NVIDIA A100 SXM 40GB vs NVIDIA A30 Full Specs

Summary

6,912 Shaders 1.41GHz	3,584 Shaders 1.44GHz
40GB HBM2e1.55TB/s	24GB HBM2933.1GB/s
Peak·FP32·FP16 19.49 TFLOPS	Peak·FP32·FP16 10.32 TFLOPS
Form Factor SXM4	Form Factor PCIe Card
TDP 400W	TDP 165W

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

A100 SXM 40GB2.5 POPSINT4 Tensor Sparse

x1.89

A301.32 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1410MHz UC·Base·Boost·OC	Clock Speed1440MHz UC·Base·Boost·OC
Peak OPS 2.5 POPSINT4 Tensor Sparse	Peak OPS 1.32 POPSINT4 Tensor Sparse
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 FP16-16 165.2 TFLOPS FP16-16 Tensor Sparse 330.3 TFLOPS Tensor FP16-32 165.2 TFLOPS FP16-32 Tensor Sparse 330.3 TFLOPS
BF16 38.98 TFLOPS Tensor BF16 311.9 TFLOPS BF16 Tensor Sparse 623.7 TFLOPS	BF16 20.64 TFLOPS Tensor BF16 165.2 TFLOPS BF16 Tensor Sparse 330.3 TFLOPS
Tensor TF32 155.9 TFLOPS	Tensor TF32 82.58 TFLOPS
FP32 19.49 TFLOPS	FP32 10.32 TFLOPS
FP64 9.75 TFLOPS Tensor FP64 19.49 TFLOPS	FP64 5.16 TFLOPS Tensor FP64 10.32 TFLOPS
Tensor INT4 1.25 POPS	Tensor INT4 660.6 TOPS
Tensor INT8 623.7 TOPS	Tensor INT8 330.3 TOPS
Pixel Rate 225.6 GPixel/s	Pixel Rate 138.2 GPixel/s
Texture Rate 609.1 GTexel/s	Texture Rate 322.6 GTexel/s

Core Config

Shaders 6,912 Shaders	Shaders 3,584 Shaders
TMUs 432 TMUs	TMUs 224 TMUs
ROPs 160 ROPs	ROPs 96 ROPs
Tensor Cores 432 T-Cores	Tensor Cores 224 T-Cores
SMs 108 SMs	SMs 56 SMs

Clocks

Base Clock 1.09GHz	Base Clock 930MHz
Boost Clock 1.41GHz	Boost Clock 1.44GHz

Cache

L2 Cache 41MB shared

L2 Cache 24.6MB shared

Memory

40GB HBM2e	24GB HBM2
Memory Bus 5120-bit	Memory Bus 3072-bit
Memory Speed 2.4GT/s	Memory Speed 2.4GT/s
Memory Bandwidth 1.55TB/s	Memory Bandwidth 933.1GB/s

Power & Thermals

TDP 400W

TDP 165W

Decoder

Decoder Model 5x NVDEC 4

Decoder Model 5x NVDEC 4

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

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ampere
Family Server	Family Server
Branding	Branding
Codename NV170	Codename NV170
Market Segment Server	Market Segment Server
Release Date Jun 28, 2021	Release Date Apr 12, 2021

Fabrication

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

NVIDIAA30 vs GPU AMDRadeon PRO W7700 NVIDIAA30 vs GPU AMDRadeon RX 9070 NVIDIAA30 vs GPU AMDRadeon RX 7800 XT Show 12 more