AMD Instinct MI300X vs Intel Gaudi 2 Full Specs

Summary

19,456 Shaders 2.1GHz	6,144 Shaders 550MHz
192GB HBM35.33TB/s	96GB HBM2e2.45TB/s
Peak·FP32·FP16 163.4 TFLOPS	Peak·FP32·FP16 -
Form Factor OAM Module	Form Factor OAM Module
TDP 560W	TDP 600W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse Tensor FP32 FP64 Tensor FP64 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Instinct MI300X5.23 POPSINT4 Tensor Sparse

x6.05

Gaudi 2865.1 TFLOPSFP8-32 Tensor

x1

Show Top Score

Theoretical Performance

Clock Speed2100MHz UC·Base·Boost·OC	Clock Speed550MHz UC·Boost·OC
Peak OPS 5.23 POPSINT4 Tensor Sparse	Peak OPS 865.1 TFLOPSFP8-32 Tensor
Tensor FP8-16 2.62 PFLOPS FP8-16 Tensor Sparse 5.23 PFLOPS Tensor FP8-32 2.62 PFLOPS FP8-32 Tensor Sparse 5.23 PFLOPS	Tensor FP8-16 - FP8-16 Tensor Sparse - Tensor FP8-32 865.1 TFLOPS FP8-32 Tensor Sparse -
Tensor FP16-16 1.31 PFLOPS FP16-16 Tensor Sparse 2.62 PFLOPS Tensor FP16-32 1.31 PFLOPS FP16-32 Tensor Sparse 2.62 PFLOPS	-
Tensor BF16 1.31 PFLOPS BF16 Tensor Sparse 2.62 PFLOPS	Tensor BF16 432.5 TFLOPS BF16 Tensor Sparse -
Tensor TF32 653.7 TFLOPS	Tensor TF32 -
FP32 163.4 TFLOPS Tensor FP32 163.4 TFLOPS	-
FP64 81.72 TFLOPS Tensor FP64 163.4 TFLOPS	-
Tensor INT4 2.62 POPS	Tensor INT4 -
Tensor INT8 2.62 POPS	-
Texture Rate 2.55 TTexel/s	Texture Rate -

Core Config

Shaders 19,456 Shaders	Shaders 6,144 Shaders
TMUs 1,216 TMUs	TMUs -
Tensor Cores 1,216 T-Cores	Tensor Cores 24 T-Cores
CUs 304 CUs	CUs 2 CUs

Clocks

Base Clock 1GHz	Base Clock -
Boost Clock 2.1GHz	Boost Clock 550MHz

Cache

L2 Cache 16.4MB shared	L2 Cache -
L3 Cache 256MB shared	L3 Cache -

Memory

192GB HBM3	96GB HBM2e
Memory Bus 8192-bit	Memory Bus 6144-bit
Memory Speed 5.2GT/s	Memory Speed 3.2GT/s
Memory Bandwidth 5.33TB/s	Memory Bandwidth 2.45TB/s
ECC Yes	ECC Yes
ESRAM -	ESRAM 48MBSize 6400GB/sBandwidth

Power & Thermals

TDP 560W

TDP 600W

Encoder

Encoder Model 2x VCN 2.6

-

Decoder

Decoder Model 2x VCN 2.6

Decoder Model 8x Gaudi

Card

Form Factor OAM Module	Form Factor OAM Module
Cooling Passive	Cooling Passive

Chip

Manufacturer AMD	Manufacturer Intel
Chip Designer AMD	Chip Designer Intel
Architecture CDNA 3	Architecture Gaudi 2
Family Instinct	Family Gaudi
Branding	Branding
Codename Aqua Vanjaram	Codename Gaudi 2
Chip Variant Aqua Vanjaram XTX	Chip Variant HL-2080
Market Segment Server	Market Segment Server
Release Date Dec 6, 2023	Release Date May 1, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCActive Interposer	Other Foundries -
Fabrication Node N5 N6Active Interposer	Fabrication Node N7 -
Die Size 1480mm²	Die Size -
Transistor Count 146 Billion	Transistor Count -
Transistor Density 98.65 MTr/mm²	Transistor Density -

Images

No images available

No images available

Competitors

AMDInstinct MI300X vs GPU AMDInstinct MI325X AMDInstinct MI300X vs GPU AMDInstinct MI355X AMDInstinct MI300X vs GPU AMDInstinct MI350X Show 12 more

IntelGaudi 2 vs GPU NVIDIAA800 IntelGaudi 2 vs GPU NVIDIAA100 SXM IntelGaudi 2 vs GPU NVIDIAA100X Show 12 more