Implement CPU discovery support (#77)

* Implement CPU discovery support

SWDEV-482949:

enable the CPU model name info support to the RDC, rdci command
can detect GPU and CPU modules at the same time.
It will query the CPU info through the amdsmi interface like below:

1 GPUs found.
-----------------------------------------------------------------
GPU Index        Device Information
0               AMD Radeon PRO W7800
=================================================================
1 CPUs found.
-----------------------------------------------------------------
CPU Index        Device Information
0               AMD Ryzen Threadripper PRO 7995WX 96-Cores
-----------------------------------------------------------------

Change-Id: Ibc6533c9a61000cd86c45b1bae14c3eb6788c119
Signed-off-by: Perry Yuan <perry.yuan@amd.com>

* CMAKE - Add required version for amdsmi

Change-Id: I341a89351d196ec66cce215a5d1d3953302fcc66
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

---------

Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Co-authored-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
This commit is contained in:
Yuan, Perry
2025-03-31 10:58:36 +08:00
committed by GitHub
parent 80ee980cdb
commit 3bdca8b8b6
16 changed files with 365 additions and 5 deletions
@@ -234,6 +234,30 @@ rdc_status_t RdcStandaloneHandler::rdc_device_get_all(uint32_t gpu_index_list[RD
return RDC_ST_OK;
}
rdc_status_t RdcStandaloneHandler::rdc_device_get_all_cpu(uint32_t cpu_index_list[RDC_MAX_NUM_DEVICES],
uint32_t* count) {
if (!count) {
return RDC_ST_BAD_PARAMETER;
}
::rdc::Empty request;
::rdc::GetAllCpuDevicesResponse reply;
::grpc::ClientContext context;
::grpc::Status status = stub_->GetAllCpuDevices(&context, request, &reply);
rdc_status_t err_status = error_handle(status, reply.status());
if (err_status != RDC_ST_OK) return err_status;
if (reply.cpus_size() > RDC_MAX_NUM_DEVICES) {
return RDC_ST_BAD_PARAMETER;
}
*count = reply.cpus_size();
for (uint32_t i = 0; i < *count; i++) {
cpu_index_list[i] = reply.cpus(i);
}
return RDC_ST_OK;
}
rdc_status_t RdcStandaloneHandler::rdc_device_get_attributes(uint32_t gpu_index,
rdc_device_attributes_t* p_rdc_attr) {
if (!p_rdc_attr) {
@@ -254,6 +278,27 @@ rdc_status_t RdcStandaloneHandler::rdc_device_get_attributes(uint32_t gpu_index,
return RDC_ST_OK;
}
rdc_status_t RdcStandaloneHandler::rdc_device_get_cpu_attributes(uint32_t cpu_index,
rdc_device_attributes_t* p_rdc_attr) {
if (!p_rdc_attr) {
return RDC_ST_BAD_PARAMETER;
}
::rdc::GetCpuDeviceAttributesRequest request;
::rdc::GetCpuDeviceAttributesResponse reply;
::grpc::ClientContext context;
request.set_cpu_index(cpu_index);
::grpc::Status status = stub_->GetDeviceCpuAttributes(&context, request, &reply);
rdc_status_t err_status = error_handle(status, reply.status());
if (err_status != RDC_ST_OK) return err_status;
strncpy_with_null(p_rdc_attr->device_name, reply.attributes().device_name().c_str(),
RDC_MAX_STR_LENGTH);
return RDC_ST_OK;
}
rdc_status_t RdcStandaloneHandler::rdc_device_get_component_version(
rdc_component_t component, rdc_component_version_t* p_rdc_compv) {
if (!p_rdc_compv) {