NVIDIA H100 vs AMD Instinct MI300P Full Specs

Summary

14,592 Shaders 1.75GHz	9,728 Shaders 2.1GHz
80GB HBM2e2.04TB/s	64GB HBM32.66TB/s
Peak·FP32·FP16 51.22 TFLOPS	Peak·FP32·FP16 81.72 TFLOPS
Form Factor PCIe Card	Form Factor OAM Module
TDP 350W	TDP 300W
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

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 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

H1003.03 POPSINT8 Tensor Sparse

x1.16

Instinct MI300P2.62 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1755MHz UC·Base·Boost·OC	Clock Speed2100MHz UC·Base·Boost·OC
Peak OPS 3.03 POPSINT8 Tensor Sparse	Peak OPS 2.62 POPSINT4 Tensor Sparse
Tensor FP8-16 1.51 PFLOPS FP8-16 Tensor Sparse 3.03 PFLOPS Tensor FP8-32 1.51 PFLOPS FP8-32 Tensor Sparse 3.03 PFLOPS	Tensor FP8-16 1.31 PFLOPS FP8-16 Tensor Sparse 2.62 PFLOPS Tensor FP8-32 1.31 PFLOPS FP8-32 Tensor Sparse 2.62 PFLOPS
Tensor FP16-16 756.4 TFLOPS FP16-16 Tensor Sparse 1.51 PFLOPS Tensor FP16-32 756.4 TFLOPS FP16-32 Tensor Sparse 1.51 PFLOPS	Tensor FP16-16 653.7 TFLOPS FP16-16 Tensor Sparse 1.31 PFLOPS Tensor FP16-32 653.7 TFLOPS FP16-32 Tensor Sparse 1.31 PFLOPS
BF16 102.4 TFLOPS Tensor BF16 756.4 TFLOPS BF16 Tensor Sparse 1.51 PFLOPS	BF16 - Tensor BF16 653.7 TFLOPS BF16 Tensor Sparse 1.31 PFLOPS
Tensor TF32 378.2 TFLOPS	Tensor TF32 326.9 TFLOPS
FP32 51.22 TFLOPS Tensor FP32 -	FP32 81.72 TFLOPS Tensor FP32 81.72 TFLOPS
FP64 25.61 TFLOPS Tensor FP64 47.28 TFLOPS	FP64 40.86 TFLOPS Tensor FP64 81.72 TFLOPS
Tensor INT4 -	Tensor INT4 1.31 POPS
Tensor INT8 1.51 POPS	Tensor INT8 1.31 POPS
Pixel Rate 42.1 GPixel/s	Pixel Rate -
Texture Rate 800.3 GTexel/s	Texture Rate 1.28 TTexel/s

Core Config

Shaders 14,592 Shaders	Shaders 9,728 Shaders
TMUs 456 TMUs	TMUs 608 TMUs
ROPs 24 ROPs	ROPs -
Tensor Cores 456 T-Cores	Tensor Cores 608 T-Cores
SMs 114 SMs	CUs 152 CUs

Clocks

Base Clock 1.06GHz	Base Clock 1GHz
Boost Clock 1.75GHz	Boost Clock 2.1GHz
Tensor Clock 1.62GHz	Tensor Clock -

Cache

L2 Cache 51.2MB shared	L2 Cache 16.4MB shared
L3 Cache -	L3 Cache 128MB shared

Memory

80GB HBM2e	64GB HBM3
Memory Bus 5120-bit	Memory Bus 4096-bit
Memory Speed 3.2GT/s	Memory Speed 5.2GT/s
Memory Bandwidth 2.04TB/s	Memory Bandwidth 2.66TB/s
ECC -	ECC Yes

Power & Thermals

TDP 350W

TDP 300W

Encoder

-	Encoder Model 2x VCN 2.6

Decoder

Decoder Model 7x NVDEC 5

Decoder Model 2x VCN 2.6

Card

Form Factor PCIe Card	Form Factor OAM Module
PCIe 2-Slots	PCIe -
Height 111 mm (4.37") Width 268 mm (10.55") Depth 40 mm (1.57")	-
Cooling Passive	Cooling Passive
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Hopper	Architecture CDNA 3
Family Server	Family Instinct
Branding	Branding
Codename NV180	Codename Aqua Vanjaram
Chip Variant -	Chip Variant Aqua Vanjaram XL
Market Segment Server	Market Segment Server
Release Date Mar 22, 2022	Release Date Dec 6, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries -	Other Foundries TSMCActive Interposer
Fabrication Node 4N -	Fabrication Node N5 N6Active Interposer
Die Size 814mm²	Die Size 740mm²
Transistor Count 80 Billion	Transistor Count 73 Billion
Transistor Density 98.28 MTr/mm²	Transistor Density 98.65 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAH100 vs GPU NVIDIARTX PRO 5000 Blackwell NVIDIAH100 vs GPU NVIDIAB100 NVIDIAH100 vs GPU NVIDIARTX PRO 6000 Blackwell Max-Q Show 12 more

AMDInstinct MI300P vs GPU AMDInstinct MI300A AMDInstinct MI300P vs GPU NVIDIARTX PRO 5000 Blackwell AMDInstinct MI300P vs GPU NVIDIARTX 5880 Ada Show 12 more