AMD Instinct MI355X vs NVIDIA GeForce RTX 5090 D Comparison

Head-to-Head Benchmarks

The database contains benchmark results for the NVIDIA GeForce RTX 5090 D, while the AMD Instinct MI355X has no recorded benchmark entries. The RTX 5090 D holds a 92nd percentile ranking among all GPUs in the database, with an average benchmark score of 77,712. Its nearest rivals in the database include the AMD Radeon RX 6650M XT, which scores 76,904 and sits 1.1% behind, and the AMD Radeon RX 6850M XT, which scores 78,940 and leads by 1.6%. The NVIDIA Tesla P100 PCIe 12 GB and 16 GB variants score 79,396 and 79,605 respectively, placing them 2.1% and 2.4% ahead of the RTX 5090 D in the recorded data.

For the RTX 5090 D specifically, the 3DMark Steel Nomad DX12 test yields a score of 14,326. Geekbench OpenCL returns 310,674, and Geekbench Vulkan returns 376,915. PassMark results show a G3D score of 44,065 and a GPU compute score of 28,396. The lower-level PassMark tests record 231 for DirectX 10, 371 for DirectX 11, 219 for DirectX 12, and 434 for DirectX 9. The 2D graphics test scores 1,487.

The MI355X has no benchmark scores, no wins recorded, and no nearest rivals listed in the database. The head-to-head benchmark comparison table is empty. This means no direct performance comparison can be made from measured data between these two products. The RTX 5090 D stands as a measured performer with concrete scores, while the MI355X remains unmeasured in the database. The percentile ranking for the MI355X is 50, which places it at the midpoint of all GPUs in the database, but this ranking is not supported by any actual benchmark entries, so it should be treated as a placeholder rather than a verified performance indicator.

Architecture Differences

The AMD Instinct MI355X uses the CDNA 4.0 architecture, built on the MI350 256CU chip. It is manufactured on a 3 nm process at TSMC. The NVIDIA GeForce RTX 5090 D uses the Blackwell 2.0 architecture, built on the GB202 chip, and is manufactured on a 5 nm process, also at TSMC. The MI355X integrates 185,000 million transistors on a 2,380 mm² die, giving a transistor density of 77.7 million per mm². The RTX 5090 D integrates 92,200 million transistors on a 750 mm² die, yielding a higher transistor density of 122.9 million per mm².

Memory architectures differ substantially. The MI355X uses 288 GB of HBM3e memory on an 8,192-bit bus, delivering 8.19 TB/s of bandwidth. The RTX 5090 D uses 32 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The MI355X has 16,384 shading units and 1,024 texture mapping units, with no ROPs, no RT cores, and no tensor cores listed. The RTX 5090 D has 21,760 shading units, 680 TMUs, 176 ROPs, 170 RT cores, and 680 tensor cores.

The MI355X reports a pixel rate of 0 MPixel/s and a texture rate of 2,457.6 GTexel/s. FP32 performance is 78.64 TFLOPS, and FP16 performance is also 78.64 TFLOPS with a 1:1 ratio. The RTX 5090 D reports a pixel rate of 423.6 GPixel/s and a texture rate of 1,636.8 GTexel/s. FP32 performance is 104.8 TFLOPS, and FP16 performance is 104.8 TFLOPS with a 1:1 ratio. The RTX 5090 D has higher raw FP32 and FP16 throughput, while the MI355X has a higher texture rate.

Clock speeds also differ. The MI355X has a base clock of 1000 MHz and a boost clock of 2400 MHz, with memory clocked at 2000 MHz (8 Gbps effective). The RTX 5090 D has a base clock of 2017 MHz and a boost clock of 2407 MHz, with memory clocked at 1750 MHz (28 Gbps effective). The RTX 5090 D runs at significantly higher base and boost clocks, while the MI355X relies on a wider memory bus and larger memory pool.

API support is another major divider. The MI355X lists DirectX, OpenGL, and Vulkan as N/A, meaning it has no consumer graphics API support in the recorded data. The RTX 5090 D supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI355X also has no display outputs, while the RTX 5090 D provides 1x HDMI 2.1b and 3x DisplayPort 2.1b.

FAQ

Q: Which GPU has more memory bandwidth?

A: The AMD Instinct MI355X delivers 8.19 TB/s of bandwidth from 288 GB of HBM3e memory on an 8,192-bit bus. The NVIDIA GeForce RTX 5090 D delivers 1.79 TB/s from 32 GB of GDDR7 memory on a 512-bit bus.

Q: Does the MI355X support DirectX or Vulkan?

A: No. The database lists DirectX, OpenGL, and Vulkan support as N/A for the MI355X. The RTX 5090 D supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the power consumption difference?

A: The MI355X has a TDP of 1400 W and a suggested PSU of 1800 W. The RTX 5090 D has a TDP of 575 W and a suggested PSU of 950 W.

Q: Which GPU has more shading units?

A: The RTX 5090 D has 21,760 shading units, while the MI355X has 16,384 shading units.

Q: What are the release dates for these products?

A: The MI355X was released on June 11, 2025. The RTX 5090 D was released on January 29, 2025.

Q: Does the MI355X have any display outputs?

A: No. The MI355X lists no display outputs. The RTX 5090 D has 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Specification Differences

| Specification | AMD Instinct MI355X | NVIDIA GeForce RTX 5090 D |

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

| Architecture | CDNA 4.0 | Blackwell 2.0 |

| Process Node | 3 nm | 5 nm |

| Transistors | 185,000 million | 92,200 million |

| Die Size | 2380 mm² | 750 mm² |

| Transistor Density | 77.7M / mm² | 122.9M / mm² |

| Base Clock | 1000 MHz | 2017 MHz |

| Boost Clock | 2400 MHz | 2407 MHz |

| Memory Size | 288 GB | 32 GB |

| Memory Type | HBM3e | GDDR7 |

| Memory Bus Width | 8192 bit | 512 bit |

| Memory Bandwidth | 8.19 TB/s | 1.79 TB/s |

| Shading Units | 16384 | 21760 |

| TMUs | 1024 | 680 |

| ROPs | 0 | 176 |

| RT Cores | None listed | 170 |

| Tensor Cores | None listed | 680 |

| Pixel Rate | 0 MPixel/s | 423.6 GPixel/s |

| Texture Rate | 2,457.6 GTexel/s | 1,636.8 GTexel/s |

| FP32 | 78.64 TFLOPS | 104.8 TFLOPS |

| FP16 | 78.64 TFLOPS (1:1) | 104.8 TFLOPS (1:1) |

| TDP | 1400 W | 575 W |

| Slot Width | OAM Module | Dual-slot |

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

| Suggested PSU | 1800 W | 950 W |

| Display Outputs | No outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

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

| OpenGL Support | N/A | 4.6 |

| Vulkan Support | N/A | 1.4 |

| Release Date | 2025-06-11 | 2025-01-29 |

| Predecessor | Radeon Instinct | GeForce 40 |

| Successor | None listed | GeForce 60 |

| Production Status | Not listed | Active |

The Verdict

The data shows two fundamentally different products with almost no overlap in intended use. The NVIDIA GeForce RTX 5090 D is a measured performer with a 92nd percentile ranking, an average benchmark score of 77,712, and concrete scores across DirectX, Vulkan, OpenCL, and PassMark tests. It supports consumer graphics APIs, has display outputs, and fits in a dual-slot form factor with a 575 W TDP. The AMD Instinct MI355X has no benchmark scores, no API support, no display outputs, and is an OAM module with a 1400 W TDP. Its 50th percentile ranking is not backed by any recorded benchmarks.

For anyone needing a GPU for graphics workloads, gaming, or any application that requires DirectX, Vulkan, or OpenGL, the RTX 5090 D is the only viable choice from this comparison. It also has higher FP32 and FP16 throughput at 104.8 TFLOPS each, compared to 78.64 TFLOPS for the MI355X. The RTX 5090 D also has RT cores and tensor cores, which the MI355X lacks entirely.

For workloads that prioritize memory capacity and bandwidth, the MI355X offers 288 GB of HBM3e at 8.19 TB/s, which is nine times the capacity and more than four times the bandwidth of the RTX 5090 D. The MI355X also has a higher texture rate at 2,457.6 GTexel/s versus 1,636.8 GTexel/s. These characteristics point toward data-center compute or large-scale inference tasks where graphics output and consumer API support are irrelevant.

The RTX 5090 D has a launch MSRP of 2,299 USD. No launch MSRP is listed for the MI355X. The production status of the RTX 5090 D is Active, while the MI355X has no production status recorded.

Where Each One Wins

The RTX 5090 D wins in every measured benchmark category because it is the only product with benchmark data. It wins on FP32 and FP16 compute throughput, pixel rate, shading unit count, and clock speeds. It has RT cores and tensor cores for ray tracing and AI acceleration. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it suitable for graphics applications. Its dual-slot design and 575 W TDP are more practical for conventional PC builds, and it includes display outputs for direct monitor connection.

The MI355X wins on memory capacity and bandwidth. Its 288 GB of HBM3e with 8.19 TB/s bandwidth dwarfs the 32 GB GDDR7 with 1.79 TB/s on the RTX 5090 D. It also has a higher texture rate and a wider memory bus at 8,192 bit versus 512 bit. Its larger die size of 2,380 mm² and higher transistor count of 185,000 million indicate a design focused on massive parallel compute. The 3 nm process node is more advanced than the 5 nm node used by the RTX 5090 D, though the RTX 5090 D achieves higher transistor density.

In practical terms, the RTX 5090 D is the choice for any workload that requires graphics output, consumer API support, or a conventional power and cooling setup. The MI355X is the choice for memory-bound compute workloads that can use an OAM module, tolerate a 1400 W TDP, and do not need display output or consumer graphics APIs. The data does not support any claim of the MI355X outperforming the RTX 5090 D in measured benchmarks, because no measurements exist for the MI355X. The RTX 5090 D is the only product in this comparison with verified performance data.