Skip to content

Emit informational msgs regarding recompilation with different GRF mode under TRITON_DEBUG #2385

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

Merged
merged 2 commits into from
Sep 30, 2024
Merged

Emit informational msgs regarding recompilation with different GRF mode under TRITON_DEBUG #2385

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8d26281
Emit informational messages regarding recompilation with different GR…
etiotto Sep 30, 2024
30a29f6
Address code review comments
etiotto Sep 30, 2024
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
15 changes: 11 additions & 4 deletions third_party/intel/backend/driver.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,9 +192,13 @@ static PyObject *loadBinary(PyObject *self, PyObject *args) {
// If the register mode isn't set, and the number of spills is greater
// than the threshold, recompile the kernel using large GRF mode.
if (!is_GRF_mode_specified && n_spills > max_reg_spill) {
std::cout << "(I): Detected " << n_spills
<< " spills, recompiling the kernel using large GRF mode"
<< std::endl;
std::optional<bool> debugEnabled =
isEnvValueBool(getStrEnv("TRITON_DEBUG"));
if (debugEnabled)
std::cout << "(I): Detected " << n_spills
<< " spills, recompiling kernel \"" << kernel_name
<< "\" using large GRF mode" << std::endl;

const std::string new_build_flags =
build_flags_str.append(" -cl-intel-256-GRF-per-thread");
l0_module = checkSyclErrors(
Expand All @@ -204,7 +208,10 @@ static PyObject *loadBinary(PyObject *self, PyObject *args) {
l0_kernel = checkL0Errors(l0_module);
gpuAssert(zeKernelGetProperties(l0_kernel, &props));
n_spills = props.spillMemSize;
std::cout << "(I): Kernel has now " << n_spills << " spills" << std::endl;

if (debugEnabled)
std::cout << "(I): Kernel has now " << n_spills << " spills"
<< std::endl;
}
}

Expand Down