AMD Radeon 8065S vs NVIDIA GeForce RTX 5090 D Comparison

Where Each One Wins

The recorded data paints a very one-sided picture. The NVIDIA GeForce RTX 5090 D wins every single benchmark category in which it has recorded results, while the AMD Radeon 8065S has no benchmark entries whatsoever in the database. This means the use-case split is not about choosing between two competitive options; it is about recognizing that the RTX 5090 D is the only one of the two with measurable performance data.

For the RTX 5090 D, its wins span the full range of graphics workloads. In synthetic DirectX testing, it records a Passmark DirectX 9 score of 434, a DirectX 10 score of 231, a DirectX 11 score of 371, and a DirectX 12 score of 219. These are not isolated wins; they cover legacy APIs and modern ones alike. The card also dominates compute-oriented tasks, with a Passmark GPU Compute score of 28,396 and a Geekbench OpenCL score of 310,674. For cross-platform graphics, the Geekbench Vulkan score reaches 376,915, indicating strong performance in Vulkan-based titles and applications.

The 3DMark Steel Nomad DX12 test, which is a more modern and demanding workload, shows a score of 14,326. This is a meaningful data point because it represents a current-generation benchmark rather than a legacy one. The RTX 5090 D also posts a Passmark G3D score of 44,065, which is the overall graphics score that aggregates several sub-tests. The Passmark G2D score of 1,487 covers 2D desktop and video workloads, where the card also performs well.

The AMD Radeon 8065S, by contrast, has zero recorded benchmarks and zero wins. Its percentile rank of 50 among all GPUs is a positional placeholder, not a performance result. Any use-case analysis for the 8065S must rely on its architectural specifications, not on measured performance. The data simply does not support a scenario where the 8065S wins any head-to-head comparison, because there are no head-to-head benchmark results in the database.

Architecture Differences

The two GPUs come from different architectural generations and are built for entirely different physical envelopes. The AMD Radeon 8065S uses the Gorgon Halo chip with RDNA 3.5 architecture, fabricated on a 4 nm process at TSMC. It is part of the Navi Mobile (RX 8000M) generation and is classified as an integrated graphics processor (IGP) with a slot width of "IGP" and no power connectors. Its die size is 308 mm². The chip contains 2,560 shading units, 160 texture mapping units, 64 raster output units, and 40 ray tracing cores. It has no dedicated tensor cores listed.

The NVIDIA GeForce RTX 5090 D uses the GB202 chip with Blackwell 2.0 architecture, also fabricated at TSMC but on a 5 nm process. It belongs to the GeForce 50-series and the GeForce 50 generation. The die is substantially larger at 750 mm² and contains 92,200 million transistors, giving a transistor density of 122.9 million per mm². The RTX 5090 D packs 21,760 shading units, 680 texture mapping units, 176 raster output units, 170 ray tracing cores, and 680 tensor cores. It is a dual-slot discrete card with a 1x 16-pin power connector and a suggested PSU of 950 W.

Memory architecture is where the two diverge most sharply. The 8065S uses system-shared memory with no dedicated VRAM, no fixed bus width, and bandwidth that is system dependent. Its memory clock is also listed as system shared. The RTX 5090 D, in contrast, has 32 GB of GDDR7 memory on a 512-bit bus, with 1.79 TB/s of bandwidth and a memory clock of 1750 MHz (28 Gbps effective). This is a fundamental difference: one GPU relies on the host system's memory, the other has a massive dedicated frame buffer.

Clock behavior also differs. The 8065S has a base clock of 1295 MHz and a boost clock of 3000 MHz, which is a large boost delta. The RTX 5090 D has a base clock of 2017 MHz and a boost of 2407 MHz, a much smaller relative boost. Pixel and texture rates follow the hardware counts: the 8065S delivers 192.0 GPixel/s and 480.0 GTexel/s, while the RTX 5090 D delivers 423.6 GPixel/s and 1,636.8 GTexel/s. FP32 compute is 15.36 TFLOPS for the 8065S versus 104.8 TFLOPS for the RTX 5090 D, both at 1:1 FP16 ratios.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and both use a PCIe 5.0 x16 bus interface. The 8065S has no fixed display outputs (portable device dependent), while the RTX 5090 D has 1x HDMI 2.1b and 3x DisplayPort 2.1b. Physical dimensions differ as well: the RTX 5090 D is 304 mm long, 137 mm tall, and 48 mm wide, while the 8065S has no listed dimensions because it is an IGP.

Head-to-Head Benchmarks

There are no head-to-head benchmark results in the database, and the RTX 5090 D is the only one of the two with any recorded scores. The wins count is 0 for the 8065S and 0 for the RTX 5090 D in the head-to-head field, but that is because no paired tests were run. The RTX 5090 D's individual scores, however, provide a reference point.

The largest single-score advantage comes in compute. The Geekbench OpenCL score of 310,674 and Geekbench Vulkan score of 376,915 are both massive numbers when compared against the 8065S's zero recorded results. For pure rasterization, the Passmark G3D score of 44,065 is the aggregate measure. The 3DMark Steel Nomad DX12 score of 14,326 is a modern DirectX 12 workload, and it shows the card's current-generation capability.

In legacy API tests, the RTX 5090 D posts a DirectX 9 score of 434, which is its highest Passmark API score. DirectX 11 comes in at 371, DirectX 10 at 231, and DirectX 12 at 219. These numbers are useful for understanding that the card does not lose performance in older APIs, which is a common concern for newer architectures. The Passmark GPU Compute score of 28,396 is separate from the graphics API tests and reflects GPGPU workloads.

The 8065S has no scores to compare, so the only meaningful statement is that the RTX 5090 D's recorded data stands alone. The 8065S's percentile rank of 50 is not a benchmark result; it is a database position. The RTX 5090 D's percentile rank of 92 places it above the vast majority of GPUs in the database, and its average benchmark score of 77,712 is the aggregate number used for ranking.

The nearest rivals for the RTX 5090 D are all other GPUs, not the 8065S. The AMD Radeon RX 6650M XT scores 76,904 with a delta of +1.1%, meaning the RTX 5090 D is slightly ahead. The AMD Radeon RX 6850M XT scores 78,940 with a delta of -1.6%, meaning the RTX 5090 D is slightly behind. The NVIDIA Tesla P100 PCIe 12 GB scores 79,396 with a delta of -2.1%, and the Tesla P100 PCIe 16 GB scores 79,605 with a delta of -2.4%. These deltas show that the RTX 5090 D sits in a tight cluster with these rival cards, within a few percentage points either way, despite its much higher absolute specifications.

The Verdict

From the data, the choice is straightforward for anyone who needs measured performance: the NVIDIA GeForce RTX 5090 D is the only option with benchmark results, and those results are extensive. It covers DirectX 9 through DirectX 12, OpenCL, Vulkan, and 3DMark Steel Nomad. Its 92nd percentile ranking and average score of 77,712 put it in the top tier of the database. The card is a dual-slot, 575 W discrete GPU with 32 GB of GDDR7 memory and 1.79 TB/s of bandwidth, which makes it suitable for high-resolution gaming, heavy compute, and workstation-class tasks.

The AMD Radeon 8065S is a different kind of product entirely. It is an integrated GPU with system-shared memory, a 55 W TDP, and no power connectors. Its 2,560 shading units and 15.36 TFLOPS of FP32 compute are respectable for an IGP, but there are no recorded benchmarks to validate real-world performance. Its 50th percentile rank is not a performance claim; it is a placeholder. For a portable device or a low-power system, the 8065S may be adequate, but the database cannot confirm that with numbers.

The practical verdict is that the RTX 5090 D is for users who need maximum measured graphics and compute performance, with the power budget and physical space to accommodate a 575 W, 304 mm dual-slot card. The 8065S is for users who need an integrated solution in a portable device, where the lack of discrete memory and power connectors is a feature rather than a drawback. The data does not support any scenario where the 8065S competes with the RTX 5090 D on performance.

FAQ

Q: Does the AMD Radeon 8065S have any benchmark scores in the database?

A: No. The 8065S has zero recorded benchmark results, while the RTX 5090 D has ten separate scores across different test suites.

Q: What is the memory configuration of the NVIDIA GeForce RTX 5090 D?

A: It has 32 GB of GDDR7 memory on a 512-bit bus, with 1.79 TB/s of bandwidth and a memory clock of 1750 MHz (28 Gbps effective).

Q: How does the AMD Radeon 8065S handle memory?

A: It uses system-shared memory with no dedicated VRAM, no fixed bus width, and bandwidth that is system dependent.

Q: What is the highest single benchmark score for the RTX 5090 D?

A: The Geekbench Vulkan score of 376,915 is the highest recorded result, followed by the Geekbench OpenCL score of 310,674.

Q: Which GPUs are the nearest rivals to the RTX 5090 D?

A: The AMD Radeon RX 6650M XT (delta +1.1%), AMD Radeon RX 6850M XT (delta -1.6%), NVIDIA Tesla P100 PCIe 12 GB (delta -2.1%), and NVIDIA Tesla P100 PCIe 16 GB (delta -2.4%).

Q: What is the TDP difference between the two cards?

A: The RTX 5090 D has a TDP of 575 W with a suggested PSU of 950 W, while the 8065S has a TDP of 55 W and uses no power connectors.

Specification Differences

| Specification | AMD Radeon 8065S | NVIDIA GeForce RTX 5090 D |

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

| Architecture | RDNA 3.5 | Blackwell 2.0 |

| Process Node | 4 nm | 5 nm |

| Die Size | 308 mm² | 750 mm² |

| Transistors | unknown | 92,200 million |

| Transistor Density | not listed | 122.9M / mm² |

| Base Clock | 1295 MHz | 2017 MHz |

| Boost Clock | 3000 MHz | 2407 MHz |

| Memory Size | System Shared | 32 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 512 bit |

| Memory Bandwidth | System Dependent | 1.79 TB/s |

| Shading Units | 2560 | 21760 |

| Texture Mapping Units | 160 | 680 |

| Raster Output Units | 64 | 176 |

| Ray Tracing Cores | 40 | 170 |

| Tensor Cores | not listed | 680 |

| Pixel Rate | 192.0 GPixel/s | 423.6 GPixel/s |

| Texture Rate | 480.0 GTexel/s | 1,636.8 GTexel/s |

| FP32 Compute | 15.36 TFLOPS | 104.8 TFLOPS |

| TDP | 55 W | 575 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 16-pin |

| Suggested PSU | not listed | 950 W |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Length | not listed | 304 mm |

| Height | not listed | 137 mm |

| Width | not listed | 48 mm |

| Release Date | 2025-12-31 | 2025-01-29 |

| Predecessor | Polaris Mobile | GeForce 40 |

| Successor | not listed | GeForce 60 |

| Launch MSRP | not listed | 2,299 USD |