Intel Arc Pro B390 vs Intel Data Center GPU Max 1550 Comparison

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark results between the Intel Arc Pro B390 and the Intel Data Center GPU Max 1550. Both products hold a percentile rank of 50 against all GPUs in the database, and neither has an average benchmark score recorded. Without direct performance measurements, the comparison must rely on the architectural and specification data available.

The raw compute figures show a substantial gap in peak throughput. The Data Center GPU Max 1550 delivers 52.43 TFLOPS of FP32 performance, while the Arc Pro B390 produces 7.680 TFLOPS. That places the Max 1550 approximately 6.8 times higher in raw single-precision compute. The FP16 comparison follows a similar pattern: the Max 1550 achieves 52.43 TFLOPS with a 1:1 ratio, while the Arc Pro B390 reaches 15.36 TFLOPS using a 2:1 rate. In texture throughput, the Max 1550 records 1,638.4 GTexel/s against 120.0 GTexel/s for the Arc Pro B390, a difference of roughly 13.7 times.

The pixel rate comparison is unusual. The Arc Pro B390 shows 60.00 GPixel/s, while the Data Center GPU Max 1550 lists 0 MPixel/s. This reflects the Max 1550 having no ROPs and no display outputs; it is not a rasterization-oriented part. The Arc Pro B390, by contrast, is an integrated graphics processor with 24 ROPs and display support dependent on the portable device.

Architecture Differences

The two products come from different architectural lineages and target completely different deployment scenarios. The Arc Pro B390 uses the Panther Lake chip with Xe3-LPG architecture, built on a 3 nm process at Intel. It belongs to the Arc Graphics-WM generation. The Data Center GPU Max 1550 uses the Ponte Vecchio chip with Generation 12.5 architecture, built on a 10 nm process, also at Intel. It belongs to the Data Center GPU generation.

The transistor counts illustrate the scale difference. The Max 1550 packs 100,000 million transistors on a 1280 mm² die, with a transistor density of 78.1M per mm². The Arc Pro B390 has unknown transistor count and die size, but its integrated nature and 80 W TDP point to a far smaller implementation.

Shading unit counts differ significantly: 1,536 for the Arc Pro B390 versus 16,384 for the Max 1550. Texture mapping units stand at 48 versus 1,024. Ray tracing cores number 12 versus 128. Neither product lists tensor cores in the database.

Clock behavior also diverges. The Arc Pro B390 runs at a 300 MHz base clock and boosts to 2500 MHz. The Max 1550 has a 900 MHz base and a 1600 MHz boost. Despite the lower boost clock, the Max 1550 achieves far higher throughput because of its massive execution resource count.

Memory architecture represents the starkest split. The Arc Pro B390 uses system shared memory, with type, bus width, and bandwidth all listed as system dependent. The Max 1550 carries 128 GB of HBM2e on an 8192-bit bus, delivering 3.28 TB/s of bandwidth. Memory clock for the Max 1550 is 1600 MHz with 3.2 Gbps effective data rate. The Arc Pro B390's memory clock is tied to the system.

Power and physical configuration differ completely. The Arc Pro B390 has an 80 W TDP, is an IGP with no power connectors, and uses an IGP bus interface. The Max 1550 has a 600 W TDP, is an OAM Module, and uses PCIe 5.0 x16. The suggested PSU for a system with the Max 1550 is 1000 W. The Arc Pro B390 lists no suggested PSU.

Display capabilities separate the two as well. The Arc Pro B390 has display outputs described as portable device dependent, meaning it can drive displays in the host system. The Max 1550 has no outputs at all, consistent with its accelerator role.

API support shows a notable inversion. The Arc Pro B390 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Max 1550 supports DirectX 12 (12_1) and OpenGL 4.6, but lists no Vulkan support. The Arc Pro B390 therefore carries a newer DirectX feature level and broader graphics API coverage despite its smaller compute footprint.

Where Each One Wins

The Arc Pro B390 wins in scenarios requiring integrated graphics, modern graphics API features, and low power draw. Its 80 W TDP makes it suitable for compact or portable systems where a discrete accelerator is impractical. The DirectX 12 Ultimate support with feature level 12_2, along with Vulkan 1.4, positions it for contemporary graphics workloads and gaming-oriented applications. The 2500 MHz boost clock and 300 MHz base clock indicate a design tuned for bursty, latency-sensitive graphics work rather than sustained throughput.

The Data Center GPU Max 1550 wins in raw compute density, memory capacity, and bandwidth. The 128 GB HBM2e pool with 3.28 TB/s bandwidth is an order of magnitude beyond what any integrated solution can address. The 16,384 shading units and 128 ray tracing cores provide the execution resources for large-scale parallel workloads. The 52.43 TFLOPS FP32 and FP16 performance, delivered at a 1:1 ratio, suits compute tasks that need consistent precision without the half-rate penalty seen in the Arc Pro B390's 2:1 FP16 path.

The pixel rate figures highlight a functional split. The Arc Pro B390 renders to displays at 60.00 GPixel/s, while the Max 1550 has no raster output stage. The Max 1550 is not designed for traditional graphics output; it is a compute accelerator. The Arc Pro B390, despite lower raw numbers, is the only one of the two that can present frames to a screen.

The API support difference reinforces this. The Max 1550 lacks Vulkan support in the database, and its DirectX 12 (12_1) feature level is older than the Arc Pro B390's 12_2. Workloads that depend on modern graphics APIs will favor the Arc Pro B390. Workloads that depend on massive memory bandwidth and raw FP32 or FP16 throughput will favor the Max 1550.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Data Center GPU Max 1550 delivers 52.43 TFLOPS of FP32, compared to 7.680 TFLOPS for the Intel Arc Pro B390.

Q: How much memory does each product use?

A: The Arc Pro B390 uses system shared memory, with size, type, and bandwidth dependent on the host system. The Data Center GPU Max 1550 has 128 GB of HBM2e memory on an 8192-bit bus with 3.28 TB/s bandwidth.

Q: Does the Data Center GPU Max 1550 support display output?

A: No. The Max 1550 lists no display outputs and has a pixel rate of 0 MPixel/s. The Arc Pro B390 has display outputs that are portable device dependent.

Q: Which product supports a newer DirectX version?

A: The Arc Pro B390 supports DirectX 12 Ultimate (12_2). The Data Center GPU Max 1550 supports DirectX 12 (12_1).

Q: What is the power consumption difference?

A: The Arc Pro B390 has an 80 W TDP with no power connectors. The Data Center GPU Max 1550 has a 600 W TDP and a suggested PSU of 1000 W.

Q: What process nodes are used?

A: The Arc Pro B390 is built on a 3 nm process. The Data Center GPU Max 1550 is built on a 10 nm process. Both are manufactured by Intel.

The Verdict

The data defines two products with almost no overlap in purpose. The Intel Arc Pro B390 is an integrated graphics processor for portable devices, built on a 3 nm process with Xe3-LPG architecture. It draws 80 W, supports DirectX 12 Ultimate, and provides display output. Its performance class is defined by 7.680 TFLOPS FP32, 60.00 GPixel/s, and system-dependent shared memory.

The Intel Data Center GPU Max 1550 is a 600 W OAM module for data center compute. It uses 100,000 million transistors on a 1280 mm² die, carries 128 GB of HBM2e with 3.28 TB/s bandwidth, and delivers 52.43 TFLOPS of FP32 and FP16 compute. It has no display outputs and no ROPs. Its API support is older, with DirectX 12 (12_1) and no Vulkan.

Users with a portable or integrated system should select the Arc Pro B390. It is the only one of the two with display capability, and its modern API support covers current graphics standards. Users building or populating a data center accelerator slot should select the Data Center GPU Max 1550, assuming the 600 W power draw and 1000 W suggested PSU can be accommodated. The Max 1550 provides roughly 6.8 times the FP32 throughput and over 13 times the texture rate of the Arc Pro B390, plus a dedicated 128 GB memory pool. Neither product has recorded benchmark scores in the database, so these conclusions rest on specification data alone.

Specification Differences

| Field | Intel Arc Pro B390 | Intel Data Center GPU Max 1550 |

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

| Chip | Panther Lake | Ponte Vecchio |

| Architecture | Xe3-LPG | Generation 12.5 |

| Generation | Arc Graphics-WM (Panther Lake) | Data Center GPU (Ponte Vecchio) |

| Process Node | 3 nm | 10 nm |

| Transistors | unknown | 100,000 million |

| Die Size | unknown | 1280 mm² |

| Transistor Density | not listed | 78.1M / mm² |

| Base Clock | 300 MHz | 900 MHz |

| Boost Clock | 2500 MHz | 1600 MHz |

| Memory Size | System Shared | 128 GB |

| Memory Type | System Shared | HBM2e |

| Memory Bus Width | System Shared | 8192 bit |

| Memory Bandwidth | System Dependent | 3.28 TB/s |

| Shading Units | 1536 | 16384 |

| TMUs | 48 | 1024 |

| ROPs | 24 | 0 |

| RT Cores | 12 | 128 |

| Pixel Rate | 60.00 GPixel/s | 0 MPixel/s |

| Texture Rate | 120.0 GTexel/s | 1,638.4 GTexel/s |

| FP32 | 7.680 TFLOPS | 52.43 TFLOPS |

| FP16 | 15.36 TFLOPS (2:1) | 52.43 TFLOPS (1:1) |

| TDP | 80 W | 600 W |

| Slot Width | IGP | OAM Module |

| Power Connectors | None | not listed |

| Suggested PSU | not listed | 1000 W |

| Bus Interface | IGP | PCIe 5.0 x16 |

| Display Outputs | Portable Device Dependent | No outputs |

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

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | not listed |

| Release Date | 2026-01-26 | 2023-01-09 |

| Predecessor | HD Graphics-WM | not listed |

| Successor | not listed | H3C Graphics |

| Production Status | Active | Active |