AMD Instinct™ MI300X Accelerator
Earn 15,000 points when you buy me!
The AMD Instinct™ MI300X platform is designed to deliver exceptional performance for AI and HPC.
Earn 15,000 points when you buy me!
The AMD Instinct™ MI300X platform is designed to deliver exceptional performance for AI and HPC.
AMD Instinct™ MI300 Series accelerators are uniquely well-suited to power even the most demanding AI and HPC workloads, offering exceptional compute performance, large memory density, high bandwidth memory, and support for specialized data formats.
AMD Instinct MI300 Series accelerators are built on AMD CDNA™ 3 architecture, which offers Matrix Core Technologies and support for a broad range of precision capabilities—from the highly efficient INT8 and FP8 (including sparsity support for AI), to the most demanding FP64 for HPC.
AMD Instinct MI300X Series accelerators are designed to deliver leadership performance for Generative AI workloads and HPC applications.
304 GPU Compute Units
192 GB HBM3 Memory
5.3 TB/s Peak Theoretical Memory Bandwidth
The AMD Instinct MI300X Platform integrates 8 fully connected MI300X GPU OAM modules onto an industry-standard OCP design via 4th-Gen AMD Infinity Fabric™ links, delivering up to 1.5TB HBM3 capacity for low-latency AI processing. This ready-to-deploy platform can accelerate time-to-market and reduce development costs when adding MI300X accelerators into existing AI rack and server infrastructure.
8 MI300X GPU OAM modules
1.5 TB Total HBM3 Memory
42.4 TB/s Peak Theoretical Aggregate Memory Bandwidth
AMD Instinct MI300A accelerated processing units (APUs) combine the power of AMD Instinct accelerators and AMD EPYC™ processors with shared memory to enable enhanced efficiency, flexibility, and programmability. They are designed to accelerate the convergence of AI and HPC, helping advance research and propel new discoveries.
Offers approximately 2.6X the HPC workload performance per watt using FP32 compared to AMD MI250X accelerators⁷
AMD Instinct accelerators power some of the world’s top supercomputers, including Lawrence Livermore National Laboratory’s El Capitan system. See how this two-Exascale supercomputer will use AI to run first-of-its-kind simulations and advance scientific research.
Product Basics
Name AMD Instinct™ MI300X
Family Instinct
Series Instinct MI300 Series
Form Factor Servers
Launch Date 12/06/2023
GPU Specifications
GPU Architecture CDNA3
Lithography TSMC 5nm | 6nm FinFET
Stream Processors 19,456
Matrix Cores 1216
Compute Units 304
Peak Engine Clock 2100 MHz
Peak Eight-bit Precision (FP8) Performance (E5M2, E4M3) 2.61 PFLOPs
Peak Eight-bit Precision (FP8) Performance with Structured Sparsity (E5M2, E4M3) 5.22 PFLOPs
Peak Half Precision (FP16) Performance 1.3 PFLOPs
Peak Half Precision (FP16) Performance with Structured Sparsity 2.61 PFLOPs
Peak Single Precision (TF32 Matrix) Performance 653.7 TFLOPs
Peak Single Precision (TF32) Performance with Structured Sparsity 1.3 PFLOPs
Peak Single Precision Matrix (FP32) Performance 163.4 TFLOPs
Peak Double Precision Matrix (FP64) Performance 163.4 TFLOPs
Peak Single Precision (FP32) Performance 163.4 TFLOPs
Peak Double Precision (FP64) Performance 81.7 TFLOPs
Peak INT8 Performance 2.6 POPs
Peak INT8 Performance with Structured Sparsity 5.22 POPs
Peak bfloat16 1.3 PFLOPs
Peak bfloat16 with Strutured Sparsity 2.61 PFLOPs
Transistor Count 153 Billion
Requirements
External Power Connectors 54V UBB
Typical Board Power (TBP) 750W Peak
GPU Memory
Last Level Cache (LLC) 256 MB
Dedicated Memory Size 192 GB
Dedicated Memory Type HBM3
Infinity Cache Yes
Memory Interface 8192-bit
Memory Clock 5.2 GHz
Peak Memory Bandwidth 5.3 TB/s
Memory ECC Support Yes (Full-Chip)
Board Specifications
GPU Form Factor OAM Module
Bus Type PCIe® 5.0 x16
Infinity Fabric™ Links 8
Peak Infinity Fabric™ Link Bandwidth 128 GB/s
Cooling Passive OAM
Additional Features
Supported Technologies AMD CDNA™ 3 Architecture , AMD ROCm™ - Ecosystem without Borders , AMD Infinity Architecture
RAS Support Yes
Page Retirement Yes
Page Avoidance Yes
SR-IOV Yes