-
- Name
- AMD Instinct™ MI455X
- Family
- Instinct
- Series
- Instinct MI400 Series
- Launch Date
- 7/23/2026
-
- GPU Architecture
- CDNA5
- Lithography
- TSMC 2nm | 3nm FinFET
- Work Group Processors
- 256
- Peak Engine Clock
- 2400 MHz
- Peak OCP MXFP4 Performance
- 40.3 PFLOPs
- Peak OCP MXFP6 Performance
- 20.1 PFLOPs
- Peak OCP MXFP8 Performance
- 20.1 PFLOPs
- Peak OCP FP8 Performance
- 20.1 PFLOPs
- Peak Vector FP16 Performance
- 315 TFLOPs
- Peak Matrix FP16 Performance
- 5 PFLOPs
- Peak Matrix FP16 Performance with Structured Sparsity
- 10.1 PFLOPs
- Peak Matrix FP32 Performance
- 315 TFLOPs
- Peak Vector FP32 Performance
- 315 TFLOPs
- Peak Matrix FP64 Performance
- 5 TFLOPs
- Peak Vector FP64 Performance
- 5 TFLOPs
- Peak INT8 Matrix Performance
- 5 POPs
- Peak INT8 Matrix Performance with Structured Sparsity
- 10.1 POPs
- Peak bfloat16 (BF16) Matrix Performance
- 5 PFLOPs
- Peak bfloat16 (BF16) Matrix Performance with Structured Sparsity
- 10.1 PFLOPs
- Transistor Count
- 320 Billion
- OS Support
- Linux x86 64-Bit
-
- Dedicated Memory Size
- 432 GB
- Dedicated Memory Type
- HBM4
- L2 Cache
- 192 MB
- Stacks of Memory
- 12
- Peak Memory Bandwidth
- 23.3 TB/s
- Memory ECC Support
- Yes
-
- GPU Form Factor
- Enhanced Accelerator Module (EAM)
- Scale-up (Peak) UALoE Bi-directional Bandwidth
- 3.6 TB/s
- Scale-out (Peak) UALink™ Bi-directional Bandwidth
- 600 GB/s
- Scale-out Bus Type
- UALink™
- Cooling
- Direct Liquid Cooling (DLC)
-
- Supported Technologies
- AMD CDNA™ 5 Architecture , AMD ROCm™ - Ecosystem without Borders , UALink™, UALoE
- RAS Support
- Yes
- SR-IOV
- Yes
-
- OpenMP®
- Yes
- OpenCL™
- Yes
- HIP
- Yes
- ROCm™ Open Ecosystem
-
Yes
- Vulkan®
- No
-
- TensorFlow
- Yes
- PyTorch
- Yes
- ONYX-RT
- Yes
- SGLang
- Yes
- JAX
- Yes
- Triton
- Yes
- Kokkos
- Yes
- RAJA
- Yes
AMD Instinct™ MI455X GPUs
AMD Instinct™ MI455X is built on 5th Gen AMD CDNA™ architecture is design specifically for the AMD Helios™ rackscale solution offering leadership AI performance for frontier AI supporting modern AI capability for inference, training, and fine-tuning.
