AMD Instinct™ MI300X Accelerators

AMD Instinct™ MI300X accelerators are designed to deliver leadership performance for Generative AI workloads and HPC applications.

AMD ROCm™ Software

Optimize GPU-accelerated applications with AMD ROCm™ software. Built on a code-once, use-everywhere approach.

ROCm Developer Hub About ROCm

AMD CDNA™ Architecture

Learn more about the architecture that underlies AMD Instinct accelerators.

Discover CDNA

AMD Instinct Documentation

Find documentation about AMD Instinct accelerators on the Documentation Hub.

MI300X Platform Data Sheet See Docs

Footnotes

MI300-17: Measurements conducted by AMD Performance Labs as of November 11th, 2023 on the AMD Instinct™ MI300X (750W) GPU designed with AMD CDNA™ 3 5nm | 6nm FinFET process technology at 2,100 MHz peak boost engine clock resulted in 653.7 TFLOPS peak theoretical TensorFloat-32 (TF32), 1307.4 TFLOPS peak theoretical half precision (FP16), 1307.4 TFLOPS peak theoretical Bfloat16 format precision (BF16), 2614.9 TFLOPS peak theoretical 8-bit precision (FP8), 2614.9 TOPs INT8 floating-point performance. The MI300X is expected to be able to take advantage of fine-grained structure sparsity providing an estimated 2x improvement in math efficiency resulting 1,307.4 TFLOPS peak theoretical TensorFloat-32 (TF32), 2,614.9 TFLOPS peak theoretical half precision (FP16), 2,614.9 TFLOPS peak theoretical Bfloat16 format precision (BF16), 5,229.8 TFLOPS peak theoretical 8-bit precision (FP8), 5,229.8 TOPs INT8 floating-point performance with sparsity. Published results on Nvidia H100 SXM (80GB) 700W GPU resulted in 989.4 TFLOPs peak TensorFloat-32 (TF32) with sparsity, 1,978.9 TFLOPS peak theoretical half precision (FP16) with sparsity, 1,978.9 TFLOPS peak theoretical Bfloat16 format precision (BF16) with sparsity, 3,957.8 TFLOPS peak theoretical 8-bit precision (FP8) with sparsity, 3,957.8 TOPs peak theoretical INT8 with sparsity floating-point performance. Nvidia H100 source: https://resources.nvidia.com/en-us-tensor-core.
MI300-18: Measurements conducted by AMD Performance Labs as of November 11th, 2023 on the AMD Instinct™ MI300X (750W) GPU designed with AMD CDNA™ 3 5nm | 6nm FinFET process technology at 2,100 MHz peak boost engine clock resulted in 163.4 TFLOPs peak theoretical double precision Matrix (FP64 Matrix), 81.7 TFLOPs peak theoretical double precision (FP64), 163.4 TFLOPs peak theoretical single precision Matrix (FP32 Matrix), 163.4 TFLOPs peak theoretical single precision (FP32), 653.7 TFLOPS peak theoretical TensorFloat-32 (TF32), 1307.4 TFLOPS peak theoretical half precision (FP16), 1307.4 TFLOPS peak theoretical Bfloat16 format precision (BF16), 2614.9 TFLOPS peak theoretical 8-bit precision (FP8), 2614.9 TOPs INT8 floating-point performance. Published results on Nvidia H100 SXM (80GB) GPU resulted in 66.9 TFLOPs peak theoretical double precision tensor (FP64 Tensor), 33.5 TFLOPs peak theoretical double precision (FP64), 66.9 TFLOPs peak theoretical single precision (FP32), 494.7 TFLOPs peak TensorFloat-32 (TF32)*, 989.4 TFLOPS peak theoretical half precision tensor (FP16 Tensor), 133.8 TFLOPS peak theoretical half precision (FP16), 989.4 TFLOPS peak theoretical Bfloat16 tensor format precision (BF16 Tensor), 133.8 TFLOPS peak theoretical Bfloat16 format precision (BF16), 1,978.9 TFLOPS peak theoretical 8-bit precision (FP8), 1,978.9 TOPs peak theoretical INT8 floating-point performance. Nvidia H100 source: https://resources.nvidia.com/en-us-tensor-core/ * Nvidia H100 GPUs don’t support FP32 Tensor.
MI300-05A: Calculations conducted by AMD Performance Labs as of November 17, 2023, for the AMD Instinct™ MI300X OAM accelerator 750W (192 GB HBM3) designed with AMD CDNA™ 3 5nm FinFet process technology resulted in 192 GB HBM3 memory capacity and 5.325 TFLOPS peak theoretical memory bandwidth performance. MI300X memory bus interface is 8,192 and memory data rate is 5.2 Gbps for total peak memory bandwidth of 5.325 TB/s (8,192 bits memory bus interface * 5.2 Gbps memory data rate/8). The highest published results on the NVidia Hopper H200 (141GB) SXM GPU accelerator resulted in 141GB HBM3e memory capacity and 4.8 TB/s GPU memory bandwidth performance. https://nvdam.widen.net/s/nb5zzzsjdf/hpc-datasheet-sc23-h200-datasheet-3002446 The highest published results on the NVidia Hopper H100 (80GB) SXM5 GPU accelerator resulted in 80GB HBM3 memory capacity and 3.35 TB/s GPU memory bandwidth performance. https://resources.nvidia.com/en-us-tensor-core/nvidia-tensor-core-gpu-datasheet

Data Center

Business Systems

Personal & Gaming

Embedded

Resources

GPU Accelerators

Adaptive Accelerators

DPU Accelerators

Ethernet Adapters

Workstations

Desktops

Laptops

Resources

Adaptive SoCs & FPGAs

System-on-Modules (SOMs)

Technologies

Resources

Evaluation Boards & Kits

Processor Tools

Graphics Tools & Apps

Adaptive SoC & FPGA Tools

Intellectual Property & Apps

GPU Accelerator Tools & Apps

Overview

For Data Center & Cloud

For Edge & Endpoints

For Developers

Industries

Industries

Industries

Industries

Industries

Workloads

Gaming

Systems

Technologies

Resources

EPYC Processors

Radeon Graphics & AMD Chipsets

Adaptive SoCs & FPGAs

Alveo Accelerators & Kria SOMs

Ryzen Processors

Ethernet Adapters

Overview

Processors

Accelerators

Adaptive SoCs, FPGAs, & SOMs

Graphics

Overview

Resources by Market Segment

Resources by Product

Resources by Type

About Our Partners

AMD Global Support

Processors & Graphics

Accelerators

Adaptive SoCs & FPGAs

Gaming & Personal Computing

Adaptive & Embedded Computing

Get AMD Fan Gear

Shop Our Retail Partners

AMD Instinct™ MI300X Accelerators

Specs Comparisons

AI Performance (Peak TFLOPs)

HPC Performance (Peak TFLOPs)

Memory Capacity & Bandwidth

Support & Resources

AMD ROCm™ Software

AMD CDNA™ Architecture

AMD Instinct Documentation

Company

News & Events

Community

Partners

Investors