-
Notifications
You must be signed in to change notification settings - Fork 14
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.
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
Improve Batched GEMV Speed #113
base: master
Are you sure you want to change the base?
Commits on Jul 11, 2016
-
Refactor gemv_prog Geometry into a separate class
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 74fb5c2 - Browse repository at this point
Copy the full SHA 74fb5c2View commit details -
Compute bandwidth and FLOPS in test_clra_gemv
In addition, run GEMV multiple times to improve the accuracy of the result. Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for e5e445d - Browse repository at this point
Copy the full SHA e5e445dView commit details -
Print profiling stats when profiling is not 0
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for d4f5aa1 - Browse repository at this point
Copy the full SHA d4f5aa1View commit details -
Show profiling runtime to five decimal places
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for a496cf3 - Browse repository at this point
Copy the full SHA a496cf3View commit details -
Use list instead of map when generating profiling columns
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for a982813 - Browse repository at this point
Copy the full SHA a982813View commit details -
Support both row and column-major RaggedArray
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for e8c0759 - Browse repository at this point
Copy the full SHA e8c0759View commit details -
Descriptive block_impl NotImplementedError messages
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 162d7eb - Browse repository at this point
Copy the full SHA 162d7ebView commit details -
Add some comments to geometry for clarification
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 621f776 - Browse repository at this point
Copy the full SHA 621f776View commit details -
Generate a_s0 or a_s1 in cl_geometry_and_textconf
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 6690d23 - Browse repository at this point
Copy the full SHA 6690d23View commit details -
Make clra_gemv reduce_impl column-major
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 3e97b6a - Browse repository at this point
Copy the full SHA 3e97b6aView commit details -
Make clra_gemv block_impl column-major
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 7a1b166 - Browse repository at this point
Copy the full SHA 7a1b166View commit details
Commits on Jul 16, 2016
-
Add clra_gemv one_thread_per_row_impl
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 1308e04 - Browse repository at this point
Copy the full SHA 1308e04View commit details -
Fix RaggedArray stride and order assert
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 2c8d10f - Browse repository at this point
Copy the full SHA 2c8d10fView commit details
Commits on Jul 31, 2016
-
Implement current LIF model in nengo
This commit implements the more accurate LIF model, implemented in Nengo 2.1.1, in OpenCL. A new boolean argument `fastlif' is also added in plan_lif, which defaults to False. See <nengo/nengo#975> for details regarding the new LIF model. Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 43d747b - Browse repository at this point
Copy the full SHA 43d747bView commit details
Commits on Aug 1, 2016
-
Modify clra_nonlineralities to accept column-major
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 161a032 - Browse repository at this point
Copy the full SHA 161a032View commit details -
Fix CLRaggedArray __setitem__ for column-major
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 92349e4 - Browse repository at this point
Copy the full SHA 92349e4View commit details -
Use column-major RaggedArray by default
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for e0c3297 - Browse repository at this point
Copy the full SHA e0c3297View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0c3b028 - Browse repository at this point
Copy the full SHA 0c3b028View commit details -
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 2a33c21 - Browse repository at this point
Copy the full SHA 2a33c21View commit details -
Use plan_one_thread_per_row_gemv in Simulator
Signed-off-by: Shaun Ren <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for d4fa2a4 - Browse repository at this point
Copy the full SHA d4fa2a4View commit details