Skip to content

thomas-segercrantz: Implemented CUDA matrix multiplication #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ThomasSegercrantz wants to merge 1 commit into
base: main
Choose a base branch
from
Open

thomas-segercrantz: Implemented CUDA matrix multiplication #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions .idea/.gitignore
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions .idea/.name
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 2 additions & 0 deletions .idea/Homework-3.iml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

247 changes: 247 additions & 0 deletions .idea/editor.xml
View file
Open in desktop

Large diffs are not rendered by default.

7 changes: 7 additions & 0 deletions .idea/misc.xml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 8 additions & 0 deletions .idea/modules.xml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 6 additions & 0 deletions .idea/vcs.xml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

15 changes: 15 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,3 +205,18 @@ git push origin student-name

Good luck, and enjoy accelerating matrix multiplication with CUDA!

Here is my table, with numbers taken from the table in Assignment 2 as well:

| Test Case | Dimensions (\( m \times n \times p \)) | Naive CPU (s) | Blocked CPU (s) | Parallel CPU (s) | Naive CUDA (s) | Tiled CUDA (s) | Tiled CUDA Speedup (vs. Naive CUDA) | Tiled CUDA Speedup (vs. Parallel CPU) |
|-----------|----------------------------------------|---------------|-----------------|------------------|----------------|----------------|-------------------------------------|---------------------------------------|
| 0 | 64x64x64 | 0.000999928 | 0.00200009 | 0.00200009 | 0.000183 | 0.000108 | 1.686373x | 0.49994x |
| 1 | 128x64x128 | 0.00399995 | 0.00500011 | 0.000999928 | 0.00145 | 0.000090 | 1.611844 | 4.00024x |
| 2 | 100x128x56 | 0.00300002 | 0.00300002 | 0.00300002 | 0.000139 | 0.000079 | 1.749597x | 1x |
| 3 | 128x64x128 | 0.00600004 | 0.00399995 | 0.00200009 | 0.000266 | 0.000190 | 1.404657x | 2.99988x |
| 4 | 32x128x32 | 0.00100017 | 0.00099993 | 0 | 0.000190 | 0.000161 | 1.176062x | infx |
| 5 | 200x100x256 | 0.0210001 | 0.0209999 | 0.00700021 | 0.000264 | 0.000133 | 1.986526x | 2.99993x |
| 6 | 256x256x256 | 0.0650001 | 0.066 | 0.017 | 0.000335 | 0.000200 | 1.672361x | 3.82354x |
| 7 | 256x300x256 | 0.069 | 0.0839999 | 0.0180001 | 0.000440 | 0.000432 | 1.019646x | 3.83331x |
| 8 | 64x128x64 | 0.00300002 | 0.00300002 | 0.00300002 | 0.000194 | 0.000112 | 1.727454x | 1x |
| 9 | 256x256x257 | 0.810001 | 0.0669999 | 0.0669999 | 0.000446 | 0.000240 | 1.859331 | 5.39997x |

65 changes: 65 additions & 0 deletions data/0/result.raw
View file
Open in desktop

Large diffs are not rendered by default.

65 changes: 65 additions & 0 deletions data/0/result_naive.raw
View file
Open in desktop

Large diffs are not rendered by default.

129 changes: 129 additions & 0 deletions data/1/result.raw
View file
Open in desktop

Large diffs are not rendered by default.

Loading