Loading the catalog…
MI350X GPU - PID#253461430A (AMD)
Blurred values are subscriber-only. Sign in to start a free trial — 2 full pages a day — or subscribe for unlimited access.
| Process Node | TSMC 3nm/6nm FinFET |
|---|---|
| Multi Instance Support | Up to 8 @ 36 GB |
| Tdp W | 1000 |
| Peak Engine Clock Mhz | 2200 |
| Gpu Compute Units | 256 |
| Architecture | CDNA |
| Gpu Memory Gb | 288 |
| Memory Bandwidth Tb S | 8 |
| Memory Bus Width Bits | 8192 |
| Accelerator Form Factor | OAM |
| Host Interface | 1 PCIe® Gen 5 x16 (128 GB/s) |
| Memory Type | HBM3E |
| Interconnect | AMD Infinity Fabric™ Link, Universal Base Board (UBB 2.0) compatibility |
| Fp16 Bf16 Tflops Dense | 2309.6 |
| Fp8 Tflops Dense | 4614 |
| Fp16 Bf16 Tflops Sparse | 4619.2 |
| Fp32 Tflops | 144.2 |
| Int8 Tops Dense | 4614 |
| Amd Infinity Cache Last Level | |
| Fp4 Tflops Dense | |
| Fp64 Tflops | |
| Fp8 Tflops Sparse | |
| Int8 Tops Sparse |
|---|
| Matrix Cores |
|---|
| Media Engines |
|---|
| Product Name |
|---|
| Ras Features |
|---|
| Stream Processors |
|---|
| SKU | MI350X GPU - PID#253461430A |
|---|
| Product title | |
|---|---|
| Tagline | |
| Memory capacity (prose) | |
| Memory bandwidth (prose) | |
| Interconnect (prose) | |
| Expanded datatype support | |
| I/O DIES (IODS) | |
| SCALE-UP AMD INFINITY FABRIC™ LINKS | |
| Decoder footnote | |
| Multi-chip architecture - process | |
| Accelerated compute dies (XCDs) per OAM module | |
| Supported decoders (architecture detail) | |
| HBM3E memory (architecture detail) | |
| SR-IOV partitions | |
| Coherent shared memory bandwidth | |
| Security features | |
| Software stack | |
| Document ID | |
| Copyright | |
| AI PEAK THEORETICAL PERFORMANCE - FP16 VECTOR | |
| AI PEAK THEORETICAL PERFORMANCE - FP16 MATRIX | |
| AI PEAK THEORETICAL PERFORMANCE - BFLOAT16 | |
| AI PEAK THEORETICAL PERFORMANCE - INT8 MATRIX | |
| AI PEAK THEORETICAL PERFORMANCE - MXFP8 | |
| AI PEAK THEORETICAL PERFORMANCE - OCP-FP8 | |
| AI PEAK THEORETICAL PERFORMANCE - MXFP6 | |
| AI PEAK THEORETICAL PERFORMANCE - MXFP4 | |
| HPC PEAK THEORETICAL PERFORMANCE - FP64 VECTOR | |
| HPC PEAK THEORETICAL PERFORMANCE - FP32 VECTOR | |
| HPC PEAK THEORETICAL PERFORMANCE - FP64 MATRIX | |
| HPC PEAK THEORETICAL PERFORMANCE - FP32 MATRIX |
