Tesla D870 vs Radeon RX 550

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking	622	not rated
Place by popularity	29	not in top-100
Cost-effectiveness evaluation	2.92	no data
Power efficiency	9.90	no data
Architecture	GCN 4.0 (2016−2020)	Tesla (2006−2010)
GPU code name	Lexa	G80
Market segment	Desktop	Workstation
Release date	20 April 2017 (8 years ago)	2 May 2007 (18 years ago)
Launch price (MSRP)	$79	$7,499

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

Performance to price scatter graph

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	512	128 ×2
Core clock speed	1100 MHz	600 MHz
Boost clock speed	1183 MHz	no data
Number of transistors	2,200 million	681 million
Manufacturing process technology	14 nm	90 nm
Power consumption (TDP)	50 Watt	520 Watt
Texture fill rate	37.86	38.40 ×2
Floating-point processing power	1.211 TFLOPS	0.3456 TFLOPS ×2
ROPs	16	24 ×2
TMUs	32	32 ×2
L1 Cache	128 KB	no data
L2 Cache	512 KB	96 KB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 3.0 x8	PCIe 1.0 x16
Length	145 mm	no data
Width	2-slot	2-slot
Supplementary power connectors	None	no data

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR5	GDDR3
Maximum RAM amount	4 GB	1536 MB ×2
Memory bus width	128 Bit	384 Bit ×2
Memory clock speed	1750 MHz	800 MHz
Memory bandwidth	112.0 GB/s	76.8 GB/s ×2

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors	1x DVI, 1x HDMI, 1x DisplayPort	No outputs
HDMI	+	-

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 (12_0)	11.1 (10_0)
Shader Model	6.4	4.0
OpenGL	4.6	3.3
OpenCL	2.0	1.1
Vulkan	1.2.131	N/A
CUDA	-	+

Pros & cons summary

---

Recency	20 April 2017	2 May 2007
Maximum RAM amount	4 GB	1536 MB
Chip lithography	14 nm	90 nm
Power consumption (TDP)	50 Watt	520 Watt