Intel Arc Pro A60M vs NVIDIA Jetson Orin Nano Super Comparison

Head-to-Head Benchmarks

The recorded database contains no direct benchmark scores for either the Intel Arc Pro A60M or the NVIDIA Jetson Orin Nano Super. Both products show an average benchmark score of zero, and the head-to-head benchmark comparison list is empty. This absence of measured data means a direct performance comparison must rely on the architectural and specification differences recorded in the database.

The Intel Arc Pro A60M delivers 5.325 TFLOPS of FP32 compute, while the NVIDIA Jetson Orin Nano Super delivers 2.089 TFLOPS. That places the Intel part at roughly 2.5 times the raw single-precision throughput of the NVIDIA module. In FP16, the gap narrows slightly: the Arc Pro A60M reaches 10.65 TFLOPS (2:1), while the Jetson Orin Nano Super reaches 4.178 TFLOPS (2:1). The Intel GPU still holds a clear lead, but the Tensor Core-equipped NVIDIA part may be better suited for workloads that can exploit its dedicated tensor hardware.

Pixel throughput further separates the two. The Arc Pro A60M renders at 83.20 GPixel/s, compared to 16.32 GPixel/s for the Jetson Orin Nano Super. Texture rate tells a similar story: 166.4 GTexel/s versus 32.64 GTexel/s. These figures indicate that the Intel GPU is substantially faster in traditional rasterization tasks, likely due to its larger number of execution units and higher clock speeds.

Memory bandwidth also favors Intel. The Arc Pro A60M uses 8 GB of GDDR6 on a 128-bit bus, achieving 256.0 GB/s. The Jetson Orin Nano Super uses 8 GB of LPDDR5 on the same 128-bit bus, but only reaches 102.4 GB/s. That is a 2.5x difference in bandwidth, which can heavily impact fill-rate-bound scenarios and large texture streaming workloads.

Both devices share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means software compatibility at the API level is equivalent, though the underlying hardware capabilities differ significantly. Neither product recorded any wins in the head-to-head benchmark section, as both have empty benchmark arrays.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro A60M delivers 5.325 TFLOPS, which is more than double the 2.089 TFLOPS of the NVIDIA Jetson Orin Nano Super.

Q: How do their memory bandwidths compare?

A: The Arc Pro A60M achieves 256.0 GB/s over a 128-bit GDDR6 bus, while the Jetson Orin Nano Super achieves 102.4 GB/s over a 128-bit LPDDR5 bus. Intel holds a 2.5x bandwidth advantage.

Q: Do both support the same graphics APIs?

A: Yes, both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 in the database.

Q: What is the power consumption difference?

A: The Intel part is rated at 95 W, while the NVIDIA module is rated at 25 W. The NVIDIA device uses 70 W less power, a significant difference for embedded or mobile deployments.

Q: Does the Jetson Orin Nano Super have Tensor Cores?

A: Yes, it has 32 Tensor Cores. The Intel Arc Pro A60M has no Tensor Cores listed, but it does have 16 ray tracing cores.

Q: What are the physical dimensions of each?

A: The Jetson Orin Nano Super measures 70 mm by 45 mm. The Arc Pro A60M has no recorded length or height dimensions in the database.

Q: Which product is newer?

A: The NVIDIA Jetson Orin Nano Super has a release date of 2024-12-16, while the Intel Arc Pro A60M was released on 2023-06-05.

Architecture Differences

The Intel Arc Pro A60M is built on the Xe-HPG architecture, specifically the DG2-256 chip, and belongs to the Alchemist generation for Pro-Series Mobile. It uses a 6 nm process from TSMC, with 11,500 million transistors on a 269 mm² die. That translates to a transistor density of 42.8M per mm². This is a dedicated mobile GPU design with a full complement of graphics hardware.

The NVIDIA Jetson Orin Nano Super uses the Ampere architecture, implemented in the GA10B chip, part of the Tegra (Ampere) generation. It is fabricated on an 8 nm process from Samsung, with a die size of 200 mm². The transistor count is listed as unknown, and no transistor density is recorded. This is a system-on-module rather than a traditional discrete GPU, which explains its compact footprint.

The shading hardware differs significantly. The Arc Pro A60M has 2048 shading units, 128 texture mapping units, and 64 raster output units. It also includes 16 ray tracing cores but no Tensor Cores. The Jetson Orin Nano Super has 1024 shading units, 32 TMUs, and 16 ROPs. It has no ray tracing cores but includes 32 Tensor Cores. This reflects different design priorities: Intel focuses on traditional graphics throughput and ray tracing, while NVIDIA emphasizes tensor-based inferencing and AI workloads.

The compute rates follow the hardware counts. The Arc Pro A60M reaches 5.325 TFLOPS FP32 and 10.65 TFLOPS FP16 (2:1). The Jetson Orin Nano Super reaches 2.089 TFLOPS FP32 and 4.178 TFLOPS FP16 (2:1). The Intel GPU clearly has more raw shader throughput, but the NVIDIA module's Tensor Cores are not captured in these FP32 or FP16 figures, so AI-specific performance is not directly comparable from the recorded data.

Specification Differences

| Specification | Intel Arc Pro A60M | NVIDIA Jetson Orin Nano Super |

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

| Chip | DG2-256 | GA10B |

| Architecture | Xe-HPG | Ampere |

| Process Node | 6 nm (TSMC) | 8 nm (Samsung) |

| Die Size | 269 mm² | 200 mm² |

| Transistors | 11,500 million | unknown |

| Base Clock | 900 MHz | not listed |

| Boost Clock | 1300 MHz | not listed |

| Memory Clock | 2000 MHz, 16 Gbps effective | 800 MHz, 6.4 Gbps effective |

| Memory Type | GDDR6 | LPDDR5 |

| Memory Size | 8 GB | 8 GB |

| Memory Bus | 128 bit | 128 bit |

| Memory Bandwidth | 256.0 GB/s | 102.4 GB/s |

| Shading Units | 2048 | 1024 |

| TMUs | 128 | 32 |

| ROPs | 64 | 16 |

| Ray Tracing Cores | 16 | none |

| Tensor Cores | none | 32 |

| Pixel Rate | 83.20 GPixel/s | 16.32 GPixel/s |

| Texture Rate | 166.4 GTexel/s | 32.64 GTexel/s |

| FP32 Performance | 5.325 TFLOPS | 2.089 TFLOPS |

| FP16 Performance | 10.65 TFLOPS (2:1) | 4.178 TFLOPS (2:1) |

| TDP | 95 W | 25 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x4 |

| Dimensions | not listed | 70 mm x 45 mm |

| Release Date | 2023-06-05 | 2024-12-16 |

| Launch MSRP | not listed | 249 USD |

The power envelopes are starkly different. The Arc Pro A60M draws 95 W, while the Jetson Orin Nano Super draws only 25 W. This makes the NVIDIA module far more suitable for battery-powered or passively cooled systems, while the Intel GPU requires more substantial thermal management. The bus interface also differs: PCIe 4.0 x16 for Intel, PCIe 4.0 x4 for NVIDIA.

The Verdict

The data points to two entirely different use cases. The Intel Arc Pro A60M is a traditional mobile graphics processor aimed at rendering workloads. Its 5.325 TFLOPS FP32, 256.0 GB/s memory bandwidth, and 83.20 GPixel/s pixel rate make it the clear choice for graphics-intensive tasks like 3D rendering, CAD, and gaming. The 16 ray tracing cores add hardware acceleration for ray-traced effects, which the NVIDIA part lacks entirely.

The NVIDIA Jetson Orin Nano Super is a compact, low-power compute module. Its 25 W TDP, 70 mm by 45 mm footprint, and 32 Tensor Cores point toward edge AI and inference applications. The FP32 performance of 2.089 TFLOPS is modest, but the Tensor Cores are not measured in the recorded FP32 or FP16 figures, so the module's true AI capability is likely understated by those numbers alone. The 102.4 GB/s bandwidth is sufficient for embedded workloads, though it lags the Intel part by 2.5x.

Neither product recorded any benchmark wins in the database, and both have an identical percentile standing of 50 against all GPUs. This means the database does not currently rank one as superior overall; the appropriate choice depends entirely on the workload. For raw graphics throughput, the Intel Arc Pro A60M dominates. For low-power embedded AI, the NVIDIA Jetson Orin Nano Super is the only sensible option given its power budget and Tensor Core hardware.

Where Each One Wins

Intel Arc Pro A60M wins on: Rasterization throughput, with 83.20 GPixel/s versus 16.32 GPixel/s. Texture-heavy workloads, with 166.4 GTexel/s versus 32.64 GTexel/s. Raw FP32 and FP16 compute, at 5.325 TFLOPS and 10.65 TFLOPS respectively versus 2.089 and 4.178. Memory bandwidth, at 256.0 GB/s versus 102.4 GB/s. Ray tracing, thanks to 16 dedicated RT cores. It also has more than double the shading units (2048 vs 1024), 4x the TMUs (128 vs 32), and 4x the ROPs (64 vs 16).

NVIDIA Jetson Orin Nano Super wins on: Power efficiency, drawing 25 W versus 95 W. Tensor Core availability, with 32 dedicated tensor units versus none on the Intel part. Physical size, at 70 mm by 45 mm with no dimensions recorded for the Intel GPU. It also has a lower launch MSRP of 249 USD, though the Intel part has no recorded launch MSRP for comparison.

The latency-sensitive and AI-oriented workloads favor NVIDIA, while the pure graphics and compute-heavy tasks favor Intel. The Jetson Orin Nano Super's 2.089 TFLOPS FP32 is still usable for light graphics, but its 16.32 GPixel/s pixel rate means it will struggle with high-resolution rendering. Conversely, the Arc Pro A60M's 95 W power draw and lack of Tensor Cores make it unsuitable for edge deployments where power is limited and AI inference is the primary task.