NVIDIA P102 100 vs NVIDIA GeForce GTX 1070 GDDR5X
We compared two Desktop platform GPUs: 5GB VRAM P102 100 and 8GB VRAM GeForce GTX 1070 GDDR5X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA P102 100 's Advantages
Larger VRAM bandwidth (440.3GB/s vs 256.3GB/s)
1280 additional rendering cores
NVIDIA GeForce GTX 1070 GDDR5X 's Advantages
Released 10 months late
More VRAM (8GB vs 5GB)
Lower TDP (150W vs 250W)
Score
Benchmark
FP32 (float)
P102 100
+66%
10.77 TFLOPS
GeForce GTX 1070 GDDR5X
6.463 TFLOPS
3DMark Time Spy
P102 100
+15%
7042
GeForce GTX 1070 GDDR5X
6078
3DMark Time Spy Extreme
P102 100
+35%
3817
GeForce GTX 1070 GDDR5X
2825
Blender
P102 100
+30%
859
GeForce GTX 1070 GDDR5X
657
OctaneBench
P102 100
+60%
184
GeForce GTX 1070 GDDR5X
115
Graphics Card
Feb 2018
Release Date
Dec 2018
Mining GPUs
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 3.0 x4
Bus Interface
PCIe 3.0 x16
Clock Speeds
1582 MHz
Base Clock
1506 MHz
1683 MHz
Boost Clock
1683 MHz
1376 MHz
Memory Clock
1001 MHz
Memory
5GB
Memory Size
8GB
GDDR5X
Memory Type
GDDR5X
320bit
Memory Bus
256bit
440.3GB/s
Bandwidth
256.3GB/s
Render Config
-
-
-
25
SM Count
15
3200
Shading Units
1920
200
TMUs
120
80
ROPs
64
-
-
-
-
-
-
48 KB (per SM)
L1 Cache
48 KB (per SM)
0 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
134.6 GPixel/s
Pixel Rate
107.7 GPixel/s
336.6 GTexel/s
Texture Rate
202.0 GTexel/s
168.3 GFLOPS
FP16 (half)
101.0 GFLOPS
10.77 TFLOPS
FP32 (float)
6.463 TFLOPS
336.6 GFLOPS
FP64 (double)
202.0 GFLOPS
Board Design
250W
TDP
150W
600 W
Suggested PSU
450 W
No outputs
Outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GP102
GPU Name
GP104
GP102-100-A1
GPU Variant
GP104-200-A1
Pascal
Architecture
Pascal
TSMC
Foundry
TSMC
16 nm
Process Size
16 nm
11.8 billion
Transistors
7.2 billion
471 mm²
Die Size
314 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
6.1
CUDA
6.1
6.4
Shader Model
6.4
