Scribd
Upload
22 views1 page

Computer Science & Engg, Dept

CUDA is a parallel programming model that allows developers to distribute tasks across the numerous cores of a GPU. It supports multiprocessor architectures for parallel matrix multiplication and task distribution. The goal is to demonstrate concurrent execution of tasks on a multi-core GPU using CUDA. CUDA provides access to the GPU's virtual instruction set and memory, simplifying hardware but complicating software by giving the application control over memory and communication between cores.

Uploaded by

Karthik Subramanya
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
22 views1 page

Computer Science & Engg, Dept

CUDA is a parallel programming model that allows developers to distribute tasks across the numerous cores of a GPU. It supports multiprocessor architectures for parallel matrix multiplication and task distribution. The goal is to demonstrate concurrent execution of tasks on a multi-core GPU using CUDA. CUDA provides access to the GPU's virtual instruction set and memory, simplifying hardware but complicating software by giving the application control over memory and communication between cores.

Uploaded by

Karthik Subramanya
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Parallel programming with CUDA

INTRODUCTION

A parallel programming model is a set of software technologies to express parallel


algorithms and match applications with the underlying parallel systems. GPU’s have much more
processing power than CPU’s and have numerous cores that operate in parallel to run intensive
graphics operations. CUDA supports multiprocessor and multi-core architecture for task
distribution of matrix multiplication.

PROBLEM STATEMENT

To demonstrate task distribution and concurrent execution of tasks on a multi-core/


multiprocessor architecture using CUDA.

CONCLUSION

CUDA gives developers access to the virtual instruction set and memory of the parallel
computational elements in CUDA. The approach simplifies the hardware implementation but
complicates the software from a number of perspectives. For example, memory management is
under application control, as is communication between cores.

REFERENCES
[1]. David Kirk and Wen-mei. (2009). Many core-Processors for Science and Engineering
Applications.
[2]. NVIDIA, CUDA programming guide 1.1
[3]. Viola, P. Jones, M. (2004) Robust Real-Time Face Detection. International Journal of
Computer Vision.

Computer science & Engg, Dept. Page 1

You might also like