Intel Arc A530M vs Intel Arc B390 Comparison

FAQ

Q: What is the Intel Arc A530M based on?

A: The Intel Arc A530M uses the DG2-256 chip with the Xe-HPG architecture, belonging to the Alchemist (Arc 5 Mobile) generation. It is built on a 6 nm process at TSMC.

Q: What is the Intel Arc B390 based on?

A: The Intel Arc B390 uses the Panther Lake chip with the Xe3-LPG architecture, belonging to the Arc Graphics-M (Panther Lake) generation. It is built on a 3 nm process at Intel.

Q: How do their shading unit counts compare?

A: Both GPUs have 1536 shading units and 12 ray tracing cores. They differ in TMUs (96 vs 48) and ROPs (48 vs 24), with the A530M having double the texture units and raster operation units.

Q: What is the memory configuration of the Intel Arc A530M?

A: The A530M has 8 GB of GDDR6 memory on a 128-bit bus, with a bandwidth of 224.0 GB/s and a memory clock of 1750 MHz (14 Gbps effective).

Q: What is the memory configuration of the Intel Arc B390?

A: The B390 uses system shared memory, with the type, bus width, and bandwidth all being system dependent. Its memory clock is also listed as system shared.

Q: Which GPU has a higher boost clock?

A: The Intel Arc B390 has a boost clock of 2500 MHz, significantly higher than the A530M's 1300 MHz boost. The A530M has a higher base clock at 900 MHz versus 300 MHz.

Where Each One Wins

The Intel Arc A530M and Intel Arc B390 occupy very different positions in the database's performance landscape, and each has distinct strengths based on the recorded measurements.

The A530M demonstrates strong compute performance in general-purpose benchmarks. Its Geekbench OpenCL score of 49,735 and Geekbench Vulkan score of 43,492 produce an average benchmark score of 46,614. This places it at the 85th percentile of all GPUs in the database. Its nearest rivals include the AMD Radeon RX 5600M (46,601, a 0% delta), the AMD Radeon RX 6550M (46,702, a -0.2% delta), the NVIDIA RTX A2000 (46,043, a 1.2% delta), and the NVIDIA RTX 5880 Ada Generation (45,972, a 1.4% delta). This positioning indicates the A530M is competitive with established discrete mobile GPUs, sitting within a narrow band of 1.6 percentage points across all four rivals.

The B390 shows a contrasting profile. Its only recorded benchmark is 3DMark Steel Nomad DX12, with a score of 1,482. This yields an average benchmark score of 1,482, placing it at the 9th percentile of all GPUs. Its nearest rivals are all much older NVIDIA parts: the GeForce GT 520MX (1,463, a 1.3% delta), the GeForce 800M (1,460, a 1.5% delta), the GeForce GT 625 OEM (1,446, a 2.5% delta), and the GeForce GT 710 (1,443, a 2.7% delta). The B390 outperforms these older parts, but the comparison set shows its performance class is far below the A530M.

Where each one wins depends on the workload. The A530M wins decisively in raw compute throughput, as evidenced by its TFLOPS figures and its benchmark scores. The B390 wins in clock speed headroom, with a much higher boost clock that suggests better performance scaling in short, bursty workloads. The B390 also uses a more advanced 3 nm process, which typically enables higher efficiency per clock.

Architecture Differences

The two GPUs come from different architectural generations within Intel's lineup. The A530M uses the Xe-HPG architecture on the DG2-256 chip, which is part of the Alchemist generation for Arc 5 Mobile. The B390 uses the newer Xe3-LPG architecture on the Panther Lake chip, belonging to the Arc Graphics-M (Panther Lake) generation.

The manufacturing processes differ substantially. The A530M is built on a 6 nm process at TSMC, with 11,500 million transistors on a 269 mm² die, yielding a transistor density of 42.8 million transistors per square millimeter. The B390 is built on a 3 nm process at Intel, with the transistor count and die size listed as unknown in the database.

Both GPUs share the same DirectX 12 Ultimate (12_2) support, OpenGL 4.6, and Vulkan 1.4 APIs. Both have 1536 shading units and 12 ray tracing cores. The core configuration diverges at the texture and raster level: the A530M has 96 texture mapping units and 48 render output units, while the B390 has 48 TMUs and 24 ROPs. This means the A530M has exactly double the texture and pixel processing capacity of the B390.

The clock behavior is a major architectural difference. The A530M runs at a 900 MHz base clock and 1300 MHz boost clock. The B390 runs at a 300 MHz base clock and 2500 MHz boost clock. The B390's boost clock is nearly double the A530M's, which partially compensates for its reduced TMU and ROP counts in certain workloads.

Memory architecture differs completely. The A530M uses dedicated 8 GB GDDR6 memory with a 128-bit bus and 224.0 GB/s bandwidth. The B390 uses system shared memory, with bandwidth described as system dependent. This means the B390's memory performance is tied to the host system's memory configuration, whereas the A530M has fixed dedicated memory resources.

The B390 has no power connectors and an IGP slot width, while the A530M also has an IGP slot width but no power connector information listed. The bus interface also differs: the A530M uses PCIe 4.0 x8, while the B390 uses an integrated graphics processor (IGP) interface.

Specification Differences

| Specification | Intel Arc A530M | Intel Arc B390 |

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

| Architecture | Xe-HPG | Xe3-LPG |

| Generation | Alchemist (Arc 5 Mobile) | Arc Graphics-M (Panther Lake) |

| Process Node | 6 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 11,500 million | Unknown |

| Die Size | 269 mm² | Unknown |

| Base Clock | 900 MHz | 300 MHz |

| Boost Clock | 1300 MHz | 2500 MHz |

| Memory Size | 8 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 224.0 GB/s | System Dependent |

| Memory Clock | 1750 MHz (14 Gbps effective) | System Shared |

| TMUs | 96 | 48 |

| ROPs | 48 | 24 |

| Pixel Rate | 62.40 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 124.8 GTexel/s | 120.0 GTexel/s |

| FP32 Performance | 3.994 TFLOPS | 7.680 TFLOPS |

| FP16 Performance | 7.987 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 65 W | 80 W |

| Bus Interface | PCIe 4.0 x8 | IGP |

| Power Connectors | Not listed | None |

| Release Date | 2023-07-31 | 2026-01-26 |

The FP32 and FP16 figures show a clear divergence. The B390 delivers 7.680 TFLOPS of FP32 performance and 15.36 TFLOPS of FP16 performance, which is 92% higher than the A530M's 3.994 TFLOPS and 7.987 TFLOPS respectively. This is notable because the A530M has double the TMUs and ROPs. The B390 achieves its higher compute throughput through its much higher boost clock and architectural efficiency.

The pixel and texture rates tell a different story. The A530M has a pixel rate of 62.40 GPixel/s and a texture rate of 124.8 GTexel/s. The B390 has a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s. These are very close, with the A530M ahead by 4% in both metrics. The A530M's double TMU and ROP counts nearly offset the B390's clock advantage.

Power consumption differs, with the A530M at 65 W and the B390 at 80 W. Both are classified as IGP slot width, meaning they are integrated into a host device rather than discrete expansion cards. The B390 has no power connectors, while the A530M's power connector configuration is not listed.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between the Intel Arc A530M and the Intel Arc B390. The head-to-head array is empty, and the win counts are zero for both GPUs. This means a direct comparison must rely on their respective benchmark suites and percentile rankings.

The A530M's recorded benchmarks are Geekbench OpenCL with a score of 49,735 and Geekbench Vulkan with a score of 43,492. These produce an average benchmark score of 46,614. The B390's only recorded benchmark is 3DMark Steel Nomad DX12 with a score of 1,482, which is also its average benchmark score.

These benchmarks measure different workloads, so a direct score comparison is not meaningful. The Geekbench tests measure general compute and graphics API performance across a wide range of tasks. The 3DMark Steel Nomad DX12 test specifically measures DirectX 12 gaming performance in a modern title scenario.

The percentile rankings provide context. The A530M sits at the 85th percentile of all GPUs in the database, indicating it outperforms 85% of recorded graphics processors. The B390 sits at the 9th percentile, indicating it outperforms only 9% of recorded GPUs. This is a substantial gap in overall performance classification.

The nearest rival comparisons confirm this separation. The A530M's nearest rivals are all modern or professional GPUs with average scores in the 45,972 to 46,702 range. The B390's nearest rivals are older NVIDIA parts with average scores in the 1,443 to 1,463 range. The delta percentages show the A530M is within 1.4 percentage points of its closest rivals, while the B390 is within 2.7 percentage points of its closest rivals.

The B390's boost clock of 2500 MHz is nearly double the A530M's 1300 MHz, and its FP32 throughput of 7.680 TFLOPS is 92% higher. However, the B390's system shared memory configuration and lower TMU/ROP counts likely limit its real-world graphics performance. The A530M's dedicated 8 GB GDDR6 memory with 224.0 GB/s bandwidth provides consistent memory performance that the B390 cannot guarantee.

The data indicates the A530M is the stronger overall performer in the database's recorded metrics, with a much higher percentile ranking and benchmark scores that place it among capable discrete mobile GPUs. The B390, despite its architectural advantages in clock speed and process node, records performance that places it in the lower percentile range, comparable to legacy NVIDIA entry-level parts. The A530M's advantage in texture and pixel throughput, combined with its dedicated memory subsystem, gives it a clear edge in the recorded benchmark data.