Home GPU Comparison NVIDIA Tesla T4 vs NVIDIA Tesla S870

NVIDIA Tesla T4 vs NVIDIA Tesla S870

We compared two Professional market GPUs: 16GB VRAM Tesla T4 and 1536MB VRAM Tesla S870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA Tesla T4 's Advantages
Released 11 years and 4 months late
Boost Clock1590MHz
More VRAM (16GB vs 1GB)
Larger VRAM bandwidth (320.0GB/s vs 76.80GB/s)
2432 additional rendering cores
Lower TDP (70W vs 800W)

Score

Benchmark

FP32 (float)
Tesla T4 +2252%
8.141 TFLOPS
Tesla S870
0.346 TFLOPS
VS

Graphics Card

Sep 2018
Release Date
May 2007
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x16

Clock Speeds

585 MHz
Base Clock
-
1590 MHz
Boost Clock
-
1250 MHz
Memory Clock
800 MHz

Memory

16GB
Memory Size
1536MB
GDDR6
Memory Type
GDDR3
256bit
Memory Bus
384bit
320.0GB/s
Bandwidth
76.80GB/s

Render Config

40
SM Count
16
-
Compute Units
-
2560
Shading Units
128
160
TMUs
32
64
ROPs
24
320
Tensor Cores
-
40
RT Cores
-
64 KB (per SM)
L1 Cache
-
4 MB
L2 Cache
96 KB

Theoretical Performance

101.8 GPixel/s
Pixel Rate
14.40 GPixel/s
254.4 GTexel/s
Texture Rate
38.40 GTexel/s
65.13 TFLOPS
FP16 (half)
-
8.141 TFLOPS
FP32 (float)
345.6 GFLOPS
254.4 GFLOPS
FP64 (double)
-

Graphics Processor

TU104
GPU Name
G80
TU104-895-A1
GPU Variant
-
Turing
Architecture
Tesla
TSMC
Foundry
TSMC
12 nm
Process Size
90 nm
13.6 billion
Transistors
0.681 billion
545 mm²
Die Size
484 mm²

Board Design

70W
TDP
800W
250 W
Suggested PSU
1200 W
No outputs
Outputs
No outputs
None
Power Connectors
-

Graphics Features

12 Ultimate (12_2)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
1.3
Vulkan
N/A
7.5
CUDA
1.0
6.6
Shader Model
4.0

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy