Skip to content
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

Update device property names #685

Merged
merged 1 commit into from
Aug 7, 2024
Merged

Update device property names #685

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: 4 additions & 4 deletions csrc/gpu/aten/core/DeviceInfo.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,10 +34,10 @@ struct DeviceInfo {
uint32_t max_num_sub_groups;
std::vector<size_t> sub_group_sizes;
bool support_fp64;
bool support_cl_bf16_conversion;
bool support_cl_sg_matmul_acc;
bool support_cl_sg_matmul_acc_tf32;
bool support_cl_sg_2d_block_io;
bool has_bf16_conversion;
bool has_subgroup_matrix_multiply_accumulate;
bool has_subgroup_matrix_multiply_accumulate_tensor_float32;
bool has_subgroup_2d_block_io;
};

} // namespace dpcpp
Expand Down
26 changes: 18 additions & 8 deletions csrc/gpu/runtime/Device.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -323,10 +323,18 @@ static void initDeviceProperty(DeviceId device_id) {
device_prop.support_atomic64 = device.has(dpcpp_dev_aspect_atomic64);
device_prop.support_fp64 = device.has(dpcpp_dev_aspect_fp64);
sycl::ext::oneapi::experimental::cl_version version;
device_prop.support_cl_bf16_conversion = device.ext_oneapi_supports_cl_extension("cl_intel_bfloat16_conversions", &version);
device_prop.support_cl_sg_matmul_acc = device.ext_oneapi_supports_cl_extension("cl_intel_subgroup_matrix_multiply_accumulate", &version);
device_prop.support_cl_sg_matmul_acc_tf32 = device.ext_oneapi_supports_cl_extension("cl_intel_subgroup_matrix_multiply_accumulate_tensor_float32", &version);
device_prop.support_cl_sg_2d_block_io = device.ext_oneapi_supports_cl_extension("cl_intel_subgroup_2d_block_io", &version);
device_prop.has_bf16_conversion = device.ext_oneapi_supports_cl_extension(
"cl_intel_bfloat16_conversions", &version);
device_prop.has_subgroup_matrix_multiply_accumulate =
device.ext_oneapi_supports_cl_extension(
"cl_intel_subgroup_matrix_multiply_accumulate", &version);
device_prop.has_subgroup_matrix_multiply_accumulate_tensor_float32 =
device.ext_oneapi_supports_cl_extension(
"cl_intel_subgroup_matrix_multiply_accumulate_tensor_float32",
&version);
device_prop.has_subgroup_2d_block_io =
device.ext_oneapi_supports_cl_extension(
"cl_intel_subgroup_2d_block_io", &version);

device_properties[device_id] = device_prop;

Expand Down Expand Up @@ -361,10 +369,12 @@ static void initDeviceProperty(DeviceId device_id) {
dev_info.max_num_sub_groups = device_prop.max_num_subgroup;
dev_info.sub_group_sizes = device_prop.subgroup_sizes;
dev_info.support_fp64 = device_prop.support_fp64;
dev_info.support_cl_bf16_conversion = device_prop.support_cl_bf16_conversion;
dev_info.support_cl_sg_matmul_acc = device_prop.support_cl_sg_matmul_acc;
dev_info.support_cl_sg_matmul_acc_tf32 = device_prop.support_cl_sg_matmul_acc_tf32;
dev_info.support_cl_sg_2d_block_io = device_prop.support_cl_sg_2d_block_io;
dev_info.has_bf16_conversion = device_prop.has_bf16_conversion;
dev_info.has_subgroup_matrix_multiply_accumulate =
device_prop.has_subgroup_matrix_multiply_accumulate;
dev_info.has_subgroup_matrix_multiply_accumulate_tensor_float32 =
device_prop.has_subgroup_matrix_multiply_accumulate_tensor_float32;
dev_info.has_subgroup_2d_block_io = device_prop.has_subgroup_2d_block_io;
#if (defined(__INTEL_LLVM_COMPILER) && __INTEL_LLVM_COMPILER >= 20240100)
dev_info.device_arch = static_cast<uint64_t>(device_prop.device_arch);
#else
Expand Down
8 changes: 4 additions & 4 deletions csrc/gpu/runtime/DeviceProp.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,10 +143,10 @@ struct DeviceProp {

bool support_fp64;
bool support_atomic64;
bool support_cl_bf16_conversion;
bool support_cl_sg_matmul_acc;
bool support_cl_sg_matmul_acc_tf32;
bool support_cl_sg_2d_block_io;
bool has_bf16_conversion;
bool has_subgroup_matrix_multiply_accumulate;
bool has_subgroup_matrix_multiply_accumulate_tensor_float32;
bool has_subgroup_2d_block_io;
};

} // namespace dpcpp
Expand Down
25 changes: 16 additions & 9 deletions intel_extension_for_pytorch/csrc/xpu/Module.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -577,10 +577,15 @@ static void register_xpu_device_info(PyObject* module) {
.def_readonly("max_num_sub_groups", &DeviceInfo::max_num_sub_groups)
.def_readonly("sub_group_sizes", &DeviceInfo::sub_group_sizes)
.def_readonly("has_fp64", &DeviceInfo::support_fp64)
.def_readonly("support_cl_bf16_conversion", &DeviceInfo::support_cl_bf16_conversion)
.def_readonly("support_cl_sg_matmul_acc", &DeviceInfo::support_cl_sg_matmul_acc)
.def_readonly("support_cl_sg_matmul_acc_tf32", &DeviceInfo::support_cl_sg_matmul_acc_tf32)
.def_readonly("support_cl_sg_2d_block_io", &DeviceInfo::support_cl_sg_2d_block_io)
.def_readonly("has_bf16_conversion", &DeviceInfo::has_bf16_conversion)
.def_readonly(
"has_subgroup_matrix_multiply_accumulate",
&DeviceInfo::has_subgroup_matrix_multiply_accumulate)
.def_readonly(
"has_subgroup_matrix_multiply_accumulate_tensor_float32",
&DeviceInfo::has_subgroup_matrix_multiply_accumulate_tensor_float32)
.def_readonly(
"has_subgroup_2d_block_io", &DeviceInfo::has_subgroup_2d_block_io)
.def_readonly("device_arch", &DeviceInfo::device_arch)
.def_property_readonly(
"dev_type", [](const DeviceInfo& info) { return get_dev_type(info); })
Expand All @@ -593,11 +598,13 @@ static void register_xpu_device_info(PyObject* module) {
<< ", total_memory=" << info.global_mem_size / (1024 * 1024)
<< "MB, max_compute_units=" << info.max_compute_units
<< ", gpu_eu_count=" << info.gpu_eu_count
<< ", device_arch=" << info.device_arch
<< ", support_cl_bf16_conversion=" << info.support_cl_bf16_conversion
<< ", support_cl_sg_matmul_acc=" << info.support_cl_sg_matmul_acc
<< ", support_cl_sg_matmul_acc_tf32=" << info.support_cl_sg_matmul_acc_tf32
<< ", support_cl_sg_2d_block_io=" << info.support_cl_sg_2d_block_io
<< ", device_arch=" << info.device_arch
<< ", has_bf16_conversion=" << info.has_bf16_conversion
<< ", has_subgroup_matrix_multiply_accumulate="
<< info.has_subgroup_matrix_multiply_accumulate
<< ", has_subgroup_matrix_multiply_accumulate_tensor_float32="
<< info.has_subgroup_matrix_multiply_accumulate_tensor_float32
<< ", has_subgroup_2d_block_io=" << info.has_subgroup_2d_block_io
<< ")";
return stream.str();
});
Expand Down
Loading