NVIDIA A100 SXM4 40 GB vs NVIDIA GeForce RTX 3080
GPU Specs Compare
Graphics Card
Release Date
May 2020
Sep 2020
Generation
Tesla Ampere
GeForce 30
Type
AI GPU
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1095 MHz
1440 MHz
Boost Clock
1410 MHz
1710 MHz
Memory Clock
1215 MHz
1188 MHz
Memory
Memory Size
40GB
10GB
Memory Type
HBM2e
GDDR6X
Memory Bus
5120bit
320bit
Bandwidth
1555GB/s
760.3GB/s
Render Config
SM Count
108
68
Shading Units
6912
8704
TMUs
432
272
ROPs
160
96
Tensor Cores
432
272
L1 Cache
192 KB (per SM)
128 KB (per SM)
L2 Cache
40 MB
5 MB
RT Cores
-
68
Theoretical Performance
Pixel Rate
225.6 GPixel/s
164.2 GPixel/s
Texture Rate
609.1 GTexel/s
465.1 GTexel/s
FP16 (half)
77.97 TFLOPS
29.77 TFLOPS
FP32 (float)
19.49 TFLOPS
29.77 TFLOPS
FP64 (double)
9.746 TFLOPS
465.1 GFLOPS
Graphics Processor
GPU Name
GA100
GA102
Architecture
Ampere
Ampere
Foundry
TSMC
Samsung
Process Size
7 nm
8 nm
Transistors
54.2 billion
28.3 billion
Die Size
826 mm²
628 mm²
GPU Variant
-
GA102-200-KD-A1
Board Design
TDP
400W
320W
Suggested PSU
800 W
700 W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
None
1x 12-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
CUDA
8.0
8.6
Shader Model
N/A
6.6
📊 Benchmark
Blender
2,186
-
3DMark Time Spy
-
17,662
3DMark Time Spy Extreme
-
8,879