NVIDIA A2 vs NVIDIA H100 Full Specs

Summary

1,280 Shaders 1.77GHz	14,592 Shaders 1.75GHz
16GB GDDR6100.1GB/s	80GB HBM2e2.04TB/s
Peak·FP32·FP16 4.53 TFLOPS	Peak·FP32·FP16 51.22 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 60W	TDP 350W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

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 FP64 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

A2145 TOPSINT4 Tensor Sparse

x1

H1003.03 POPSINT8 Tensor Sparse

x20.87

Show Top Score

Theoretical Performance

Clock Speed1770MHz UC·Base·Boost·OC	Clock Speed1755MHz UC·Base·Boost·OC
Peak OPS 145 TOPSINT4 Tensor Sparse	Peak OPS 3.03 POPSINT8 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 FP16-16 18.12 TFLOPS FP16-16 Tensor Sparse 36.25 TFLOPS Tensor FP16-32 9.06 TFLOPS FP16-32 Tensor Sparse 18.12 TFLOPS	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
BF16 4.53 TFLOPS Tensor BF16 9.06 TFLOPS BF16 Tensor Sparse 18.12 TFLOPS	BF16 102.4 TFLOPS Tensor BF16 756.4 TFLOPS BF16 Tensor Sparse 1.51 PFLOPS
Tensor TF32 4.53 TFLOPS	Tensor TF32 378.2 TFLOPS
FP32 4.53 TFLOPS	FP32 51.22 TFLOPS
FP64 70.8 GFLOPS Tensor FP64 -	FP64 25.61 TFLOPS Tensor FP64 47.28 TFLOPS
Tensor INT4 72.5 TOPS	Tensor INT4 -
Tensor INT8 36.25 TOPS	Tensor INT8 1.51 POPS
Ray 6.83 TOPS	Ray -
Pixel Rate 56.6 GPixel/s	Pixel Rate 42.1 GPixel/s
Texture Rate 70.8 GTexel/s	Texture Rate 800.3 GTexel/s

Core Config

Shaders 1,280 Shaders	Shaders 14,592 Shaders
TMUs 40 TMUs	TMUs 456 TMUs
ROPs 32 ROPs	ROPs 24 ROPs
Tensor Cores 40 T-Cores	Tensor Cores 456 T-Cores
RT Cores 10 RT-Cores	RT Cores -
SMs 10 SMs	SMs 114 SMs

Clocks

Base Clock 1.44GHz	Base Clock 1.06GHz
Boost Clock 1.77GHz	Boost Clock 1.75GHz
Tensor Clock -	Tensor Clock 1.62GHz

Cache

L2 Cache 2MB shared

L2 Cache 51.2MB shared

Memory

16GB GDDR6	80GB HBM2e
Memory Bus 128-bit	Memory Bus 5120-bit
Memory Speed 6.3GT/s	Memory Speed 3.2GT/s
Memory Bandwidth 100.1GB/s	Memory Bandwidth 2.04TB/s

Power & Thermals

TDP 60W

TDP 350W

Encoder

Encoder Model NVENC 7

-

Decoder

Decoder Model NVDEC 5

Decoder Model 7x NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 1-Slots	PCIe 2-Slots
Height 69 mm (2.72") Width 168 mm (6.61") Depth 20 mm (0.79")	Height 111 mm (4.37") Width 268 mm (10.55") Depth 40 mm (1.57")
Cooling Passive	Cooling Passive
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Hopper
Family Server	Family Server
Branding	Branding
Codename NV177	Codename NV180
Chip Variant GA107-140-A1	Chip Variant -
Market Segment Server	Market Segment Server
Release Date Nov 10, 2021	Release Date Mar 22, 2022

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 4N
Die Size 200mm²	Die Size 814mm²
Transistor Count 8.7 Billion	Transistor Count 80 Billion
Transistor Density 43.5 MTr/mm²	Transistor Density 98.28 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAA2 vs GPU AMDRadeon PRO W7500 NVIDIAA2 vs GPU AMDRadeon RX 7400 NVIDIAA2 vs GPU AMDRadeon PRO W7400 Show 12 more

NVIDIAH100 vs GPU AMDInstinct MI300P NVIDIAH100 vs GPU NVIDIARTX PRO 5000 Blackwell NVIDIAH100 vs GPU NVIDIAB100 Show 12 more