AMD Playstation 5 Pro GPU vs Intel Arc Pro B60 Dual Comparison

FAQ

Q: What are the core architectural differences between the AMD Playstation 5 Pro GPU and the Intel Arc Pro B60 Dual?

A: The AMD chip, codenamed Viola, uses RDNA 2.0 architecture and is built on a 4 nm process at TSMC. The Intel Arc Pro B60 Dual uses Xe2-HPG architecture (Battlemage generation) on a 5 nm process, also at TSMC. AMD integrates 21,000 million transistors on a 279 mm² die, while Intel packs 19,600 million transistors into a 272 mm² die.

Q: How do the memory configurations compare?

A: The AMD Playstation 5 Pro GPU has 16 GB of GDDR6 memory on a 256-bit bus, delivering 576.0 GB/s bandwidth. The Intel Arc Pro B60 Dual offers 24 GB of GDDR6 on a 192-bit bus, providing 456.0 GB/s. Despite the smaller bus, Intel's memory runs at 2375 MHz (19 Gbps effective) versus AMD's 2250 MHz (18 Gbps effective).

Q: Which GPU has higher raw compute throughput?

A: The AMD part delivers 18.05 TFLOPS FP32 and 36.10 TFLOPS FP16 (2:1), while the Intel card provides 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1). AMD holds a 47% advantage in FP32 and 47% in FP16.

Q: What are the display output capabilities?

A: The AMD Playstation 5 Pro GPU includes 1x HDMI 2.1 and 1x USB Type-C. The Intel Arc Pro B60 Dual provides 4x mini-DisplayPort 2.1 outputs. Neither lists a bus interface for AMD, while Intel uses PCIe 5.0 x8.

Q: What is the power consumption difference?

A: The AMD Playstation 5 Pro GPU is rated at 232 W TDP. The Intel Arc Pro B60 Dual has a 400 W TDP and requires an 800 W suggested PSU with a 1x 16-pin power connector. Intel's card is dual-slot, while AMD's slot width is not specified.

Q: When were these products released and at what launch MSRP?

A: The AMD Playstation 5 Pro GPU was released on 2024-11-06 with a launch MSRP of 699 USD. The Intel Arc Pro B60 Dual launched on 2025-09-04 with a launch MSRP of 1,199 USD.

Architecture Differences

The AMD Playstation 5 Pro GPU uses the Viola chip based on RDNA 2.0, a console-focused design from Sony's partnership. The Intel Arc Pro B60 Dual uses the BMG-G21 chip based on Xe2-HPG, representing Intel's Battlemage professional series. These are fundamentally different design philosophies: AMD's console GPU prioritizes balanced throughput within a fixed system, while Intel's pro card targets workstation flexibility.

The manufacturing processes differ. AMD uses TSMC's 4 nm node with a transistor density of 75.3M per mm², while Intel uses TSMC's 5 nm node with 72.1M per mm². AMD's die is slightly larger at 279 mm² versus 272 mm², and AMD packs more transistors (21,000 million versus 19,600 million).

Compute unit configurations diverge significantly. AMD fields 3840 shading units, 240 TMUs, and 64 ROPs. Intel counters with 2560 shading units, 160 TMUs, and 80 ROPs. Intel has a higher ROP count, which explains its superior pixel rate of 192.0 GPixel/s versus AMD's 150.4 GPixel/s. AMD's texture rate of 564.0 GTexel/s substantially exceeds Intel's 384.0 GTexel/s due to the higher TMU count.

Ray tracing support differs. Intel explicitly lists 20 RT cores, while AMD's RT core count is not specified in the database. API support also separates them: Intel supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while AMD lists DirectX as N/A and Vulkan 1.2. Both support OpenGL 4.6.

Clock behavior shows Intel's advantage in boost frequency. AMD runs at 2170 MHz base and 2350 MHz boost. Intel runs at 2000 MHz base but reaches 2400 MHz boost, a 50 MHz higher peak. Memory clocks favor Intel at 2375 MHz versus AMD's 2250 MHz.

Physical design differs considerably. The AMD card measures 386 mm in length, 216 mm in height, and 89 mm in width. The Intel card is shorter at 300 mm, lower at 110 mm, and thinner at 40 mm. Intel specifies a dual-slot form factor, while AMD's slot width is not recorded. Intel uses a 1x 16-pin power connector and suggests an 800 W PSU; AMD's power connectors and PSU recommendation are not listed.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark results between these two GPUs, and neither has an average benchmark score or nearest rival entries. The wins count is zero for both. However, the specification data allows for quantitative comparisons across several performance metrics.

In FP32 compute, AMD delivers 18.05 TFLOPS against Intel's 12.29 TFLOPS, a 47% advantage. This translates directly to general-purpose shader workloads where AMD's additional 1280 shading units provide a substantial throughput edge. The FP16 figures follow the same pattern: 36.10 TFLOPS versus 24.58 TFLOPS, again a 47% lead for AMD.

Texture throughput heavily favors AMD. With 240 TMUs at 2350 MHz boost, AMD achieves 564.0 GTexel/s. Intel's 160 TMUs at 2400 MHz produce only 384.0 GTexel/s. AMD's 47% TMU advantage results in a 47% texture rate advantage, which matters for games and applications that rely on heavy texture sampling.

Rasterization throughput tells the opposite story. Intel's 80 ROPs at 2400 MHz generate 192.0 GPixel/s, while AMD's 64 ROPs at 2350 MHz produce 150.4 GPixel/s. Intel leads by 28% in pixel fill rate, which can benefit high-resolution rendering and heavy overdraw scenarios.

Memory bandwidth favors AMD. The 256-bit bus combined with 2250 MHz memory yields 576.0 GB/s. Intel's 192-bit bus at 2375 MHz provides 456.0 GB/s. AMD's 26% bandwidth advantage supports its higher compute throughput in memory-bound workloads. However, Intel's 24 GB capacity versus AMD's 16 GB means Intel can hold larger datasets, beneficial for professional workloads like rendering scenes with large textures or AI inference batches.

The transistor density metric slightly favors AMD at 75.3M per mm² versus Intel's 72.1M per mm², indicating AMD uses the 4 nm process more efficiently per area. Both chips are active production parts with release dates roughly ten months apart: AMD on 2024-11-06 and Intel on 2025-09-04.

Power efficiency favors AMD. The 232 W TDP with 18.05 TFLOPS yields roughly 77.8 TFLOPS per kilowatt. Intel's 400 W TDP with 12.29 TFLOPS yields approximately 30.7 TFLOPS per kilowatt. AMD delivers over twice the compute per watt in this comparison.

The Verdict

The data positions these products for different roles despite similar transistor budgets. AMD's Playstation 5 Pro GPU leads in compute throughput, texture rate, memory bandwidth, and power efficiency. Intel's Arc Pro B60 Dual leads in pixel fill rate, memory capacity, display outputs, and API support breadth.

For raw shader performance, AMD's 47% FP32 and FP16 advantages make it the clear choice for compute-heavy workloads. The 564.0 GTexel/s texture rate supports this, indicating strong performance in games and applications that saturate texture units. The 576.0 GB/s bandwidth complements the high compute throughput, reducing memory bottlenecks.

For rasterization-heavy tasks, Intel's 192.0 GPixel/s pixel rate provides a 28% advantage. The 80 ROPs handle pixel output more efficiently, which can improve performance in geometry-heavy scenes, MSAA, and high-resolution rendering. The 24 GB memory capacity offers practical benefits for datasets that exceed 16 GB, including large textures or multi-model machine learning inference.

The launch MSRP figures place AMD at 699 USD and Intel at 1,199 USD. The database shows both at the 50th percentile among all GPUs, indicating mid-pack positioning overall. Intel's higher TDP of 400 W requires an 800 W suggested PSU, a significant system requirement compared to AMD's 232 W.

The production status for both is Active. AMD's console form factor (386 mm length) suggests integration into a fixed system, while Intel's dual-slot, 300 mm card with four mini-DisplayPort 2.1 outputs targets professional workstations. Intel's PCIe 5.0 x8 interface provides modern host connectivity, while AMD's bus interface is not specified.

Specification Differences

| Specification | AMD Playstation 5 Pro GPU | Intel Arc Pro B60 Dual |

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

| Architecture | RDNA 2.0 | Xe2-HPG |

| Process Node | 4 nm | 5 nm |

| Transistors | 21,000 million | 19,600 million |

| Die Size | 279 mm² | 272 mm² |

| Transistor Density | 75.3M / mm² | 72.1M / mm² |

| Base Clock | 2170 MHz | 2000 MHz |

| Boost Clock | 2350 MHz | 2400 MHz |

| Memory Clock | 2250 MHz 18 Gbps effective | 2375 MHz 19 Gbps effective |

| Memory Size | 16 GB | 24 GB |

| Memory Type | GDDR6 | GDDR6 |

| Memory Bus Width | 256 bit | 192 bit |

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

| Shading Units | 3840 | 2560 |

| TMUs | 240 | 160 |

| ROPs | 64 | 80 |

| RT Cores | Not specified | 20 |

| Pixel Rate | 150.4 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 564.0 GTexel/s | 384.0 GTexel/s |

| FP32 | 18.05 TFLOPS | 12.29 TFLOPS |

| FP16 | 36.10 TFLOPS (2:1) | 24.58 TFLOPS (2:1) |

| TDP | 232 W | 400 W |

| Slot Width | Not specified | Dual-slot |

| Power Connectors | Not specified | 1x 16-pin |

| Suggested PSU | Not specified | 800 W |

| Bus Interface | Not specified | PCIe 5.0 x8 |

| Display Outputs | 1x HDMI 2.1, 1x USB Type-C | 4x mini-DisplayPort 2.1 |

| DirectX | N/A | 12 Ultimate (12_2) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.2 | 1.4 |

| Length | 386 mm | 300 mm |

| Height | 216 mm | 110 mm |

| Width | 89 mm | 40 mm |

| Release Date | 2024-11-06 | 2025-09-04 |

| Launch MSRP | 699 USD | 1,199 USD |