GeekRadar / The comparison desk
COMPARE.
GPU
ASUS

ASUS ROG MARS II Prototype

Graphics processor

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture
Fermi*
Process node
40 nm*
GPUs per card
2*
Graphics interface
PCIe 2.0 x16*
Reported chip die area
529 mm²*
Transistors
3,100 million*
Graphics processor
GF100*
Chip foundry
TSMC*
Card or module format
Triple-slot*
Declared GPU TDP
365 W*
Suggested system PSU
750 W*
External power connectors
3x 8-pin*
DirectX / feature level
12 (11_0)*
OpenGL
4.6*
OpenCL
1.1*
CUDA compute capability
2.0*
Shader model
5.1*
Reported video memory (allocation unspecified)
1,536 MB*
Reported shader processors (allocation unspecified)
480*
Reported memory bandwidth (allocation unspecified)
164 GB/s*

Memory & storage

Video memory type
GDDR5*

Power specifications

Thermal design power
365 W*

System configuration

Detailed specifications

Specifications 1 · 24 fields
proc transistors
3,100 million*
proc die size
529* mm²
Reported shader processors (allocation unspecified)
480*
sm count
15*
memory clock
854*
Reported video memory (allocation unspecified)
1,536*
name
ASUS ROG MARS II Prototype*
ram type
GDDR5*
bus width
384*
bus interface
PCIe 2.0 x16*
Reported memory bandwidth (allocation unspecified)
164* GB/s
fp32 performance
1.1664*
fp64 performance
0.1458*
tdp
365* W
suggested psu
750* W
slot width
Triple-slot*
power connectors
3x 8-pin*
api cuda
2*
is retail board
Yes*
gpi value
4.25*
manufacturer
ASUS*
arch name
Fermi*
proc foundry
TSMC*
proc process size
40* nm
Specifications 2 · 37 fields
CUDA compute capability
2.0*
DirectX / feature level
12 (11_0)*
OpenCL
1.1*
OpenGL
4.6*
Shader model
5.1*
Architecture
Fermi*
Graphics interface
PCIe 2.0 x16*
Memory bus (allocation unspecified)
384* bit
Reported shader processors (allocation unspecified)
480*
Reported theoretical FP32 peak
1.1664* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
0.1458* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared L1 cache configuration
64 KB (per SM)*
Declared GPU L2 cache (allocation unspecified)
768 KB*
Reported display outputs
Active
2x DVI, 1x HDMI 1.3a, 1x DisplayPort*
Struck-out declarations
  • 3x DVI, 1x mini-DisplayPort*
Theoretical pixel fill rate
18.24 GPixel/s*
External power connectors
3x 8-pin*
Reported chip die area
529 mm²*
Chip foundry
TSMC*
Process node declaration
40 nm*
Transistors
3,100 million*
Graphics processor
GF100*
GPUs per card
2*
Reported video memory (allocation unspecified)
1,536* MB
Rated memory bandwidth (allocation unspecified)
164.0 GB/s*
Video memory type
GDDR5*
Raster output units (allocation unspecified)
48*
Reported shading units (allocation unspecified)
480*
Card or module format
Triple-slot*
Streaming multiprocessors (allocation unspecified)
15*
Suggested system PSU
750 W*
2:4 tensor sparsity
No*
Declared GPU TDP
365 W*
Theoretical texture fill rate
36.48 GTexel/s*
Texture mapping units (allocation unspecified)
60*
Reported shader processors (allocation unspecified)
480*
Reported video memory (allocation unspecified)
1,536* MB
Video memory type
GDDR5*

* Provisional data