NVIDIA A30 vs NVIDIA Tesla P100 SXM Full Specs

Summary

3,584 Shaders 1.44GHz	3,584 Shaders 1.48GHz
24GB HBM2933.1GB/s	16GB HBM2732.2GB/s
Peak·FP32·FP16 10.32 TFLOPS	Peak·FP32·FP16 10.61 TFLOPS
Form Factor PCIe Card	Form Factor SXM
TDP 165W	TDP 300W

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

A301.32 POPSINT4 Tensor Sparse

x124.54

Tesla P100 SXM10.61 TFLOPSFP32

x1

Show Top Score

Theoretical Performance

Clock Speed1440MHz UC·Base·Boost·OC	Clock Speed1480MHz UC·Base·Boost·OC
Peak OPS 1.32 POPSINT4 Tensor Sparse	Peak OPS 10.61 TFLOPSFP32
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 20.64 TFLOPS Tensor BF16 165.2 TFLOPS BF16 Tensor Sparse 330.3 TFLOPS	-
Tensor TF32 82.58 TFLOPS	Tensor TF32 -
FP32 10.32 TFLOPS	FP32 10.61 TFLOPS
FP64 5.16 TFLOPS Tensor FP64 10.32 TFLOPS	FP64 5.3 TFLOPS Tensor FP64 -
Tensor INT4 660.6 TOPS	Tensor INT4 -
Tensor INT8 330.3 TOPS	-
Pixel Rate 138.2 GPixel/s	Pixel Rate 189.4 GPixel/s
Texture Rate 322.6 GTexel/s	Texture Rate 331.5 GTexel/s

Core Config

Shaders 3,584 Shaders	Shaders 3,584 Shaders
TMUs 224 TMUs	TMUs 224 TMUs
ROPs 96 ROPs	ROPs 128 ROPs
Tensor Cores 224 T-Cores	Tensor Cores -
SMs 56 SMs	SMs 56 SMs

Clocks

Base Clock 930MHz	Base Clock 1.33GHz
Boost Clock 1.44GHz	Boost Clock 1.48GHz

Cache

L2 Cache 24.6MB shared

L2 Cache 4.1MB shared

Memory

24GB HBM2	16GB HBM2
Memory Bus 3072-bit	Memory Bus 4096-bit
Memory Speed 2.4GT/s	Memory Speed 1.4GT/s
Memory Bandwidth 933.1GB/s	Memory Bandwidth 732.2GB/s
ECC No	ECC No

Power & Thermals

TDP 165W

TDP 300W

Encoder

-	Encoder Model 3x NVENC 4

Decoder

Decoder Model 5x NVDEC 4

Decoder Model NVDEC 3

Card

Form Factor PCIe Card	Form Factor SXM
PCIe 2-Slots	PCIe -
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 Pascal
Family Server	Family Tesla P
Branding	Branding
Codename NV170	Codename NV130
Chip Variant -	Chip Variant GP100-876-A1
Market Segment Server	Market Segment Server
Release Date Apr 12, 2021	Release Date Apr 5, 2016

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 7N	Fabrication Node 16FF
Die Size 826mm²	Die Size 610mm²
Transistor Count 54.2 Billion	Transistor Count 15.3 Billion
Transistor Density 65.62 MTr/mm²	Transistor Density 25.08 MTr/mm²

Images

No images available

No images available

Competitors

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

NVIDIATesla P100 SXM vs GPU AMDRadeon RX 9070 XT NVIDIATesla P100 SXM vs GPU AMDRadeon RX 7800 XT NVIDIATesla P100 SXM vs GPU AMDRadeon RX 9070 Show 12 more