NVIDIA Tesla D870 vs NVIDIA Tesla S870

Comparative analysis of NVIDIA Tesla D870 and NVIDIA Tesla S870 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory.

NVIDIA Tesla D870

NVIDIA Tesla S870

Differences

Reasons to consider the NVIDIA Tesla D870

Around 54% lower typical power consumption: 520 Watt vs 800 Watt

Thermal Design Power (TDP)	520 Watt vs 800 Watt

Reasons to consider the NVIDIA Tesla S870

Around 91% higher texture fill rate: 4x 19.2 GTexel / s billion / sec vs 2x 19.2 GTexel / s billion / sec
2x more pipelines: 4x 128 vs 2x 128
2x better floating-point performance: 4x 345.6 gflops vs 2x 345.6 gflops
2x more maximum memory size: 4x 1536 MB vs 2x 1536 MB

Texture fill rate	4x 19.2 GTexel / s billion / sec vs 2x 19.2 GTexel / s billion / sec
Pipelines	4x 128 vs 2x 128
Floating-point performance	4x 345.6 gflops vs 2x 345.6 gflops
Maximum memory size	4x 1536 MB vs 2x 1536 MB

Compare specifications (specs)

	NVIDIA Tesla D870	NVIDIA Tesla S870
Essentials
Architecture	Tesla	Tesla
Code name	G80	G80
Launch date	2 May 2007	2 May 2007
Launch price (MSRP)	$7,499	$11,999
Place in performance rating	not rated	not rated
Type	Workstation	Workstation
Technical info
Core clock speed	600 MHz	600 MHz
Floating-point performance	2x 345.6 gflops	4x 345.6 gflops
Manufacturing process technology	90 nm	90 nm
Pipelines	2x 128	4x 128
Texture fill rate	2x 19.2 GTexel / s billion / sec	4x 19.2 GTexel / s billion / sec
Thermal Design Power (TDP)	520 Watt	800 Watt
Transistor count	681 million	681 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 1.0 x16	PCIe 1.0 x16
API support
DirectX	10.0	10.0
OpenGL	3.3	3.3
Memory
Maximum RAM amount	2x 1536 MB	4x 1536 MB
Memory bandwidth	2x 76.8 GB / s	4x 76.8 GB / s
Memory bus width	2x 384 Bit	4x 384 Bit
Memory clock speed	1600 MHz	1600 MHz
Memory type	GDDR3	GDDR3