Radeon R7 360 896SP 

Released June, 2015
  • 1.1 GHz
  • 2 GB GDDR5

In order to support the ability for NVIDIA’s Kepler architecture to launch additional workloads a new Grid Management Unit was built that handles the incoming workloads from the host system as well as the algorithmically created workloads and balances accordingly.
by Ryan-Shrout (May, 2012)
For this reason Imagination has continued to iterate on the Rogue architecture for Series7 to further improve its efficiency and resulting performance.
by Ryan-Smith (Nov, 2014)

Features Key features of the Radeon R7 360 896SP

memory bandwidth Rate at which data can be read from or stored in onboard memory

Radeon R7 360 896SP
96 GB/s
GeForce GTX 750 Ti
86.4 GB/s

pixel rate Number of pixels a graphics card can render to the screen every second

Radeon R7 360 896SP
17.6 GPixel/s
GeForce 9600 GSO 512
8.8 GPixel/s
GeForce GTX 750 Ti
16.32 GPixel/s

texture rate Speed at which a graphics card can perform texture mapping

Radeon R7 360 896SP
61.6 GTexel/s
GeForce 9600 GSO 512
13.2 GTexel/s
GeForce GTX 750 Ti
40.8 GTexel/s

floating point performance How fast the gpu can crunch numbers

Radeon R7 360 896SP
1,971.2 GFLOPS
GeForce GTX 750 Ti
1,305.6 GFLOPS

shading units Subcomponents of the gpu, these run in parallel to enable fast pixel shading

Radeon R7 360 896SP

texture mapping units Built into each gpu, these resize and rotate bitmaps for texturing scenes

Radeon R7 360 896SP

In The News From around the web

With the Rogue USCs implementing a modern shader pipeline, there’s no innate weakness to the design that requires correction.
It should be noted that these numbers do not hold power consumption equal – higher utilization means transistors doing more work and burning energy more often – so real-world performance gains in power/heat limited scenarios would not be as great.
While the Haswell processors were met with a great response and backed by a variety of overclocking features, the processors didn’t happen to be great at overclocking due to the cheaper application of TIM between the IHS (Internal Heat Spreader) and the Haswell silicon itself which resulted in the heat to remain trapped between the chip due to poor contact.
Team MSI has won the $5000 US prize by claiming the Devil’s Canyon Air/Liquid world record achieving a core clock of 5498 MHz or 5.498 GHz.

It is a mistake not to support DX11.1 on Win 7

by David Stellmack |
It is hard to determine if this is something that gamers will consider a must-have feature and something that developers will feel needs to be included in their games.
The biggest feature of DirectX 11.1 is that it adds native stereoscopic 3D support, which gives native 11.1 applications support for viewing the content via 3D stereoscopic glasses by default, as it is built-in.

Nvidia Debuts GK110-based 7.1 Billion Transistor Super GPU

by Marcus Yam |
SMX's energy efficiency was achieved by increasing its number of CUDA architecture cores by four times, while reducing the clock speed of each core, power-gating parts of the GPU when idle and maximizing the GPU area devoted to parallel-processing cores instead of control logic.
While that card is the king of gaming (for now), the big daddy of Nvidia Kepler-based GPUs isn't even here yet.

Specifications Full list of technical specs


GPU brand AMD
GPU name Tobago
Market Desktop
Clock speed 1,100 MHz
Is dual GPU No
Reference card AMD Radeon R7 360 896SP 1.1 GHz 2 GB

raw performance

Shading units 896
Texture mapping units 56
Render output processors 16
Compute units 14
Pixel rate 17.6 GPixel/s
Texture rate 61.6 GTexel/s
Floating-point performance 1,971.2 GFLOPS


Memory clock speed 1,500 MHz
Effective memory clock speed 6,000 MHz
Memory bus 128 bit
Memory 2,048 MB
Memory type GDDR5
Memory bandwidth 96 GB/s

noise and power

Report a correction


comments powered by Disqus