8th International Conference on Soft Computing, Mathematics and Control (SMC ...
Presentation on graphics processing unit (GPU)
1. BY:
MUNTASIR MUHIT TONMOY
STUDENT ,BSC.(1ST SEMESTER)
DEPARTMENT OF SOFTWARE ENGINEERING
ID : 191-35-399
DAFFODIL INTERNATIONAL UNIVERSITY
DHAKA
GRAPHICS PROCESSING
UNIT
2. INTRODUCTION
*GPU is a graphical processing unit which enables
you run high definitions graphics on your PC,
which are the emend of modern computing. Like
the CPU , it is a single chip processor. The GPU has hundreds of cores as
compared to the 4 or 8 in the latest CPUs. The
primary job of the GPU is to compute 3D
functions .
3. G P U ARCHITECTURE
*Control hardware dominates processors
*Complex, difficult to build
*Takes substantial fraction of die Scales poorly
*Pay for max output, sustain average
output
*Quadratic dependency checking
*Control hardware doesn’t do any math!
5. LATEST TECHNOLOGY USE
NVIDIA
– Tesla HPC specific GPUs have evolved
from GeForce series
*AMD
– Fire Stream HPC specific GPUs have
evolved from (ATI) Radeon series
*Intel
– Knights Corner many-core x86 chip is
like hybrid between a GPU and many-core CPU
6. CHARACTERISTICS OF GRAPHICS
IN G P U
*Large computational requirements
*Massive parallelism
*Graphics pipeline designed for
independent operations
* GPUs are good at parallel, arithmetically
intense, streaming-memory problems
7. CONCLUSION AND FUTURE WORK
*This paper presents our evaluation and analysis of the efficiency of GPU
computing for data-parallel scientific applications. Starting with a
bimolecular code that calculates electrostatic properties in a data parallel manner (i.e., GEM), we evaluate our different
implementations
of GEM across three metrics: performance, energy consumption, and
energy efficiency.