NVIDIA A100 PCIe 80 GB vs NVIDIA B100
GPU · Specs Compare
Graphics Card
Release Date
Jun 2021
Unknown
Generation
Tesla Ampere(Axx)
Server Blackwell
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1065 MHz
700 MHz
Boost Clock
1410 MHz
975 MHz
Memory Clock
1512 MHz
2000 MHz
Memory
Memory Size
80GB
96GB
Memory Type
HBM2e
HBM3e
Memory Bus
5120bit
4096bit
Bandwidth
1.94TB/s
4.10TB/s
Render Config
SM Count
108
132
Shading Units
6912
16896
TMUs
432
528
ROPs
160
24
Tensor Cores
432
528
L1 Cache
192 KB (per SM)
256 KB (per SM)
L2 Cache
80 MB
50 MB
Theoretical Performance
Pixel Rate
225.6 GPixel/s
23.40 GPixel/s
Texture Rate
609.1 GTexel/s
514.8 GTexel/s
FP16 (half)
77.97 TFLOPS
131.8 TFLOPS
FP32 (float)
19.49 TFLOPS
32.95 TFLOPS
FP64 (double)
9.746 TFLOPS
16.47 TFLOPS
Graphics Processor
GPU Name
GA100
GB102
Architecture
Ampere
Blackwell
Foundry
TSMC
TSMC
Process Size
7 nm
5 nm
Transistors
54.2 billion
104 billion
Die Size
826 mm²
Unknown
Board Design
TDP
300W
1000W
Suggested PSU
700 W
1400 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
—
Graphics Features
DirectX
N/A
N/A
OpenGL
N/A
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
8.0
10.1
Shader Model
N/A
N/A
Benchmark
OctaneBench
310
—
Blender
3,722
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.