Home NVIDIA P104 100

NVIDIA P104 100

This is a GPU manufactured with TSMC 16nm process, based on Nvidia Pascal architecture and released on Dec 2017. It features 7.2 billion transistors, 1920 CUDA cores and 4GB GDDR5X memory, with 2MB L2 cache, theoretical performance of 6.655TFLOPS, with total power consumption of 130W.

Graphics Card

[Report Issues]
Release Date
Dec 2017
Generation
Mining GPUs
Type
Desktop
Bus Interface
PCIe 3.0 x16

Clock Speeds

[Report Issues]
Base Clock
1607MHz
Boost Clock
1733MHz
Memory Clock
1251MHz

Memory

[Report Issues]
Memory Size
4GB
Memory Type
GDDR5X
Memory Bus
256bit
Bandwidth
320.3 GB/s

Render Config

[Report Issues]
SM Count
15
Shading Units
1920
TMUs
120
ROPs
64
L1 Cache
48 KB (per SM)
L2 Cache
2MB

Theoretical Performance

[Report Issues]
Pixel Rate
110.9 GPixel/s
Texture Rate
208.0 GTexel/s
FP16 (half)
104.0 GFLOPS
FP32 (float)
6.655 TFLOPS
FP64 (double)
208.0 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GP104
GPU Variant
GP104-100-A1
Architecture
Pascal
Foundry
TSMC
Process Size
16 nm
Transistors
7,200 million
Die Size
314mm²

Board Design

[Report Issues]
TDP
130W
Suggested PSU
200W
Outputs
No outputs
Power Connectors
1x 8-pin

Graphics Features

[Report Issues]
DirectX
12 (12_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
6.1
Shader Model
6.4

Rankings

[Report Issues]
FP32 (float)
6.691 TFLOPS
6.664 TFLOPS
6.659 TFLOPS
NVIDIA P104 100 4 GB GDDR5X
6.655 TFLOPS
6.636 TFLOPS
6.543 TFLOPS
6.48 TFLOPS
Blender
627
607
NVIDIA P104 100 4 GB GDDR5X
593
587
OctaneBench
NVIDIA P104 100 4 GB GDDR5X
124
NVIDIA Tesla M40 12 GB GDDR5
123

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy