Home GPU Comparison NVIDIA A100 PCIe 80 GB vs NVIDIA GRID A100B

NVIDIA A100 PCIe 80 GB vs NVIDIA GRID A100B

We compared two Professional market GPUs: 80GB VRAM A100 PCIe 80 GB and 48GB VRAM GRID A100B to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA A100 PCIe 80 GB 's Advantages
Released 1 years and 1 months late
Boost Clock has increased by 40% (1410MHz vs 1005MHz)
More VRAM (80GB vs 48GB)
Larger VRAM bandwidth (1935GB/s vs 1866GB/s)
Lower TDP (300W vs 400W)

Score

Benchmark

FP32 (float)
A100 PCIe 80 GB +40%
19.49 TFLOPS
GRID A100B
13.89 TFLOPS
VS

Graphics Card

Jun 2021
Release Date
May 2020
Tesla Ampere
Generation
GRID
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1065 MHz
Base Clock
900 MHz
1410 MHz
Boost Clock
1005 MHz
1512 MHz
Memory Clock
1215 MHz

Memory

80GB
Memory Size
48GB
HBM2e
Memory Type
HBM2e
5120bit
Memory Bus
6144bit
1935GB/s
Bandwidth
1866GB/s

Render Config

108
SM Count
108
-
Compute Units
-
6912
Shading Units
6912
432
TMUs
432
160
ROPs
192
432
Tensor Cores
432
-
RT Cores
-
192 KB (per SM)
L1 Cache
192 KB (per SM)
80 MB
L2 Cache
48 MB

Theoretical Performance

225.6 GPixel/s
Pixel Rate
193.0 GPixel/s
609.1 GTexel/s
Texture Rate
434.2 GTexel/s
77.97 TFLOPS
FP16 (half)
55.57 TFLOPS
19.49 TFLOPS
FP32 (float)
13.89 TFLOPS
9.746 TFLOPS
FP64 (double)
6.947 TFLOPS

Graphics Processor

GA100
GPU Name
GA100
-
GPU Variant
-
Ampere
Architecture
Ampere
TSMC
Foundry
TSMC
7 nm
Process Size
7 nm
54.2 billion
Transistors
54.2 billion
826 mm²
Die Size
826 mm²

Board Design

300W
TDP
400W
700 W
Suggested PSU
800 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
None

Graphics Features

N/A
DirectX
N/A
N/A
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
8.0
CUDA
8.0
N/A
Shader Model
N/A

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy