AMD Radeon 8065S vs NVIDIA GeForce RTX 5090 D V2 Comparison

FAQ

Q: What is the AMD Radeon 8065S based on?

A: The AMD Radeon 8065S uses the Gorgon Halo chip built on RDNA 3.5 architecture, manufactured on a 4 nm process at TSMC. It belongs to the Navi Mobile (RX 8000M) generation and is an integrated graphics processor (IGP) with a 55 W TDP.

Q: What are the key specifications of the NVIDIA GeForce RTX 5090 D V2?

A: The RTX 5090 D V2 is part of the GeForce 50-series, using the GB202 chip on Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It contains 92,200 million transistors on a 750 mm² die, features 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth, and has a 575 W TDP. Its launch MSRP is 2,299 USD.

Q: How do the two GPUs compare in raw compute throughput?

A: The RTX 5090 D V2 delivers 104.8 TFLOPS of FP32 performance, which is substantially higher than the Radeon 8065S's 15.36 TFLOPS. The NVIDIA part also has far more shading units (21,760 vs. 2,560) and texture mapping units (680 vs. 160).

Q: What memory configuration does the AMD Radeon 8065S use?

A: The Radeon 8065S uses system-shared memory, meaning its memory size, type, bus width, and bandwidth are all system-dependent and not fixed specifications. This contrasts with the dedicated 24 GB GDDR7 memory on the RTX 5090 D V2.

Q: Which GPU has higher ray tracing capability?

A: The RTX 5090 D V2 has 170 ray tracing cores, while the Radeon 8065S has 40. Additionally, the NVIDIA part includes 680 tensor cores, whereas the AMD part does not list any tensor cores.

Q: What is the recorded benchmark score for the RTX 5090 D V2?

A: The RTX 5090 D V2 scored 16,504 in the 3DMark Steel Nomad DX12 test. Its average benchmark score is also 16,504, placing it in the 59th percentile of all GPUs. The Radeon 8065S has no recorded benchmark scores and sits at the 50th percentile.

The Verdict

The data presents a stark contrast between an integrated GPU and a flagship discrete part. The AMD Radeon 8065S is designed for low-power mobile systems, with a 55 W TDP, no power connectors, and an IGP form factor that uses shared system memory. Its 15.36 TFLOPS FP32 throughput and 2,560 shading units target mainstream, power-constrained workloads rather than high-end gaming or compute.

The NVIDIA GeForce RTX 5090 D V2 is a dual-slot, 575 W discrete card with a 16-pin power connector and a suggested 950 W power supply. It offers 104.8 TFLOPS FP32 performance, 24 GB of GDDR7 memory, and 170 ray tracing cores. The benchmark data confirms its position: scoring 16,504 in 3DMark Steel Nomad DX12 places it at the 59th percentile of all GPUs, with nearest rivals including the NVIDIA T400 (16,508, 0% delta) and AMD Radeon PRO W7500 (16,415, 0.5% delta). These rival scores show the RTX 5090 D V2 performs within 0.9% of the Radeon RX 5700 XT, indicating that its mid-tier percentile ranking reflects strong but not top-tier benchmark outcomes for such a high-end part.

For users requiring dedicated graphics memory, high pixel throughput (423.6 GPixel/s vs. 192.0 GPixel/s), and massive shader counts, the RTX 5090 D V2 is the clear choice based on recorded data. The Radeon 8065S suits systems where power draw, physical size, and integrated simplicity matter more than peak compute. Given the absence of benchmark scores for the AMD part, direct performance comparisons cannot be made from the database; the verdict relies on specification differences.

Head-to-Head Benchmarks

No head-to-head benchmark data exists between the AMD Radeon 8065S and the NVIDIA GeForce RTX 5090 D V2 in the database. The wins count is 0 for both sides, and the headToHeadBenchmarks list is empty. Therefore, any comparative performance analysis must rely on the RTX 5090 D V2's single benchmark result and the specification sheets.

The RTX 5090 D V2's 3DMark Steel Nomad DX12 score of 16,504 stands alone as the only recorded benchmark. Its nearest rivals in the database are the NVIDIA T400 at 16,508 (a 0% delta), the AMD Radeon PRO W7500 at 16,415 (0.5% behind), the NVIDIA RTX PRO 6000 Blackwell at 16,408 (0.6% behind), and the AMD Radeon RX 5700 XT at 16,361 (0.9% behind). This clustering indicates that the RTX 5090 D V2's measured performance is essentially tied with these four cards, despite the vast specification differences among them.

For the Radeon 8065S, the database lists no benchmarks, no average score, and no nearest rivals. The percentileVsAllGpus field shows 50, meaning it sits at the median of all GPUs in the database, but this is not tied to any measured score. Consequently, the head-to-head section cannot report numerical wins or deltas for the AMD part. What the data does show is that the RTX 5090 D V2, despite its high-end specifications, achieves a benchmark score that places it only slightly above the 50th percentile (59th), suggesting that its real-world performance in this specific test does not massively outstrip older or lower-tier parts.

Specification Differences

The two GPUs differ across nearly every measurable field. The AMD Radeon 8065S has a base clock of 1295 MHz and a boost clock of 3000 MHz, while the NVIDIA GeForce RTX 5090 D V2 runs at 2017 MHz base and 2407 MHz boost. The AMD part's memory is system-shared, whereas the NVIDIA part uses 24 GB of GDDR7 with a 384-bit bus and 1.34 TB/s bandwidth. The memory clock is listed as 1750 MHz with 28 Gbps effective for the NVIDIA card, while the AMD card's memory clock is system-dependent.

Shading units differ dramatically: 2,560 on the Radeon 8065S versus 21,760 on the RTX 5090 D V2. Texture mapping units are 160 versus 680, and ROPs are 64 versus 176. Ray tracing cores are 40 versus 170, and the NVIDIA part has 680 tensor cores while the AMD part has none listed. Pixel rate is 192.0 GPixel/s for AMD versus 423.6 GPixel/s for NVIDIA. Texture rate is 480.0 GTexel/s versus 1,636.8 GTexel/s. FP32 and FP16 throughput are both 15.36 TFLOPS (1:1) for AMD, and both 104.8 TFLOPS (1:1) for NVIDIA.

TDP is 55 W for the Radeon 8065S versus 575 W for the RTX 5090 D V2. The AMD part is an IGP with no power connectors, while the NVIDIA part is dual-slot with a single 16-pin connector and a suggested 950 W PSU. Dimensions: the AMD card has no listed length, height, or width; the NVIDIA card measures 304 mm by 137 mm by 48 mm. Display outputs are portable-device-dependent for AMD, while NVIDIA provides 1x HDMI 2.1b and 3x DisplayPort 2.1b. The bus interface is PCIe 5.0 x16 for both. The process node is 4 nm for AMD and 5 nm for NVIDIA, both from TSMC. Die size is 308 mm² for AMD versus 750 mm² for NVIDIA. Transistor count is unknown for AMD versus 92,200 million for NVIDIA; transistor density is not listed for AMD but is 122.9M per mm² for NVIDIA. Release dates differ: 2025-12-31 for AMD versus 2025-08-14 for NVIDIA. The predecessor is Polaris Mobile for AMD and GeForce 40 for NVIDIA; the successor is null for AMD and GeForce 60 for NVIDIA.

Architecture Differences

The AMD Radeon 8065S uses RDNA 3.5 architecture on the Gorgon Halo chip, belonging to the Navi Mobile (RX 8000M) generation. The NVIDIA GeForce RTX 5090 D V2 uses Blackwell 2.0 architecture on the GB202 chip, part of the GeForce 50 generation. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API-level feature compatibility is identical.

The most significant architectural distinction is the core composition. The AMD part has 2,560 shading units, 160 TMUs, and 64 ROPs, with 40 ray tracing cores and no tensor cores. The NVIDIA part has 21,760 shading units, 680 TMUs, and 176 ROPs, with 170 ray tracing cores and 680 tensor cores. This means the NVIDIA architecture dedicates far more silicon to parallel shading and ray tracing, while also adding dedicated tensor hardware for AI workloads. The AMD architecture, by contrast, relies on a smaller, power-efficient design without tensor acceleration, reflecting its integrated, low-power positioning.

Memory architecture differs fundamentally. The AMD Radeon 8065S shares system memory, making bandwidth and capacity dependent on the host platform. The NVIDIA RTX 5090 D V2 has dedicated GDDR7 memory with a fixed 384-bit bus and 1.34 TB/s bandwidth, independent of the rest of the system. The transistor counts highlight the scale gap: 92,200 million on the NVIDIA die versus an unknown count on the AMD die, with die sizes of 750 mm² and 308 mm² respectively. The process nodes also differ, with AMD using a 4 nm process and NVIDIA using a 5 nm process, both at TSMC, meaning the AMD part achieves higher transistor density per area despite its smaller die. Production status is Active for both, with the AMD part listed as a successor to Polaris Mobile and the NVIDIA part as a successor to GeForce 40.