Redefining the Role of the CPU in the Era of CPU-GPU Integration

Manish Arora, Siddhartha Nath, Subhra Mazumdar, Scott Baden, Dean Tullsen
Department of Computer Science & Engineering, University of California, San Diego
IEEE Micro, Issue: 99, 2012

   title={Redefining the Role of the CPU in the Era of CPU-GPU Integration},

   author={Arora, M. and Nath, S. and Mazumdar, S. and Baden, S. and Tullsen, D.},




Download Download (PDF)   View View   Source Source   



GPU computing has emerged as a viable alternative to CPUs for throughput oriented applications or regions of code. Speedups of 10 to 100x over CPU implementations have been reported. This trend is expected to continue in the future with GPU architectural advances, improved programming support, scaling, and tighter CPU-GPU chip integration. However, not all code will get mapped to the GPUs, even for many of those applications which map well to the GPU – the CPU still runs code that is not targeted to the GPU, and often that code is still very much performance-critical. This paper demonstrates that the code that the CPU will be expected to execute in an integrated CPU-GPU environment is profoundly different than the code it has been optimized for over the past many generations. The characteristics of this new code should drive future CPU design and architecture. Specifically, this work shows that post-GPU code tends to have lower ILP, significantly more difficult to predict loads, harder to predict stores, and more difficult branch prediction. Post-GPU code exhibits smaller gains from the availability of multiple cores because of reduced thread level parallelism.
VN:F [1.9.22_1171]
Rating: 5.0/5 (2 votes cast)
Redefining the Role of the CPU in the Era of CPU-GPU Integration, 5.0 out of 5 based on 2 ratings

* * *

* * *

Follow us on Twitter

HGPU group

1543 peoples are following HGPU @twitter

Like us on Facebook

HGPU group

274 people like HGPU on Facebook

* * *

Free GPU computing nodes at hgpu.org

Registered users can now run their OpenCL application at hgpu.org. We provide 1 minute of computer time per each run on two nodes with two AMD and one nVidia graphics processing units, correspondingly. There are no restrictions on the number of starts.

The platforms are

Node 1
  • GPU device 0: nVidia GeForce GTX 560 Ti 2GB, 822MHz
  • GPU device 1: AMD/ATI Radeon HD 6970 2GB, 880MHz
  • CPU: AMD Phenom II X6 @ 2.8GHz 1055T
  • RAM: 12GB
  • OS: OpenSUSE 13.1
  • SDK: nVidia CUDA Toolkit 6.5.14, AMD APP SDK 3.0
Node 2
  • GPU device 0: AMD/ATI Radeon HD 7970 3GB, 1000MHz
  • GPU device 1: AMD/ATI Radeon HD 5870 2GB, 850MHz
  • CPU: Intel Core i7-2600 @ 3.4GHz
  • RAM: 16GB
  • OS: OpenSUSE 12.3
  • SDK: AMD APP SDK 3.0

Completed OpenCL project should be uploaded via User dashboard (see instructions and example there), compilation and execution terminal output logs will be provided to the user.

The information send to hgpu.org will be treated according to our Privacy Policy

HGPU group © 2010-2015 hgpu.org

All rights belong to the respective authors

Contact us: