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
zatwierdzone przez GitHub
rodzic 80ee980cdb
commit 3bdca8b8b6
16 zmienionych plików z 365 dodań i 5 usunięć
@@ -53,8 +53,13 @@ class RdcEmbeddedHandler final : public RdcHandler {
// Discovery API
rdc_status_t rdc_device_get_all(uint32_t gpu_index_list[RDC_MAX_NUM_DEVICES],
uint32_t* count) override;
// Discovery API For CPU
rdc_status_t rdc_device_get_all_cpu(uint32_t cpu_index_list[RDC_MAX_NUM_DEVICES],
uint32_t* count) override;
rdc_status_t rdc_device_get_attributes(uint32_t gpu_index,
rdc_device_attributes_t* p_rdc_attr) override;
rdc_status_t rdc_device_get_cpu_attributes(uint32_t cpu_index,
rdc_device_attributes_t* p_rdc_attr) override;
rdc_status_t rdc_device_get_component_version(rdc_component_t component,
rdc_component_version_t* p_rdc_compv) override;
@@ -71,6 +71,8 @@ class RdcMetricFetcherImpl final : public RdcMetricFetcher {
public:
rdc_status_t fetch_smi_field(uint32_t gpu_index, rdc_field_t field_id,
rdc_field_value* value) override;
rdc_status_t fetch_smi_cpu_field(uint32_t cpu_index, rdc_field_t field_id,
rdc_field_value* value) override;
rdc_status_t bulk_fetch_smi_fields(
rdc_gpu_field_t* fields, uint32_t fields_count,
std::vector<rdc_gpu_field_value_t>& results) override; // NOLINT
@@ -47,8 +47,12 @@ class RdcStandaloneHandler : public RdcHandler {
// Discovery RdcAPI
rdc_status_t rdc_device_get_all(uint32_t gpu_index_list[RDC_MAX_NUM_DEVICES],
uint32_t* count) override;
rdc_status_t rdc_device_get_all_cpu(uint32_t cpu_index_list[RDC_MAX_NUM_DEVICES],
uint32_t* count) override;
rdc_status_t rdc_device_get_attributes(uint32_t gpu_index,
rdc_device_attributes_t* p_rdc_attr) override;
rdc_status_t rdc_device_get_cpu_attributes(uint32_t cpu_index,
rdc_device_attributes_t* p_rdc_attr) override;
rdc_status_t rdc_device_get_component_version(rdc_component_t component,
rdc_component_version_t* p_rdc_compv) override;