, integrated Panther Lake GPU designed for portable devices with shared system memory and minimal power requirements.

For compute-intensive workloads, the data favors the Pro B390. Its FP32 throughput of 7.680 TFLOPS is 87.5% higher than the A380E x2's 4.096 TFLOPS, and its FP16 rating follows the same proportional advantage. The 50% increase in shading units and 50% increase in ray tracing cores reinforce this direction. Users running general-purpose GPU compute, ray-traced rendering, or AI inference should expect the Pro B390 to deliver meaningfully higher throughput, provided the host system can supply sufficient memory bandwidth and the integrated GPU can sustain its 2500 MHz boost clock.

For traditional rasterized graphics with predictable memory requirements, the A380E x2 has structural advantages. Its 186.0 GB/s dedicated GDDR6 bandwidth is not subject to system contention, its 6 GB VRAM is a fixed resource that does not compete with the CPU, and its pixel rate of 64.00 GPixel/s and texture rate of 128.0 GTexel/s both exceed the Pro B390's corresponding figures. The constant 2000 MHz clock also means no boost variability under load. These characteristics make the A380E x2 a steadier choice for sustained graphics rendering where memory bandwidth is the limiting factor.

The power and form factor data point to different deployment scenarios. The A380E x2 is a single-slot card requiring a 6-pin connector and a 300 W PSU, suited to desktop systems with available expansion slots and power headroom. The Pro B390 draws 80 W, requires no power connectors, and is integrated into the system, making it appropriate for compact, portable, or power-constrained devices where the 3 nm process and lower TDP are decisive advantages.

The production status is a practical consideration. The A380E x2 is end-of-life with a successor named as Battlemage, while the Pro B390 is active with no successor recorded. For new system designs, the Pro B390 represents the currently supported path in Intel's lineup.

The verdict depends on the workload priority. The Pro B390 is the compute-oriented choice with superior FP32, FP16, shading unit count, and ray tracing resources, all within an 80 W envelope. The A380E x2 is the memory-oriented choice with dedicated VRAM, higher bandwidth, and slightly better pixel and texture throughput, but it carries a 130 W TDP and has reached end-of-life status. Benchmark data is not yet recorded for either GPU, so these conclusions derive entirely from the specification-level differences in the database.