0
Rohit khatana
Parallel Computing With GPU
Rohit Khatana
4344
Seminar guide
Prof. Aparna Joshi
ARMY INSTITUE OF TECHNOLOGY
Rohit khatana
Content
1.What is parallel computing?
2.Gpu
3.CUDA
4.Application
Rohit khatana
What is Parallel Computing?
Performing or Executing a task/program
on more than one machine or processor.
...
Rohit khatana
For example
Rohit khatana
What kind of processors will we
build?
(major design constraint: power)
Cpu: - Complex Control Hardware
Flexibility + Perf...
Modern GPU has more ALU’s
Graphics Logical Pipeline
• The GPU receives geometry information
from the CPU as an input and provides
a picture as an ou...
Host Interface
• The host interface is the communication bridge
between the CPU and the GPU
• It receives commands from th...
Vertex Processing
• The vertex processing stage receives vertices from the
host interface in object space and outputs them...
Triangle Setup
• In this stage geometry information becomes raster
information (screen space geometry is the input,
pixels...
Triangle Setup
• A fragment is generated if and only if its center
is inside the triangle
• Every fragment generated has i...
Fragment Processing
• Each fragment provided by triangle setup is fed
into fragment processing as a set of attributes
(pos...
Memory Interface
• Fragments provided by the last step are written to
the framebuffer.
• Before the final write occurs, so...
Memory Model of GPU
Basic Architecture of GPU
CUDA(compute unified device
Architecture)
• CUDA is a parallel computing platform and
programming model.
• Created by NVID...
CUDA
• CUDA gives developers access to the
virtual instruction set and memory of the
parallel computational elements in CU...
Programming Model
• Threads are organized into blocks.
• Blocks are organized into a grid.
• A multiprocessor executes one...
Typical CUDA/GPU Program
1. CPU allocates storage on GPU (cudaMalloc).
2. CPU copies input data from CPU GPU
(cudaMemcpy)....
simply squaring the elements of an array
__global__ void square(float * d_out, float * d_in){
// Todo: Fill in this functi...
Main program
int main(int argc, char **argv){
……………………
…………………….
float h_out[ARRAY_SIZE];
//declare GPU pointer
float * d_...
Main program(cont.)
// transfer the array to the GPU
cudaMemcpy(d_in, h_in, ARRAY_BYTES, cudaMemcpyHostToDevice);
// launc...
Programming Model
GPU vs CPU Code
Conclusion
• GPU computing is a good choice for fine-
grained data-parallel programs with limited
communication
• GPU comp...
References
• 1.[‘IEEE’] Accelerating image processing capability using
graphics processors Jason. Dalea, Gordon. Caina, Br...
Parallel computing with Gpu
Parallel computing with Gpu
Parallel computing with Gpu
Parallel computing with Gpu
Parallel computing with Gpu
Parallel computing with Gpu
Upcoming SlideShare
Loading in...5
×

Parallel computing with Gpu

401

Published on

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
401
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
34
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Transcript of "Parallel computing with Gpu"

  1. 1. Rohit khatana Parallel Computing With GPU Rohit Khatana 4344 Seminar guide Prof. Aparna Joshi ARMY INSTITUE OF TECHNOLOGY
  2. 2. Rohit khatana Content 1.What is parallel computing? 2.Gpu 3.CUDA 4.Application
  3. 3. Rohit khatana What is Parallel Computing? Performing or Executing a task/program on more than one machine or processor. In simple way dividing a job in a group.
  4. 4. Rohit khatana For example
  5. 5. Rohit khatana
  6. 6. What kind of processors will we build? (major design constraint: power) Cpu: - Complex Control Hardware Flexibility + Performance Expensive in Terms of Power GPU: - Simpler Control Hardware More H/W for Computation Potentially More power Efficient (ops/watt) More Restrictive Programming Model
  7. 7. Modern GPU has more ALU’s
  8. 8. Graphics Logical Pipeline • The GPU receives geometry information from the CPU as an input and provides a picture as an output • Let’s see how that happens
  9. 9. Host Interface • The host interface is the communication bridge between the CPU and the GPU • It receives commands from the CPU and also pulls geometry information from system memory • It outputs a stream of vertices in object space with all their associated information (normals, texture coordinates, per vertex color etc)
  10. 10. Vertex Processing • The vertex processing stage receives vertices from the host interface in object space and outputs them in screen space • This may be a simple linear transformation, or a complex operation involving morphing effects • No new vertices are created in this stage, and no vertices are discarded (input/output has 1:1 mapping)
  11. 11. Triangle Setup • In this stage geometry information becomes raster information (screen space geometry is the input, pixels are the output) • Prior to rasterization, triangles that are backfacing or are located outside the viewing frustrum are rejected
  12. 12. Triangle Setup • A fragment is generated if and only if its center is inside the triangle • Every fragment generated has its attributes computed to be the perspective correct interpolation of the three vertices that make up the triangle
  13. 13. Fragment Processing • Each fragment provided by triangle setup is fed into fragment processing as a set of attributes (position, normal, texcoord etc), which are used to compute the final color for this pixel • The computations taking place here include texture mapping and math operations
  14. 14. Memory Interface • Fragments provided by the last step are written to the framebuffer. • Before the final write occurs, some fragments are rejected by the zbuffer, stencil and alpha tests
  15. 15. Memory Model of GPU
  16. 16. Basic Architecture of GPU
  17. 17. CUDA(compute unified device Architecture) • CUDA is a parallel computing platform and programming model. • Created by NVIDIA and implemented by the GPUs that they produce.
  18. 18. CUDA • CUDA gives developers access to the virtual instruction set and memory of the parallel computational elements in CUDA GPUs. • CUDA supports standard programming languages , including C++,python , Fortran.
  19. 19. Programming Model • Threads are organized into blocks. • Blocks are organized into a grid. • A multiprocessor executes one block at a time. • A warp is the set of threads executed in parallel. • 32 threads in a warp.
  20. 20. Typical CUDA/GPU Program 1. CPU allocates storage on GPU (cudaMalloc). 2. CPU copies input data from CPU GPU (cudaMemcpy). 3. CPU launches kernel on GPU to process the data. (Kernel function<<<no of threads>>>(parameter)) 4. CPU copies results back to CPU from GPU (cudaMemcpy)
  21. 21. simply squaring the elements of an array __global__ void square(float * d_out, float * d_in){ // Todo: Fill in this function int idx = threadIdx.x; float f = d_in[idx]; d_out[idx] = f*f } theadIdx.x =gives the current thread number GPU/CUDA programming
  22. 22. Main program int main(int argc, char **argv){ …………………… ……………………. float h_out[ARRAY_SIZE]; //declare GPU pointer float * d_in; float * d_out; // allocate GPU memory cudaMalloc( (void*) &d_in, ARRAY_BYTES); cudaMalloc( (void*) &d_out, ARRAY_BYTES);
  23. 23. Main program(cont.) // transfer the array to the GPU cudaMemcpy(d_in, h_in, ARRAY_BYTES, cudaMemcpyHostToDevice); // launch the kernel square<<<1, ARRAY_SIZE>>>(d_out, d_in); // copy back the result array to the CPU cudaMemcpy(h_out, d_out, ARRAY_BYTES, cudaMemcpyDeviceToHost); // print out the resulting array for (int i =0; i < ARRAY_SIZE; i++) { printf("%f", h_out[i]); }
  24. 24. Programming Model
  25. 25. GPU vs CPU Code
  26. 26. Conclusion • GPU computing is a good choice for fine- grained data-parallel programs with limited communication • GPU computing is not so good for coarse- grained program with a lot of communication • The GPU has become a co-processor to the CPU.
  27. 27. References • 1.[‘IEEE’] Accelerating image processing capability using graphics processors Jason. Dalea, Gordon. Caina, Brad. ZellbaVision4ce Ltd. Crowthorne Enterprise Center, Crowthorne, Berkshire, UK, RG45 6AWbVision4ce LLC Severna Park, USA, MD2114 • • 2.Udacity cs344,Intro to parallel Programming with GPU • 3.Wikipedia • 4.Nividia docs
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×