AMD Radeon AI PRO 9600D vs Intel Arc Pro B60 Dual Comparison

Where Each One Wins

The recorded data contains no direct head-to-head benchmark results for the AMD Radeon AI PRO 9600D and the Intel Arc Pro B60 Dual. Both cards sit at the 50th percentile against all GPUs in the database, with an average benchmark score of zero for each. This means the comparison must be built from the specification sheet alone, and the wins are defined by what each card is configured to do.

The AMD Radeon AI PRO 9600D wins on raw compute throughput in FP32, where it delivers 24.82 TFLOPS against 12.29 TFLOPS for the Intel card. That is a 2.02x advantage in single-precision floating point work. The AMD card also wins on memory capacity, offering 32 GB versus 24 GB, and on memory bandwidth, with 576.0 GB/s compared to 456.0 GB/s. For workloads that are memory-bound or FP32-bound, the AMD part has the clear edge.

The Intel Arc Pro B60 Dual wins on clock speeds. Its base clock is 2000 MHz versus 1080 MHz for the AMD card, and its boost clock reaches 2400 MHz against 2020 MHz. The Intel part also wins on FP16 throughput when measured at the native ratio, delivering 24.58 TFLOPS with a 2:1 rate, nearly matching the AMD card's 24.82 TFLOPS at 1:1. The Intel card also offers four display outputs (4x mini-DisplayPort 2.1) while the AMD card provides one (1x DisplayPort 2.1a), which makes the Intel card stronger for multi-display workstation setups.

Neither card has any benchmark entries in the database, so there are no recorded wins in actual workloads. The wins described here are structural, based on what the hardware specifications indicate each card can do.

Architecture Differences

The two cards come from different manufacturers and use different architectures. The AMD Radeon AI PRO 9600D is built on RDNA 4.0 and uses the Navi 48 chip, part of the Radeon Pro Navi (Navi IV Series) generation. The Intel Arc Pro B60 Dual uses the Xe2-HPG architecture with the BMG-G21 chip, part of the Battlemage (Pro Series) generation.

The manufacturing process differs. AMD uses a 4 nm process at TSMC, while Intel uses a 5 nm process at the same foundry. The AMD chip is physically larger, with a die size of 357 mm² versus 272 mm² for Intel. Transistor counts show a major difference: the AMD chip packs 53,900 million transistors, while the Intel chip has 19,600 million. This results in a transistor density of 151.0M per mm² for AMD and 72.1M per mm² for Intel, meaning the AMD die is more than twice as dense per square millimeter.

The compute resources differ substantially. The AMD card has 3072 shading units, 192 texture mapping units, 96 render output units, and 48 ray tracing cores. The Intel card has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The AMD card leads in every one of these categories, with 20% more shading units, 20% more TMUs, 20% more ROPs, and 2.4x more ray tracing cores.

Memory architecture differs as well. Both use GDDR6, but the AMD card has a 256-bit bus with 32 GB, while the Intel card has a 192-bit bus with 24 GB. The AMD card reaches 576.0 GB/s of bandwidth, the Intel card 456.0 GB/s. The AMD card uses a PCIe 5.0 x16 interface, while the Intel card uses PCIe 5.0 x8.

Power and cooling configurations are notably different. The AMD card has a 150 W TDP and is single-slot, while the Intel card has a 400 W TDP and is dual-slot. Both use a single 16-pin power connector. The suggested power supply is 450 W for AMD and 800 W for Intel. Physically, the AMD card is 241 mm long, 111 mm tall, and 19 mm wide, while the Intel card is 300 mm long, 110 mm tall, and 40 mm wide.

The FP16 implementation also differs. The AMD card executes FP16 at a 1:1 ratio with FP32, giving 24.82 TFLOPS in both precisions. The Intel card executes FP16 at a 2:1 ratio, delivering 24.58 TFLOPS in FP16 while FP32 is 12.29 TFLOPS. This is a fundamental architectural difference in how each chip prioritizes lower-precision compute.

Head-to-Head Benchmarks

There are no head-to-head benchmark results in the database for these two cards. The winsA and winsB fields are both zero, and the headToHeadBenchmarks array is empty. The comparison therefore rests entirely on the recorded hardware specifications.

The largest numerical advantage belongs to the AMD card in FP32 compute. At 24.82 TFLOPS versus 12.29 TFLOPS, the AMD card delivers exactly 2.02x the single-precision throughput of the Intel card. This is the most significant gap in the specification sheet and would matter most for workloads that rely on FP32 math.

Memory capacity and bandwidth also favor AMD. The 32 GB frame buffer is 33.3% larger than 24 GB, and the 576.0 GB/s bandwidth is 26.3% higher than 456.0 GB/s. For large datasets or high-resolution textures, the AMD card has more headroom.

The Intel card counters with higher clocks. Its base clock of 2000 MHz is 85.2% higher than the AMD base of 1080 MHz, and its boost clock of 2400 MHz is 18.8% higher than 2020 MHz. Despite these clock advantages, the Intel card still trails in FP32 because it has fewer shading units and a fundamentally different architecture.

The FP16 comparison is nearly even. The AMD card delivers 24.82 TFLOPS at 1:1, and the Intel card delivers 24.58 TFLOPS at 2:1. The difference is 0.24 TFLOPS, or about 1.0% in favor of AMD, which is effectively a tie in low-precision throughput.

Pixel and texture rates are also close. The AMD card has a pixel rate of 193.9 GPixel/s versus 192.0 GPixel/s for Intel, a difference of 1.0%. The texture rate is 387.8 GTexel/s for AMD versus 384.0 GTexel/s for Intel, a difference of 0.99%. These near-identical rates mean the two cards are likely to perform similarly in fill-rate-bound scenarios, despite the large differences in clock speed and core counts.

The ray tracing core count is a clear differentiator. The AMD card has 48 RT cores, which is 2.4x the 20 RT cores in the Intel card. This suggests a substantial advantage in ray-traced workloads, though no benchmark data is available to quantify it.

FAQ

Q: Which card has more memory bandwidth?

A: The AMD Radeon AI PRO 9600D has 576.0 GB/s of bandwidth, while the Intel Arc Pro B60 Dual has 456.0 GB/s. The AMD card leads by 120.0 GB/s.

Q: How do the two cards compare in FP32 compute?

A: The AMD card delivers 24.82 TFLOPS in FP32, exactly 2.02x the 12.29 TFLOPS of the Intel card.

Q: Do the cards use the same process node?

A: No. The AMD card uses a 4 nm process at TSMC, while the Intel card uses a 5 nm process at TSMC.

Q: What is the power consumption difference?

A: The AMD card has a 150 W TDP and suggests a 450 W power supply. The Intel card has a 400 W TDP and suggests an 800 W power supply.

Q: How many display outputs does each card have?

A: The AMD card has one DisplayPort 2.1a output. The Intel card has four mini-DisplayPort 2.1 outputs.

Q: Which card has more ray tracing cores?

A: The AMD card has 48 ray tracing cores, which is 2.4x the 20 ray tracing cores in the Intel card.

The Verdict

The data indicates that the AMD Radeon AI PRO 9600D is the stronger card for FP32 compute, memory capacity, memory bandwidth, and ray tracing core count. It offers 32 GB of GDDR6 on a 256-bit bus, 576.0 GB/s of bandwidth, and 24.82 TFLOPS of FP32 throughput. The 48 ray tracing cores and 150 W TDP make it a more efficient and denser design, with a single-slot form factor that is 19 mm wide versus 40 mm for the Intel card. The AMD card is also smaller at 241 mm in length compared to 300 mm.

The Intel Arc Pro B60 Dual is the stronger card for FP16 workload efficiency relative to its FP32 rate, delivering 24.58 TFLOPS at a 2:1 ratio. It also has significantly higher base and boost clocks, at 2000 MHz and 2400 MHz respectively, and four display outputs instead of one. The 400 W TDP and 800 W suggested power supply indicate a much higher power draw, but the dual-slot design and 4x mini-DisplayPort 2.1 outputs support multi-monitor professional setups that the AMD card cannot match with a single output.

For users who need the largest memory pool, the highest memory bandwidth, the most FP32 throughput, and the most ray tracing cores, the AMD card is the data-backed choice. For users who need multiple display outputs, higher clock speeds, and a card that delivers comparable FP16 throughput at a favorable ratio, the Intel card is the data-backed choice. The Intel card has a launch MSRP of 1,199 USD. The AMD card has no recorded launch MSRP in the database.

There is no benchmark data to separate the two in real-world application performance. The specification sheet favors AMD in most compute and memory categories, while Intel counters in clocks, display outputs, and FP16 efficiency. Each card has a defined role, and the correct pick depends on which of these recorded attributes matters more for the intended workload.

Specification Differences

| Specification | AMD Radeon AI PRO 9600D | Intel Arc Pro B60 Dual |

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

| Architecture | RDNA 4.0 | Xe2-HPG |

| Process Node | 4 nm | 5 nm |

| Transistors | 53,900 million | 19,600 million |

| Die Size | 357 mm² | 272 mm² |

| Transistor Density | 151.0M / mm² | 72.1M / mm² |

| Base Clock | 1080 MHz | 2000 MHz |

| Boost Clock | 2020 MHz | 2400 MHz |

| Memory Size | 32 GB | 24 GB |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 576.0 GB/s | 456.0 GB/s |

| Shading Units | 3072 | 2560 |

| TMUs | 192 | 160 |

| ROPs | 96 | 80 |

| Ray Tracing Cores | 48 | 20 |

| FP32 | 24.82 TFLOPS | 12.29 TFLOPS |

| FP16 | 24.82 TFLOPS (1:1) | 24.58 TFLOPS (2:1) |

| Pixel Rate | 193.9 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 387.8 GTexel/s | 384.0 GTexel/s |

| TDP | 150 W | 400 W |

| Slot Width | Single-slot | Dual-slot |

| Suggested PSU | 450 W | 800 W |

| Bus Interface | PCIe 5.0 x16 | PCIe 5.0 x8 |

| Display Outputs | 1x DisplayPort 2.1a | 4x mini-DisplayPort 2.1 |

| Length | 241 mm | 300 mm |

| Height | 111 mm | 110 mm |

| Width | 19 mm | 40 mm |