NVIDIA A10 vs NVIDIA A100 SXM 40GB Full Specs

Summary

9,216 Shaders 1.7GHz	6,912 Shaders 1.41GHz
24GB GDDR6300.3GB/s	40GB HBM2e1.55TB/s
Peak·FP32·FP16 31.24 TFLOPS	Peak·FP32·FP16 19.49 TFLOPS
Form Factor PCIe Card	Form Factor SXM4
TDP 150W	TDP 400W
Power Connectors 1x 8-Pin	Power Connectors -

Highlights

Peak OPS

Peak OPS FP32 FP16 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

A10999.8 TOPSINT4 Tensor Sparse

x1

A100 SXM 40GB2.5 POPSINT4 Tensor Sparse

x2.50

Show Top Score

Theoretical Performance

Clock Speed1695MHz UC·Base·Boost·OC	Clock Speed1410MHz UC·Base·Boost·OC
Peak OPS 999.8 TOPSINT4 Tensor Sparse	Peak OPS 2.5 POPSINT4 Tensor Sparse
Tensor FP16-16 125 TFLOPS FP16-16 Tensor Sparse 249.9 TFLOPS Tensor FP16-32 62.48 TFLOPS FP16-32 Tensor Sparse 125 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
BF16 31.24 TFLOPS Tensor BF16 62.48 TFLOPS BF16 Tensor Sparse 125 TFLOPS	BF16 38.98 TFLOPS Tensor BF16 311.9 TFLOPS BF16 Tensor Sparse 623.7 TFLOPS
Tensor TF32 31.24 TFLOPS	Tensor TF32 155.9 TFLOPS
FP32 31.24 TFLOPS	FP32 19.49 TFLOPS
FP64 488.2 GFLOPS Tensor FP64 -	FP64 9.75 TFLOPS Tensor FP64 19.49 TFLOPS
Tensor INT4 499.9 TOPS	Tensor INT4 1.25 POPS
Tensor INT8 249.9 TOPS	Tensor INT8 623.7 TOPS
Ray 47.12 TOPS	Ray -
Pixel Rate 162.7 GPixel/s	Pixel Rate 225.6 GPixel/s
Texture Rate 488.2 GTexel/s	Texture Rate 609.1 GTexel/s

Core Config

Shaders 9,216 Shaders	Shaders 6,912 Shaders
TMUs 288 TMUs	TMUs 432 TMUs
ROPs 96 ROPs	ROPs 160 ROPs
Tensor Cores 288 T-Cores	Tensor Cores 432 T-Cores
RT Cores 72 RT-Cores	RT Cores -
SMs 72 SMs	SMs 108 SMs

Clocks

Base Clock 885MHz	Base Clock 1.09GHz
Boost Clock 1.7GHz	Boost Clock 1.41GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 41MB shared

Memory

24GB GDDR6	40GB HBM2e
Memory Bus 384-bit	Memory Bus 5120-bit
Memory Speed 6.3GT/s	Memory Speed 2.4GT/s
Memory Bandwidth 300.3GB/s	Memory Bandwidth 1.55TB/s

Power & Thermals

TDP 150W

TDP 400W

Encoder

Encoder Model NVENC 7

-

Decoder

Decoder Model NVDEC 5

Decoder Model 5x NVDEC 4

Card

Form Factor PCIe Card	Form Factor SXM4
PCIe 1-Slots	PCIe -
Height 112 mm (4.41") Width 267 mm (10.51") Depth 20 mm (0.79")	-
Cooling Passive	Cooling Passive
Power Connectors 1x 8-Pin	Power Connectors -

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ampere
Family Server	Family Server
Branding	Branding
Codename NV172	Codename NV170
Chip Variant GA102-200-KD-A1	Chip Variant -
Market Segment Server	Market Segment Server
Release Date Apr 12, 2021	Release Date Jun 28, 2021

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 7N
Die Size 628mm²	Die Size 826mm²
Transistor Count 28.3 Billion	Transistor Count 54.2 Billion
Transistor Density 45.04 MTr/mm²	Transistor Density 65.62 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAA10 vs GPU NVIDIARTX 4000 Ada NVIDIAA10 vs GPU NVIDIARTX 4500 Ada NVIDIAA10 vs GPU AMDRadeon RX 9060 XT 16GB Show 12 more

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