AMD Radeon 8065S vs AMD Steam Deck OLED GPU Comparison

FAQ

Q: What are the architectural generations of the AMD Radeon 8065S and the AMD Steam Deck OLED GPU?

A: The AMD Radeon 8065S uses the RDNA 3.5 architecture with the Gorgon Halo chip, belonging to the Navi Mobile (RX 8000M) generation. The AMD Steam Deck OLED GPU uses the RDNA 2.0 architecture with the Sephiroth chip, belonging to the Console GPU (Valve) generation.

Q: How do the shading unit counts compare between the two GPUs?

A: The Radeon 8065S has 2560 shading units, while the Steam Deck OLED GPU has 512 shading units. This is a 5x difference in raw shader hardware, which directly impacts the FP32 compute throughput.

Q: What is the FP32 performance difference in TFLOPS?

A: The Radeon 8065S delivers 15.36 TFLOPS of FP32 compute, while the Steam Deck OLED GPU delivers 1.638 TFLOPS. The Radeon 8065S provides approximately 9.4 times the single-precision floating-point throughput.

Q: What memory configurations do the two GPUs use?

A: The Radeon 8065S uses System Shared memory with a system-dependent bus width and bandwidth. The Steam Deck OLED GPU uses 16 GB of LPDDR5 memory on a 128-bit bus with 176.0 GB/s of bandwidth.

Q: What are the process nodes for each chip?

A: The Radeon 8065S is fabricated on a 4 nm process at TSMC, while the Steam Deck OLED GPU is fabricated on a 6 nm process at TSMC. The Radeon 8065S has a die size of 308 mm², whereas the Steam Deck OLED GPU has a die size of 131 mm².

Q: How do the boost clocks compare?

A: The Radeon 8065S has a boost clock of 3000 MHz, while the Steam Deck OLED GPU has a boost clock of 1600 MHz. The Radeon 8065S also has a higher base clock at 1295 MHz versus 1000 MHz for the Steam Deck OLED GPU.

Architecture Differences

The Radeon 8065S and the Steam Deck OLED GPU represent two distinct design philosophies within AMD's mobile GPU lineup. The Radeon 8065S is built on the RDNA 3.5 architecture, the latest iteration in the Navi Mobile (RX 8000M) generation, while the Steam Deck OLED GPU relies on the older RDNA 2.0 architecture. This architectural gap directly translates into differences in feature support, compute capabilities, and efficiency characteristics.

The process technology differs substantially. The Radeon 8065S uses a 4 nm TSMC process, whereas the Steam Deck OLED GPU uses a 6 nm TSMC process. This process advantage, combined with a much larger die (308 mm² versus 131 mm²), allows the Radeon 8065S to pack significantly more hardware. The Steam Deck OLED GPU has 2,400 million transistors with a density of 18.3M per mm², while the Radeon 8065S transistor count is not recorded in the database.

The compute resources diverge sharply. The Radeon 8065S features 2560 shading units, 160 texture mapping units (TMUs), and 64 render output units (ROPs). The Steam Deck OLED GPU has only 512 shading units, 32 TMUs, and 16 ROPs. The ray tracing hardware follows the same pattern: 40 RT cores on the Radeon 8065S versus 8 RT cores on the Steam Deck OLED GPU. This represents a 5x advantage in shading units and TMUs, and a 4x advantage in ROPs and RT cores for the Radeon 8065S.

Clock behavior also differs. The Radeon 8065S operates at a base clock of 1295 MHz and boosts to 3000 MHz, a remarkably high boost frequency for a mobile part. The Steam Deck OLED GPU runs at a 1000 MHz base and 1600 MHz boost. The combination of more hardware and higher clocks results in a massive throughput gap.

Memory architecture is another fundamental difference. The Radeon 8065S uses System Shared memory, meaning its bandwidth and capacity depend entirely on the host system. The Steam Deck OLED GPU has dedicated 16 GB of LPDDR5 memory on a 128-bit bus, providing 176.0 GB/s of bandwidth. The Radeon 8065S memory clock is also listed as System Shared, while the Steam Deck OLED GPU memory operates at 1375 MHz with 11 Gbps effective data rate.

The API support shows a minor difference in Vulkan versions: the Radeon 8065S supports Vulkan 1.4, while the Steam Deck OLED GPU supports Vulkan 1.3. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The bus interface also differs, with the Radeon 8065S using PCIe 5.0 x16, while the Steam Deck OLED GPU has no bus interface recorded.

Power consumption is a significant differentiator. The Radeon 8065S has a thermal design power (TDP) of 55 W, while the Steam Deck OLED GPU has a TDP of 15 W. This 40 W difference reflects the Radeon 8065S's much higher performance ceiling and its design as an integrated graphics processor (IGP) for larger portable devices. The Steam Deck OLED GPU is designed for a handheld console form factor, as indicated by its physical dimensions of 298 mm length, 117 mm height, and 49 mm width.

Head-to-Head Benchmarks

The recorded data shows no direct head-to-head benchmark results between the Radeon 8065S and the Steam Deck OLED GPU, and both have an average benchmark score of zero. The database also lists no nearest rivals for either GPU. However, the specification-level comparisons provide clear performance indicators.

The pixel rate difference is substantial. The Radeon 8065S achieves 192.0 GPixel/s, while the Steam Deck OLED GPU achieves 25.60 GPixel/s. This means the Radeon 8065S can fill pixels at 7.5 times the rate of the Steam Deck OLED GPU. For rasterization-heavy workloads, this translates into the ability to drive much higher resolutions and frame rates.

Texture rate follows a similar pattern. The Radeon 8065S delivers 480.0 GTexel/s, while the Steam Deck OLED GPU delivers 51.20 GTexel/s. The Radeon 8065S is 9.4 times faster in texture filtering and sampling. This is particularly relevant for games that rely heavily on texture detail and anisotropic filtering.

The FP32 compute throughput shows the largest relative gap. The Radeon 8065S provides 15.36 TFLOPS, while the Steam Deck OLED GPU provides 1.638 TFLOPS. The Radeon 8065S has 9.4 times the single-precision compute capability. This affects compute-heavy effects such as physics simulations, particle systems, and post-processing shaders.

FP16 performance reveals an architectural difference in data handling. The Radeon 8065S achieves 15.36 TFLOPS in FP16 at a 1:1 ratio with FP32, meaning it processes half-precision and single-precision at the same rate. The Steam Deck OLED GPU achieves 3.277 TFLOPS in FP16 at a 2:1 ratio, meaning it doubles its throughput when using half-precision. Even with this advantage, the Steam Deck OLED GPU's FP16 throughput is only 21.3% of the Radeon 8065S's FP16 throughput.

The boost clock advantage of the Radeon 8065S, at 3000 MHz versus 1600 MHz for the Steam Deck OLED GPU, compounds the hardware count differences. The Radeon 8065S also has a higher base clock of 1295 MHz versus 1000 MHz. This clock advantage, combined with the 5x shading unit count, explains the roughly 9.4x throughput gap in both FP32 and texture rate.

The Radeon 8065S's memory bandwidth is system-dependent, which means its effective performance can vary based on the host platform's memory configuration. The Steam Deck OLED GPU has a fixed 176.0 GB/s of bandwidth from its dedicated LPDDR5 memory. In scenarios where the host system provides high-bandwidth memory, the Radeon 8065S could potentially exceed this figure, but this cannot be confirmed from the recorded data.

The Verdict

The data indicates a clear performance hierarchy. The Radeon 8065S is designed for substantially higher workloads, with 9.4 times the FP32 throughput of the Steam Deck OLED GPU. Its 55 W TDP, compared to 15 W for the Steam Deck OLED GPU, shows that it is intended for larger, more power-tolerant devices such as high-performance laptops or portable workstations. The Steam Deck OLED GPU, with its 15 W TDP and 16 GB of dedicated LPDDR5 memory, is optimized for a handheld console form factor where power efficiency and compactness are priorities.

The Radeon 8065S's RDNA 3.5 architecture provides Vulkan 1.4 support, while the Steam Deck OLED GPU's RDNA 2.0 architecture supports Vulkan 1.3. Both support DirectX 12 Ultimate and OpenGL 4.6, so feature-level compatibility for modern games is broadly similar. The Radeon 8065S's 40 RT cores versus 8 RT cores on the Steam Deck OLED GPU indicates a significantly higher ray tracing capacity, though the database does not include specific ray tracing benchmarks.

The Steam Deck OLED GPU's dedicated memory configuration offers a fixed 176.0 GB/s bandwidth, which is predictable and sufficient for its target resolution and frame rate envelope. The Radeon 8065S's system-shared memory approach means its bandwidth is dependent on the host platform, which could be either an advantage or a limitation depending on the system design.

The production status for both GPUs is listed as Active. The Radeon 8065S has a release date of December 31, 2025, while the Steam Deck OLED GPU has a release date of November 8, 2023. The Radeon 8065S lists its predecessor as Polaris Mobile, while the Steam Deck OLED GPU has no predecessor recorded.

The percentile versus all GPUs is 50 for both, indicating they sit at the median of the database's GPU distribution, though this figure does not account for the massive specification differences between the two. The Radeon 8065S is clearly positioned for users who need high compute throughput in a mobile form factor, while the Steam Deck OLED GPU is positioned for handheld gaming with constrained power and thermal budgets.

Specification Differences

• Architecture: RDNA 3.5 (Radeon 8065S) versus RDNA 2.0 (Steam Deck OLED GPU)
• Chip: Gorgon Halo (Radeon 8065S) versus Sephiroth (Steam Deck OLED GPU)
• Generation: Navi Mobile (RX 8000M) (Radeon 8065S) versus Console GPU (Valve) (Steam Deck OLED GPU)
• Process Node: 4 nm (Radeon 8065S) versus 6 nm (Steam Deck OLED GPU)
• Transistors: Not recorded (Radeon 8065S) versus 2,400 million (Steam Deck OLED GPU)
• Die Size: 308 mm² (Radeon 8065S) versus 131 mm² (Steam Deck OLED GPU)
• Transistor Density: Not recorded (Radeon 8065S) versus 18.3M per mm² (Steam Deck OLED GPU)
• Base Clock: 1295 MHz (Radeon 8065S) versus 1000 MHz (Steam Deck OLED GPU)
• Boost Clock: 3000 MHz (Radeon 8065S) versus 1600 MHz (Steam Deck OLED GPU)
• Memory Clock: System Shared (Radeon 8065S) versus 1375 MHz, 11 Gbps effective (Steam Deck OLED GPU)
• Memory Size: System Shared (Radeon 8065S) versus 16 GB (Steam Deck OLED GPU)
• Memory Type: System Shared (Radeon 8065S) versus LPDDR5 (Steam Deck OLED GPU)
• Memory Bus Width: System Shared (Radeon 8065S) versus 128 bit (Steam Deck OLED GPU)
• Memory Bandwidth: System Dependent (Radeon 8065S) versus 176.0 GB/s (Steam Deck OLED GPU)
• Shading Units: 2560 (Radeon 8065S) versus 512 (Steam Deck OLED GPU)
• TMUs: 160 (Radeon 8065S) versus 32 (Steam Deck OLED GPU)
• ROPs: 64 (Radeon 8065S) versus 16 (Steam Deck OLED GPU)
• RT Cores: 40 (Radeon 8065S) versus 8 (Steam Deck OLED GPU)
• Pixel Rate: 192.0 GPixel/s (Radeon 8065S) versus 25.60 GPixel/s (Steam Deck OLED GPU)
• Texture Rate: 480.0 GTexel/s (Radeon 8065S) versus 51.20 GTexel/s (Steam Deck OLED GPU)
• FP32 Throughput: 15.36 TFLOPS (Radeon 8065S) versus 1.638 TFLOPS (Steam Deck OLED GPU)
• FP16 Throughput: 15.36 TFLOPS at 1:1 ratio (Radeon 8065S) versus 3.277 TFLOPS at 2:1 ratio (Steam Deck OLED GPU)
• TDP: 55 W (Radeon 8065S) versus 15 W (Steam Deck OLED GPU)
• Slot Width: IGP (Radeon 8065S) versus not recorded (Steam Deck OLED GPU)
• Power Connectors: None (Radeon 8065S) versus not recorded (Steam Deck OLED GPU)
• Bus Interface: PCIe 5.0 x16 (Radeon 8065S) versus not recorded (Steam Deck OLED GPU)
• Display Outputs: Portable Device Dependent (Radeon 8065S) versus 1x USB Type-C (Steam Deck OLED GPU)
• Vulkan Version: 1.4 (Radeon 8065S) versus 1.3 (Steam Deck OLED GPU)
• Dimensions: Not recorded (Radeon 8065S) versus 298 mm length, 117 mm height, 49 mm width (Steam Deck OLED GPU)
• Release Date: December 31, 2025 (Radeon 8065S) versus November 8, 2023 (Steam Deck OLED GPU)
• Predecessor: Polaris Mobile (Radeon 8065S) versus not recorded (Steam Deck OLED GPU)