-
Notifications
You must be signed in to change notification settings - Fork 17
[GPU] Register initial GPU pipeline that uses IMEX #329
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
Conversation
Signed-off-by: dchigarev <[email protected]>
Signed-off-by: dchigarev <[email protected]>
Signed-off-by: dchigarev <[email protected]>
Signed-off-by: dchigarev <[email protected]>
// RUN: gc-opt %s --gc-gpu-pipeline \ | ||
// RUN: | gc-cpu-runner -e main --entry-point-result=void \ | ||
// RUN: --shared-libs=%mlir_runner_utils,%mlir_c_runner_utils,%opencl_runtime | FileCheck %s | ||
module{ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
changed the size of the test from 32x32 to 64x64 due to #332
Signed-off-by: dchigarev <[email protected]>
Signed-off-by: dchigarev <[email protected]>
Signed-off-by: dchigarev <[email protected]>
// Otherwise 'xegpu-to-vc' pass will fail to convert it to VC | ||
if (outputShape[0] * outputShape[1] < 16) { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
gpu-runner/mlp.mlir
test contains a linalg.fill() : tensor<1x1xf32>
op which is to small to be processed via xegpu
Register the current
linalg-xegpu-gpu_bin
pipeline as is.