NVIDIA B100 vs NVIDIA L40S Full Specs

Summary

18,944 Shaders 1.6GHz	18,176 Shaders 2.52GHz
192GB HBM3e7.7TB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 60.62 TFLOPS	Peak·FP32·FP16 91.61 TFLOPS
Form Factor SXM6	Form Factor PCIe Card
TDP 700W	TDP 300W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Theoretical Performance

Clock Speed1600MHz UC·Boost·OC	Clock Speed2520MHz UC·Base·Boost·OC
Peak OPS 14.01 PFLOPSFP4 Tensor Sparse	Peak OPS 2.93 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 FP8-16 732.9 TFLOPS FP8-16 Tensor Sparse 1.47 PFLOPS Tensor FP8-32 366.4 TFLOPS FP8-32 Tensor Sparse 732.9 TFLOPS
Tensor FP16-16 1.75 PFLOPS FP16-16 Tensor Sparse 3.5 PFLOPS Tensor FP16-32 1.75 PFLOPS FP16-32 Tensor Sparse 3.5 PFLOPS	Tensor FP16-16 366.4 TFLOPS FP16-16 Tensor Sparse 732.9 TFLOPS Tensor FP16-32 183.2 TFLOPS FP16-32 Tensor Sparse 366.4 TFLOPS
BF16 121.2 TFLOPS Tensor BF16 1.75 PFLOPS BF16 Tensor Sparse 3.5 PFLOPS	BF16 91.61 TFLOPS Tensor BF16 183.2 TFLOPS BF16 Tensor Sparse 366.4 TFLOPS
Tensor TF32 875.4 TFLOPS	Tensor TF32 91.61 TFLOPS
FP32 60.62 TFLOPS	FP32 91.61 TFLOPS
FP64 30.31 TFLOPS Tensor FP64 27.36 TFLOPS	FP64 1.43 TFLOPS Tensor FP64 -
Tensor INT4 -	Tensor INT4 1.47 POPS
Tensor INT8 3.5 POPS	Tensor INT8 732.9 TOPS
Ray -	Ray 211.7 TOPS
Pixel Rate 51.2 GPixel/s	Pixel Rate 483.8 GPixel/s
Texture Rate 947.2 GTexel/s	Texture Rate 1.43 TTexel/s

Core Config

Shaders 18,944 Shaders	Shaders 18,176 Shaders
TMUs 592 TMUs	TMUs 568 TMUs
ROPs 32 ROPs	ROPs 192 ROPs
Tensor Cores 592 T-Cores	Tensor Cores 568 T-Cores
RT Cores -	RT Cores 142 RT-Cores
SMs 148 SMs	SMs 142 SMs

Clocks

Base Clock -	Base Clock 1.11GHz
Boost Clock 1.6GHz	Boost Clock 2.52GHz
Tensor Clock 1.44GHz	Tensor Clock -

Cache

L2 Cache 64MB shared

L2 Cache 96MB shared

Memory

192GB HBM3e	48GB GDDR6
Memory Bus 8192-bit	Memory Bus 384-bit
Memory Speed 7.5GT/s	Memory Speed 18GT/s
Memory Bandwidth 7.7TB/s	Memory Bandwidth 864GB/s
ECC No	ECC No

Power & Thermals

TDP 700W

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
Codec -	Codec AVC (H.264) HEVC (H.265) AV1

Decoder

Decoder Model 7x NVDEC 6	Decoder Model NVDEC 5
Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1	Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor SXM6	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 Blackwell	Architecture Ada Lovelace
Family Server	Family Server
Branding	Branding
Codename NV190	Codename NV182
Chip Variant Umbriel	Chip Variant AD102-200-A1
Market Segment Server	Market Segment Server
Release Date Mar 18, 2024	Release Date Oct 13, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4NP	Fabrication Node 4N
Die Size 1620mm²	Die Size 608mm²
Transistor Count 208 Billion	Transistor Count 76.3 Billion
Transistor Density 128.4 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images