AMD Radeon 820M vs Intel Arc A380M Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark results between the AMD Radeon 820M and Intel Arc A380M. Both entries list empty benchmark arrays, zero average benchmark scores, and zero wins for either side. The percentile fields for both GPUs sit at 50, indicating median placement in the overall database, but no comparative measurements are available to differentiate them numerically.

Without direct measurement data, the specification sheets provide the only quantitative basis for comparison. The Intel Arc A380M delivers 4.096 TFLOPS of FP32 throughput, which is 5.7 times the 716.8 GFLOPS of the AMD Radeon 820M. Texture rate favors Intel at 128.0 GTexel/s versus 22.40 GTexel/s, a 5.7x margin. Pixel rate shows Intel at 64.00 GPixel/s against AMD's 11.20 GPixel/s, a 5.7x difference as well. These figures indicate that in raw compute and rasterization throughput, the Arc A380M holds a commanding lead based on silicon specifications alone.

Memory bandwidth tells a similar story. The Intel part uses 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s. The AMD Radeon 820M relies on system shared memory with bandwidth described as "System Dependent." In a typical laptop configuration, dedicated GDDR6 at 186.0 GB/s will outperform shared system memory, though the actual margin depends entirely on the host system's memory configuration. The database records this dependency explicitly.

Clock behavior differs notably. The Radeon 820M has a 400 MHz base clock and 2800 MHz boost clock, suggesting a wide dynamic range typical of integrated graphics that can idle low and ramp high when needed. The Arc A380M runs at 1550 MHz base and 2000 MHz boost, a narrower range consistent with a discrete mobile GPU that maintains higher sustained clocks. The Radeon's boost clock is 40% higher than Intel's, but with far fewer execution units, the higher clock cannot close the throughput gap.

The FP16 to FP32 ratio also separates the two. AMD's Radeon 820M offers 716.8 GFLOPS FP16 at a 1:1 ratio, meaning no dedicated half-precision acceleration. Intel's Arc A380M delivers 8.192 TFLOPS FP16 at a 2:1 ratio, indicating dedicated FP16 hardware that doubles throughput. For workloads using half-precision math, the Intel part extends its lead further beyond the already substantial FP32 advantage.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The Intel Arc A380M delivers 4.096 TFLOPS FP32 and 8.192 TFLOPS FP16, compared to the AMD Radeon 820M's 716.8 GFLOPS for both FP32 and FP16. Intel leads by 5.7x in FP32 and by 11.4x in FP16.

Q: How do the memory subsystems compare?

A: The Intel Arc A380M uses 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth. The AMD Radeon 820M uses system shared memory with bandwidth described as "System Dependent," so its effective bandwidth varies with the host system.

Q: What are the power requirements for each GPU?

A: The AMD Radeon 820M has a 15 W TDP and uses no power connectors, consistent with an integrated graphics processor. The Intel Arc A380M has a 35 W TDP and uses an MXM Module slot width, indicating a discrete mobile module.

Q: Do both GPUs support the same API feature levels?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. No differences exist in the recorded API support.

Q: Which GPU has more ray tracing hardware?

A: The Intel Arc A380M has 8 ray tracing cores, while the AMD Radeon 820M has 2. Intel's count is four times higher.

Q: What are the release dates for each product?

A: The AMD Radeon 820M was released on February 28, 2025. The Intel Arc A380M was released on January 23, 2023. Both are listed as Active in production status.

Architecture Differences

The AMD Radeon 820M uses the RDNA 3.5 architecture on a 4 nm process node at TSMC. It belongs to the Navi III IGP generation for Strix Point Mobile and uses the Krackan Point 2 chip. The Intel Arc A380M uses the Xe-HPG architecture on a 6 nm process node, also at TSMC, and belongs to the Alchemist generation for Arc 3 Mobile with the DG2-128 chip. The process node difference is significant: AMD's 4 nm versus Intel's 6 nm, both fabricated by TSMC.

Transistor counts and die sizes are only recorded for Intel. The Arc A380M packs 7,200 million transistors into a 157 mm² die, yielding a transistor density of 45.9M per mm². The Radeon 820M's transistor count and die size are listed as unknown, so no density comparison is possible from the data.

Execution resource counts show a wide gap. The Radeon 820M has 128 shading units, 8 texture mapping units, 4 render output units, and 2 ray tracing cores. The Arc A380M has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. Each category shows Intel with an 8x advantage in shading units and TMUs, a 4x advantage in ROPs and RT cores.

The Radeon 820M uses a PCIe 4.0 x8 bus interface and is classified as an IGP with no slot width, no power connectors, and "Portable Device Dependent" display outputs. The Arc A380M uses an MXM-A (3.1) bus interface, is classified as an MXM Module, and also has "Portable Device Dependent" display outputs. Both rely on the host laptop for display connectivity.

Memory architecture differs fundamentally. AMD's part uses system shared memory for both capacity and type, with the bus width also shared. Intel's part has dedicated 6 GB GDDR6 with a 96-bit bus. This architectural distinction means the AMD IGP competes for memory bandwidth with the CPU, while Intel's discrete module has dedicated bandwidth.

Specification Differences

| Specification | AMD Radeon 820M | Intel Arc A380M |

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

| Architecture | RDNA 3.5 | Xe-HPG |

| Generation | Navi III IGP (Strix Point Mobile) | Alchemist (Arc 3 Mobile) |

| Process Node | 4 nm | 6 nm |

| Transistors | Unknown | 7,200 million |

| Die Size | Unknown | 157 mm² |

| Base Clock | 400 MHz | 1550 MHz |

| Boost Clock | 2800 MHz | 2000 MHz |

| Memory Size | System Shared | 6 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 96 bit |

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

| Shading Units | 128 | 1024 |

| TMUs | 8 | 64 |

| ROPs | 4 | 32 |

| RT Cores | 2 | 8 |

| Pixel Rate | 11.20 GPixel/s | 64.00 GPixel/s |

| Texture Rate | 22.40 GTexel/s | 128.0 GTexel/s |

| FP32 Performance | 716.8 GFLOPS | 4.096 TFLOPS |

| FP16 Performance | 716.8 GFLOPS (1:1) | 8.192 TFLOPS (2:1) |

| TDP | 15 W | 35 W |

| Slot Width | IGP | MXM Module |

| Power Connectors | None | Not listed |

| Bus Interface | PCIe 4.0 x8 | MXM-A (3.1) |

| Release Date | 2025-02-28 | 2023-01-23 |

The specification table shows Intel leading in every compute and memory metric where both have recorded values. AMD leads only in boost clock (2800 MHz versus 2000 MHz) and process node (4 nm versus 6 nm). The TDP difference is substantial: 15 W for AMD versus 35 W for Intel, reflecting the IGP versus discrete module design split.

The Verdict

The data shows two fundamentally different product classes. The AMD Radeon 820M is an integrated graphics processor within the Krackan Point 2 chip, consuming 15 W and using system shared memory. The Intel Arc A380M is a discrete MXM module with 6 GB of dedicated GDDR6, consuming 35 W. These are not direct competitors in the traditional sense; they serve different laptop designs.

For raw performance, the Intel Arc A380M dominates every recorded compute metric. Its 4.096 TFLOPS FP32 throughput is 5.7x the Radeon 820M's 716.8 GFLOPS. Its 186.0 GB/s dedicated memory bandwidth eliminates the system dependency that limits the AMD part. Its 8 ray tracing cores quadruple AMD's 2. Its larger execution resource pool (1,024 shading units versus 128) provides the hardware foundation for these advantages.

For efficiency and integration, the AMD Radeon 820M holds the edge. Its 15 W TDP is less than half of Intel's 35 W. Its 4 nm process node is more advanced than Intel's 6 nm. As an IGP, it requires no separate module, no power connectors, and integrates directly into the host chip. Laptops using the Radeon 820M can be thinner, lighter, and simpler than those requiring an MXM module.

The release timeline also matters. Intel's Arc A380M arrived in January 2023, while AMD's Radeon 820M came in February 2025, roughly two years later. The newer AMD part uses a more modern process node but still cannot match the older Intel part's compute resources. This suggests architectural priorities differ: AMD optimized for power efficiency in an integrated design, while Intel targeted higher performance in a discrete module.

Buyers should choose based on the laptop form factor and performance needs. A system with the Arc A380M will deliver substantially higher frame rates and compute throughput in GPU-bound workloads. A system with the Radeon 820M will offer lower power draw and simpler integration, but will rely entirely on system memory bandwidth and far fewer execution units.

Where Each One Wins

The Intel Arc A380M wins in every measurable performance category recorded in the database. It leads in FP32 compute by 5.7x, FP16 compute by 11.4x, pixel rate by 5.7x, texture rate by 5.7x, and memory bandwidth by a margin that depends on the AMD host system but is likely substantial given the dedicated 186.0 GB/s GDDR6. It also has 8x the shading units, 8x the TMUs, 8x the ROPs, and 4x the ray tracing cores. For gaming, 3D rendering, GPGPU workloads, or any task that scales with raw GPU throughput, the Arc A380M is the clear choice.

The AMD Radeon 820M wins in power efficiency and integration. Its 15 W TDP is 20 W lower than Intel's 35 W. Its 4 nm process node is two generations ahead of Intel's 6 nm. As an IGP, it requires no MXM slot, no dedicated memory, and no power connectors. For ultraportable laptops, fanless designs, or systems where battery life and thermal headroom take priority over GPU performance, the Radeon 820M's design philosophy offers clear advantages. Its 2800 MHz boost clock is 40% higher than Intel's 2000 MHz, indicating strong per-clock efficiency despite fewer execution units.

The memory situation favors Intel decisively. Dedicated GDDR6 at 186.0 GB/s provides predictable, consistent bandwidth. The Radeon 820M's "System Dependent" bandwidth means real-world performance varies with the laptop's memory configuration, dual-channel versus single-channel, speed, and capacity. In a well-configured system, the AMD part may perform adequately, but it can never match the dedicated bandwidth of the Intel module.

The Radeon 820M's FP16 performance equals its FP32 performance at a 1:1 ratio, meaning no half-precision acceleration. The Arc A380M doubles its FP32 throughput when running FP16 workloads, reaching 8.192 TFLOPS. For machine learning inference, image processing, or any workload using half-precision math, Intel's advantage grows beyond the already large FP32 gap.

Both GPUs support identical API feature levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Software compatibility should be similar on that front. The Arc A380M's MXM-A (3.1) interface targets upgradeable laptops, while the Radeon 820M's PCIe 4.0 x8 interface is standard for integrated processors. Each fits its intended platform.