NVIDIA P102 101 vs NVIDIA A40 PCIe
We compared two Desktop platform GPUs: 10GB VRAM P102 101 and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA P102 101 's Advantages
Lower TDP (250W vs 300W)
NVIDIA A40 PCIe 's Advantages
Released 2 years and 9 months late
Boost Clock has increased by 4% (1740MHz vs 1670MHz)
More VRAM (48GB vs 10GB)
Larger VRAM bandwidth (695.8GB/s vs 320.3GB/s)
7552 additional rendering cores
Score
Benchmark
FP32 (float)
P102 101
10.69 TFLOPS
A40 PCIe
+250%
37.42 TFLOPS
Graphics Card
Jan 2018
Release Date
Oct 2020
Mining GPUs
Generation
Tesla
Desktop
Type
Desktop
PCIe 3.0 x4
Bus Interface
PCIe 4.0 x16
Clock Speeds
1557 MHz
Base Clock
1305 MHz
1670 MHz
Boost Clock
1740 MHz
2002 MHz
Memory Clock
1812 MHz
Memory
10GB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
320bit
Memory Bus
384bit
320.3GB/s
Bandwidth
695.8GB/s
Render Config
-
-
-
25
SM Count
84
3200
Shading Units
10752
200
TMUs
336
80
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
48 KB (per SM)
L1 Cache
128 KB (per SM)
0 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
133.6 GPixel/s
Pixel Rate
194.9 GPixel/s
334.0 GTexel/s
Texture Rate
584.6 GTexel/s
167.0 GFLOPS
FP16 (half)
37.42 TFLOPS
10.69 TFLOPS
FP32 (float)
37.42 TFLOPS
334.0 GFLOPS
FP64 (double)
584.6 GFLOPS
Board Design
250W
TDP
300W
600 W
Suggested PSU
700 W
No outputs
Outputs
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
GP102
GPU Name
GA102
GP102-101-A1
GPU Variant
-
Pascal
Architecture
Ampere
TSMC
Foundry
Samsung
16 nm
Process Size
8 nm
11.8 billion
Transistors
28.3 billion
471 mm²
Die Size
628 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
6.1
CUDA
8.6
6.4
Shader Model
6.6
