ATI Radeon HD 5870 vs NVIDIA Tesla P10
GPU · Specs Compare
Graphics Card
Release Date
Sep 2009
Sep 2016
Generation
Evergreen
Tesla Pascal
Type
Desktop
Professional
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Clock Speeds
Memory Clock
1200 MHz
1808 MHz
Base Clock
—
1025 MHz
Boost Clock
—
1493 MHz
Memory
Memory Size
1024MB
24GB
Memory Type
GDDR5
GDDR5X
Memory Bus
256bit
384bit
Bandwidth
153.6GB/s
694.3GB/s
Render Config
Compute Units
20
—
Shading Units
1600
3840
TMUs
80
240
ROPs
32
96
L1 Cache
8 KB (per CU)
48 KB (per SM)
L2 Cache
512 KB
3 MB
SM Count
—
30
Theoretical Performance
Pixel Rate
27.20 GPixel/s
143.3 GPixel/s
Texture Rate
68.00 GTexel/s
358.3 GTexel/s
FP32 (float)
2.720 TFLOPS
11.47 TFLOPS
FP64 (double)
544.0 GFLOPS
358.3 GFLOPS
FP16 (half)
—
179.2 GFLOPS
Graphics Processor
GPU Name
Cypress
GP102
GPU Variant
Cypress XT(215-0735033)
—
Architecture
TeraScale 2
Pascal
Foundry
TSMC
TSMC
Process Size
40 nm
16 nm
Transistors
2.154 billion
11.8 billion
Die Size
334 mm²
471 mm²
Board Design
TDP
188W
150W
Suggested PSU
450 W
450 W
Outputs
2x DVI1x HDMI 1.3a1x DisplayPort 1.1
No outputs
Power Connectors
2x 6-pin
1x 8-pin
Graphics Features
DirectX
11.2 (11_0)
12 (12_1)
OpenGL
4.4
4.6
OpenCL
1.2
3.0
Vulkan
N/A
1.4
Shader Model
5.0
6.8
CUDA
—
6.1
▲ Specs Compare
Data sourced from official specifications and benchmark tests.