NVIDIA B100 vs AMD Instinct MI300X Full Specs

Summary

18,944 Shaders 1.6GHz	19,456 Shaders 2.1GHz
192GB HBM3e7.7TB/s	192GB HBM35.33TB/s
Peak·FP32·FP16 60.62 TFLOPS	Peak·FP32·FP16 163.4 TFLOPS
Form Factor SXM6	Form Factor OAM Module
TDP 700W	TDP 560W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse 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 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

B10014.01 PFLOPSFP4 Tensor Sparse

x2.68

Instinct MI300X5.23 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1600MHz UC·Boost·OC	Clock Speed2100MHz UC·Base·Boost·OC
Peak OPS 14.01 PFLOPSFP4 Tensor Sparse	Peak OPS 5.23 POPSINT4 Tensor Sparse
Tensor FP4 7 PFLOPS FP4 Tensor Sparse 14.01 PFLOPS	-
Tensor FP8-16 3.5 PFLOPS FP8-16 Tensor Sparse 7 PFLOPS Tensor FP8-32 3.5 PFLOPS FP8-32 Tensor Sparse 7 PFLOPS	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 FP16-16 1.75 PFLOPS FP16-16 Tensor Sparse 3.5 PFLOPS Tensor FP16-32 1.75 PFLOPS FP16-32 Tensor Sparse 3.5 PFLOPS	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
BF16 121.2 TFLOPS Tensor BF16 1.75 PFLOPS BF16 Tensor Sparse 3.5 PFLOPS	BF16 - Tensor BF16 1.31 PFLOPS BF16 Tensor Sparse 2.62 PFLOPS
Tensor TF32 875.4 TFLOPS	Tensor TF32 653.7 TFLOPS
FP32 60.62 TFLOPS Tensor FP32 -	FP32 163.4 TFLOPS Tensor FP32 163.4 TFLOPS
FP64 30.31 TFLOPS Tensor FP64 27.36 TFLOPS	FP64 81.72 TFLOPS Tensor FP64 163.4 TFLOPS
Tensor INT4 -	Tensor INT4 2.62 POPS
Tensor INT8 3.5 POPS	Tensor INT8 2.62 POPS
Pixel Rate 51.2 GPixel/s	Pixel Rate -
Texture Rate 947.2 GTexel/s	Texture Rate 2.55 TTexel/s

Core Config

Shaders 18,944 Shaders	Shaders 19,456 Shaders
TMUs 592 TMUs	TMUs 1,216 TMUs
ROPs 32 ROPs	ROPs -
Tensor Cores 592 T-Cores	Tensor Cores 1,216 T-Cores
SMs 148 SMs	CUs 304 CUs

Clocks

Base Clock -	Base Clock 1GHz
Boost Clock 1.6GHz	Boost Clock 2.1GHz
Tensor Clock 1.44GHz	Tensor Clock -

Cache

L2 Cache 65.5MB shared	L2 Cache 16.4MB shared
L3 Cache -	L3 Cache 256MB shared

Memory

192GB HBM3e	192GB HBM3
Memory Bus 8192-bit	Memory Bus 8192-bit
Memory Speed 7.5GT/s	Memory Speed 5.2GT/s
Memory Bandwidth 7.7TB/s	Memory Bandwidth 5.33TB/s
ECC -	ECC Yes

Power & Thermals

TDP 700W

TDP 560W

Encoder

-	Encoder Model 2x VCN 2.6

Decoder

Decoder Model 7x NVDEC 6

Decoder Model 2x VCN 2.6

Card

Form Factor SXM6	Form Factor OAM Module
Cooling Passive	Cooling Passive

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Blackwell	Architecture CDNA 3
Family Server	Family Instinct
Branding	Branding
Codename NV190	Codename Aqua Vanjaram
Chip Variant Umbriel	Chip Variant Aqua Vanjaram XTX
Market Segment Server	Market Segment Server
Release Date Mar 18, 2024	Release Date Dec 6, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries -	Other Foundries TSMCActive Interposer
Fabrication Node 4NP -	Fabrication Node N5 N6Active Interposer
Die Size 1620mm²	Die Size 1480mm²
Transistor Count 208 Billion	Transistor Count 146 Billion
Transistor Density 128.4 MTr/mm²	Transistor Density 98.65 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAB100 vs GPU NVIDIAB200 NVIDIAB100 vs GPU NVIDIAGB200 NVIDIAB100 vs GPU AMDInstinct MI325X Show 12 more

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