NVIDIA A100 SXM 40GB vs NVIDIA L40S Full Specs

Summary

6,912 Shaders 1.41GHz	18,176 Shaders 2.52GHz
40GB HBM2e1.55TB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 19.49 TFLOPS	Peak·FP32·FP16 91.61 TFLOPS
Form Factor SXM4	Form Factor PCIe Card
TDP 400W	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 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

A100 SXM 40GB2.5 POPSINT4 Tensor Sparse

x1

L40S2.93 POPSINT4 Tensor Sparse

x1.17

Show Top Score

Theoretical Performance

Clock Speed1410MHz UC·Base·Boost·OC	Clock Speed2520MHz UC·Base·Boost·OC
Peak OPS 2.5 POPSINT4 Tensor Sparse	Peak OPS 2.93 POPSINT4 Tensor Sparse
-	Tensor FP8-16 732.9 TFLOPS FP8-16 Tensor Sparse 1.47 PFLOPS Tensor FP8-32 366.4 TFLOPS FP8-32 Tensor Sparse 732.9 TFLOPS
Tensor FP16-16 311.9 TFLOPS FP16-16 Tensor Sparse 623.7 TFLOPS Tensor FP16-32 311.9 TFLOPS FP16-32 Tensor Sparse 623.7 TFLOPS	Tensor FP16-16 366.4 TFLOPS FP16-16 Tensor Sparse 732.9 TFLOPS Tensor FP16-32 183.2 TFLOPS FP16-32 Tensor Sparse 366.4 TFLOPS
BF16 38.98 TFLOPS Tensor BF16 311.9 TFLOPS BF16 Tensor Sparse 623.7 TFLOPS	BF16 91.61 TFLOPS Tensor BF16 183.2 TFLOPS BF16 Tensor Sparse 366.4 TFLOPS
Tensor TF32 155.9 TFLOPS	Tensor TF32 91.61 TFLOPS
FP32 19.49 TFLOPS	FP32 91.61 TFLOPS
FP64 9.75 TFLOPS Tensor FP64 19.49 TFLOPS	FP64 1.43 TFLOPS Tensor FP64 -
Tensor INT4 1.25 POPS	Tensor INT4 1.47 POPS
Tensor INT8 623.7 TOPS	Tensor INT8 732.9 TOPS
Ray -	Ray 211.7 TOPS
Pixel Rate 225.6 GPixel/s	Pixel Rate 483.8 GPixel/s
Texture Rate 609.1 GTexel/s	Texture Rate 1.43 TTexel/s

Core Config

Shaders 6,912 Shaders	Shaders 18,176 Shaders
TMUs 432 TMUs	TMUs 568 TMUs
ROPs 160 ROPs	ROPs 192 ROPs
Tensor Cores 432 T-Cores	Tensor Cores 568 T-Cores
RT Cores -	RT Cores 142 RT-Cores
SMs 108 SMs	SMs 142 SMs

Clocks

Base Clock 1.09GHz	Base Clock 1.11GHz
Boost Clock 1.41GHz	Boost Clock 2.52GHz

Cache

L2 Cache 41MB shared

L2 Cache 98.3MB shared

Memory

40GB HBM2e	48GB GDDR6
Memory Bus 5120-bit	Memory Bus 384-bit
Memory Speed 2.4GT/s	Memory Speed 18GT/s
Memory Bandwidth 1.55TB/s	Memory Bandwidth 864GB/s

Power & Thermals

TDP 400W

TDP 300W

Video Output

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

Ports

-	4x DisplayPort 1.4

Encoder

-	Encoder Model 2x NVENC 8

Decoder

Decoder Model 5x NVDEC 4

Decoder Model NVDEC 5

Card

Form Factor SXM4	Form Factor PCIe Card
PCIe -	PCIe 2-Slots
-	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 NV170	Codename NV182
Chip Variant -	Chip Variant AD102-200-A1
Market Segment Server	Market Segment Server
Release Date Jun 28, 2021	Release Date Oct 13, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 7N	Fabrication Node 4N
Die Size 826mm²	Die Size 608mm²
Transistor Count 54.2 Billion	Transistor Count 76.3 Billion
Transistor Density 65.62 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAA100 SXM 40GB vs GPU AMDInstinct MI300P NVIDIAA100 SXM 40GB vs GPU NVIDIAB100 NVIDIAA100 SXM 40GB vs GPU NVIDIAB200 Show 4 more

NVIDIAL40S vs GPU NVIDIAB200 NVIDIAL40S vs GPU NVIDIAGB200 NVIDIAL40S vs GPU NVIDIARTX PRO 5000 Blackwell Show 12 more