ATI Radeon HD 5870 vs NVIDIA Tesla T4
GPU · Specs Compare
Graphics Card
Release Date
Sep 2009
Sep 2018
Generation
Evergreen
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Clock Speeds
Memory Clock
1200 MHz
1250 MHz
Base Clock
—
585 MHz
Boost Clock
—
1590 MHz
Memory
Memory Size
1024MB
16GB
Memory Type
GDDR5
GDDR6
Memory Bus
256bit
256bit
Bandwidth
153.6GB/s
320.0GB/s
Render Config
Compute Units
20
—
Shading Units
1600
2560
TMUs
80
160
ROPs
32
64
L1 Cache
8 KB (per CU)
64 KB (per SM)
L2 Cache
512 KB
4 MB
SM Count
—
40
Tensor Cores
—
320
RT Cores
—
40
Theoretical Performance
Pixel Rate
27.20 GPixel/s
101.8 GPixel/s
Texture Rate
68.00 GTexel/s
254.4 GTexel/s
FP32 (float)
2.720 TFLOPS
8.141 TFLOPS
FP64 (double)
544.0 GFLOPS
254.4 GFLOPS
FP16 (half)
—
65.13 TFLOPS
Graphics Processor
GPU Name
Cypress
TU104
GPU Variant
Cypress XT(215-0735033)
TU104-895-A1
Architecture
TeraScale 2
Turing
Foundry
TSMC
TSMC
Process Size
40 nm
12 nm
Transistors
2.154 billion
13.6 billion
Die Size
334 mm²
545 mm²
Board Design
TDP
188W
70W
Suggested PSU
450 W
250 W
Outputs
2x DVI1x HDMI 1.3a1x DisplayPort 1.1
No outputs
Power Connectors
2x 6-pin
None
Graphics Features
DirectX
11.2 (11_0)
12 Ultimate (12_2)
OpenGL
4.4
4.6
OpenCL
1.2
3.0
Vulkan
N/A
1.3
Shader Model
5.0
6.6
CUDA
—
7.5
Benchmark
Blender
—
1,652
▲ Specs Compare
Data sourced from official specifications and benchmark tests.