Tesla S870 vs FirePro V3900

Primary details

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

Place in the ranking	1022	not rated
Place by popularity	not in top-100	not in top-100
Power efficiency	2.33	no data
Architecture	TeraScale 2 (2009−2015)	Tesla (2006−2010)
GPU code name	Turks	G80
Market segment	Workstation	Workstation
Release date	7 February 2012 (14 years ago)	2 May 2007 (19 years ago)
Launch price (MSRP)	$119	$11,999

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	480	128 ×4
Core clock speed	650 MHz	600 MHz
Number of transistors	716 million	681 million
Manufacturing process technology	40 nm	90 nm
Power consumption (TDP)	199 Watt	800 Watt
Texture fill rate	15.60	38.40 ×4
Floating-point processing power	0.624 TFLOPS	0.3456 TFLOPS ×4
ROPs	8	24 ×4
TMUs	24	32 ×4
L1 Cache	48 KB	no data
L2 Cache	256 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).

Bus support	PCIe 2.1 x16	no data
Interface	PCIe 2.0 x16	PCIe 1.0 x16
Length	168 mm	no data
Width	1-slot	2-slot
Form factor	half height / half length	no data
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	GDDR3	GDDR3
Maximum RAM amount	1 GB	1536 MB ×4
Memory bus width	128 Bit	384 Bit ×4
Memory clock speed	900 MHz	800 MHz
Memory bandwidth	28 GB/s	76.8 GB/s ×4

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 DisplayPort 1.1	No outputs
DisplayPort count	1	no data
Dual-link DVI support	+	-
HD сomponent video output	+	-

API and SDK support

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

DirectX	11.2 (11_0)	11.1 (10_0)
Shader Model	5.0	4.0
OpenGL	4.4	3.3
OpenCL	1.2	1.1
Vulkan	N/A	N/A
CUDA	-	+

Pros & cons summary

---

Recency	7 February 2012	2 May 2007
Maximum RAM amount	1 GB	1536 MB
Chip lithography	40 nm	90 nm
Power consumption (TDP)	199 Watt	800 Watt