The Tesla C2075 was a professional graphics card by NVIDIA, launched on July 25th, 2011. Built on the 40 nm process, and based on the GF110 graphics processor, in its GF110-351-A1 variant, the card supports DirectX 12. The GF110 graphics processor is a large chip with a die area of 520 mm² and 3,000 million transistors. Unlike the fully unlocked GeForce GTX 580, which uses the same GPU but has all 512 shaders enabled, NVIDIA has disabled some shading units on the Tesla C2075 to reach the product's target shader count. It features 448 shading units, 56 texture mapping units, and 48 ROPs. NVIDIA has paired 6 GB GDDR5 memory with the Tesla C2075, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 574 MHz, memory is running at 783 MHz (3.1 Gbps effective). Being a dual-slot card, the NVIDIA Tesla C2075 draws power from 1x 6-pin + 1x 8-pin power connector, with power draw rated at 247 W maximum. Display outputs include: 1x DVI. Tesla C2075 is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 248 mm in length, and features a dual-slot cooling solution.
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
574 MHz
Shader Clock
1147 MHz
Memory Clock
783 MHz
3.1 Gbps effective
Memory
Memory Size
6 GB
Memory Type
GDDR5
Memory Bus
384 bit
Bandwidth
150.3 GB/s
Render Config
Shading Units
448
TMUs
56
ROPs
48
SM Count
14
L1 Cache
64 KB (per SM)
L2 Cache
768 KB
Theoretical Performance
Pixel Rate
16.07 GPixel/s
Texture Rate
32.14 GTexel/s
FP32 (float)
1,028 GFLOPS
FP64 (double)
513.9 GFLOPS (1:2)
Board Design
Slot Width
Dual-slot
Length
248 mm
9.8 inches
TDP
247 W
Suggested PSU
550 W
Outputs
1x DVI
Power Connectors
1x 6-pin + 1x 8-pin
Board Number
P1030 SKU 221
Graphics Features
DirectX
12 (11_0)
OpenGL
4.6
OpenCL
1.1
Vulkan
N/A
CUDA
2.0
Shader Model
5.1
GF110 GPU Notes
PureVideo HD: VP4
VDPAU: Feature Set C
GF110 has 4 GPCs each capable of 8 pixels per clock. This limits complete GPU to 32 pixels per clock and because of that it can't feed all 48 ROPs when they all require data at the same time.
Additional ROPs however can be used for MSAA (because it doesn't require additional data from rasterizers, while giving more work to ROPs.)
The complete die contains 64 texture address units and 256 texture filtering units.
Latest Drivers:
Windows XP / Server 2003 x64:
GeForce Release 368.81
Quadro Release R319 U2 (321.01)
Tesla Release 340.62 / R319 U2 (321.01)
Windows Vista:
GeForce Release 365.19
Quadro Release R346 U7 (348.40)
Tesla Release 340.84