Home GPU Comparison NVIDIA A40 PCIe vs NVIDIA A800 PCIe 80 GB

NVIDIA A40 PCIe vs NVIDIA A800 PCIe 80 GB

AI GPU We compared a Desktop platform GPU: 48GB VRAM A40 PCIe and a GPU: 80GB VRAM A800 PCIe 80 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA A40 PCIe 's Advantages
Boost Clock has increased by 23% (1740MHz vs 1410MHz)
3840 additional rendering cores
NVIDIA A800 PCIe 80 GB 's Advantages
Released 2 years and 1 months late
More VRAM (80GB vs 48GB)
Larger VRAM bandwidth (2039GB/s vs 695.8GB/s)
Lower TDP (250W vs 300W)

Score

Benchmark

FP32 (float)
A40 PCIe +91%
37.42 TFLOPS
A800 PCIe 80 GB
19.49 TFLOPS
VS

Graphics Card

Oct 2020
Release Date
Nov 2022
Tesla
Generation
Ampere
Desktop
Type
AI GPU
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1305 MHz
Base Clock
1065 MHz
1740 MHz
Boost Clock
1410 MHz
1812 MHz
Memory Clock
1593 MHz

Memory

48GB
Memory Size
80GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
5120bit
695.8GB/s
Bandwidth
2039GB/s

Render Config

84
SM Count
108
-
Compute Units
-
10752
Shading Units
6912
336
TMUs
432
112
ROPs
160
336
Tensor Cores
432
84
RT Cores
-
128 KB (per SM)
L1 Cache
192 KB (per SM)
6 MB
L2 Cache
80 MB

Theoretical Performance

194.9 GPixel/s
Pixel Rate
225.6 GPixel/s
584.6 GTexel/s
Texture Rate
609.1 GTexel/s
37.42 TFLOPS
FP16 (half)
77.97 TFLOPS
37.42 TFLOPS
FP32 (float)
19.49 TFLOPS
584.6 GFLOPS
FP64 (double)
9.746 TFLOPS

Graphics Processor

GA102
GPU Name
GA100
-
GPU Variant
-
Ampere
Architecture
Ampere
Samsung
Foundry
TSMC
8 nm
Process Size
7 nm
28.3 billion
Transistors
54.2 billion
628 mm²
Die Size
826 mm²

Board Design

300W
TDP
250W
700 W
Suggested PSU
600 W
3x DisplayPort 1.4a
Outputs
No outputs
8-pin EPS
Power Connectors
8-pin EPS

Graphics Features

12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
8.0
6.6
Shader Model
N/A

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy