The Quadro Plex 2100 S4 was a professional graphics card by NVIDIA, launched on July 25th, 2008. Built on the 90 nm process, and based on the G80 graphics processor, the card supports DirectX 11.1. Even though it supports DirectX 11, the feature level is only 10_0, which can be problematic with many DirectX 11 & DirectX 12 titles. The G80 graphics processor is a large chip with a die area of 484 mm² and 681 million transistors. Quadro Plex 2100 S4 combines four graphics processors to increase performance. It features 128 shading units, 32 texture mapping units, and 24 ROPs, per GPU. NVIDIA has paired 6 GB GDDR3 memory with the Quadro Plex 2100 S4, which are connected using a 384-bit memory interface per GPU (each GPU manages 1,536 MB). The GPU is operating at a frequency of 600 MHz, memory is running at 800 MHz. Its power draw is rated at 640 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Quadro Plex 2100 S4 is connected to the rest of the system using a PCI-Express 1.0 x16 interface.
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
GPU Clock
600 MHz
Shader Clock
1350 MHz
Memory Clock
800 MHz
1600 Mbps effective
Memory
Memory Size
1536 MB
Memory Type
GDDR3
Memory Bus
384 bit
Bandwidth
76.80 GB/s
Render Config
Shading Units
128
TMUs
32
ROPs
24
SM Count
16
L2 Cache
96 KB
Theoretical Performance
Pixel Rate
14.40 GPixel/s
Texture Rate
38.40 GTexel/s
FP32 (float)
345.6 GFLOPS
Board Design
Length
522 mm
20.6 inches
TDP
640 W
Suggested PSU
1000 W
Outputs
No outputs
Graphics Features
DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1 (1.0)
Vulkan
N/A
CUDA
1.0
Shader Model
4.0
Card Notes
4x Quadro FX 5600
G80 GPU Notes
Each Streaming Multiprocessor(SM) in the chip architecture contains 8 SPs and 2 SFUs.
Each SP can fulfill up to two single precision operations MAD per clock.
Each SFU can fulfill up to four operations SF per clock (these units can also handle single-precision floating-point multiplications per clock).
The approximate ratio of operations MAD to operations SF is equal 2:1.
The theoretical SP + SFU performance in single-precision floating point operations
[FLOPSsp + sfu, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following formula: FLOPSsp+sfu; f × n × 3.
Alternative formula: FLOPSsp+sfu; f × m × ( 8 SPs * 2 (MAD) + 4 * 2 SFUs ). [m] - SM count.
SP - Shader Processor (Unified Shader, CUDA Core)
SFU - Special Function Unit
SM - Streaming Multiprocessor
MAD - ADD+MUL
Latest Drivers:
Windows 2000:
Quadro Release 261.19
Windows XP / Server 2003 x64:
GeForce Release 340.52
Quadro Release R319 U2 (321.01)
Tesla Release 258.96
Windows Vista / 7 / 8 / 8.1 / 10 32-bit:
GeForce Release 342.01
Quadro Release R340 U15 (342.01)
Tesla Release 258.96