NVIDIA A2 vs NVIDIA L40 Full Specs

Summary

1,280 Shaders 1.77GHz	18,176 Shaders 2.49GHz
16GB GDDR6100.1GB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 4.53 TFLOPS	Peak·FP32·FP16 90.52 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 60W	TDP 300W
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 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

A2145 TOPSINT4 Tensor Sparse

x1

L402.9 POPSINT4 Tensor Sparse

x19.98

Show Top Score

Theoretical Performance

Clock Speed1770MHz UC·Base·Boost·OC	Clock Speed2490MHz UC·Base·Boost·OC
Peak OPS 145 TOPSINT4 Tensor Sparse	Peak OPS 2.9 POPSINT4 Tensor Sparse
-	Tensor FP8-16 724.1 TFLOPS FP8-16 Tensor Sparse 1.45 PFLOPS Tensor FP8-32 362.1 TFLOPS FP8-32 Tensor Sparse 724.1 TFLOPS
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 FP16-16 362.1 TFLOPS FP16-16 Tensor Sparse 724.1 TFLOPS Tensor FP16-32 181 TFLOPS FP16-32 Tensor Sparse 362.1 TFLOPS
BF16 4.53 TFLOPS Tensor BF16 9.06 TFLOPS BF16 Tensor Sparse 18.12 TFLOPS	BF16 90.52 TFLOPS Tensor BF16 181 TFLOPS BF16 Tensor Sparse 362.1 TFLOPS
Tensor TF32 4.53 TFLOPS	Tensor TF32 90.52 TFLOPS
FP32 4.53 TFLOPS	FP32 90.52 TFLOPS
FP64 70.8 GFLOPS	FP64 1.41 TFLOPS
Tensor INT4 72.5 TOPS	Tensor INT4 1.45 POPS
Tensor INT8 36.25 TOPS	Tensor INT8 724.1 TOPS
Ray 6.83 TOPS	Ray 209.2 TOPS
Pixel Rate 56.6 GPixel/s	Pixel Rate 478.1 GPixel/s
Texture Rate 70.8 GTexel/s	Texture Rate 1.41 TTexel/s

Core Config

Shaders 1,280 Shaders	Shaders 18,176 Shaders
TMUs 40 TMUs	TMUs 568 TMUs
ROPs 32 ROPs	ROPs 192 ROPs
Tensor Cores 40 T-Cores	Tensor Cores 568 T-Cores
RT Cores 10 RT-Cores	RT Cores 142 RT-Cores
SMs 10 SMs	SMs 142 SMs

Clocks

Base Clock 1.44GHz	Base Clock 735MHz
Boost Clock 1.77GHz	Boost Clock 2.49GHz

Cache

L2 Cache 2MB shared

L2 Cache 98.3MB shared

Memory

16GB GDDR6	48GB GDDR6
Memory Bus 128-bit	Memory Bus 384-bit
Memory Speed 6.3GT/s	Memory Speed 18GT/s
Memory Bandwidth 100.1GB/s	Memory Bandwidth 864GB/s

Power & Thermals

TDP 60W

TDP 300W

Video Output

Multi-Monitor -	Multi-Monitor 4
HDCP -	HDCP HDCP 2.3

Ports

-	4x DisplayPort 1.4

Encoder

Encoder Model NVENC 7

Encoder Model 2x NVENC 8

Decoder

Decoder Model NVDEC 5

Decoder Model 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 267 mm (10.51") 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 Ada Lovelace
Family Server	Family Server
Branding	Branding
Codename NV177	Codename NV182
Chip Variant GA107-140-A1	Chip Variant AD102-200-A1
Market Segment Server	Market Segment Server
Release Date Nov 10, 2021	Release Date Oct 13, 2022

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 4N
Die Size 200mm²	Die Size 608mm²
Transistor Count 8.7 Billion	Transistor Count 76.3 Billion
Transistor Density 43.5 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available