[Offload] Define additional device info properties (#152533)

Add the following properties in Offload device info:
* VENDOR_ID
* NUM_COMPUTE_UNITS
* [SINGLE|DOUBLE|HALF]_FP_CONFIG
* NATIVE_VECTOR_WIDTH_[CHAR|SHORT|INT|LONG|FLOAT|DOUBLE|HALF]
* MAX_CLOCK_FREQUENCY
* MEMORY_CLOCK_RATE
* ADDRESS_BITS
* MAX_MEM_ALLOC_SIZE
* GLOBAL_MEM_SIZE

Add a bitfield option to enumerators, allowing the values to be
bit-shifted instead of incremented. Generate the per-type enums using
`foreach` to reduce code duplication.

Use macros in unit test definitions to reduce code duplication.

4 files changed, 42 insertions, 7 deletions

diff --git a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
index 61f680bab3a0..ad135f72fff1 100644
--- a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
+++ b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
@@ -71,9 +71,15 @@ typedef enum {
 } hsa_isa_info_t;
 
 typedef enum {
+  HSA_MACHINE_MODEL_SMALL = 0,
+  HSA_MACHINE_MODEL_LARGE = 1
+} hsa_machine_model_t;
+
+typedef enum {
   HSA_AGENT_INFO_NAME = 0,
   HSA_AGENT_INFO_VENDOR_NAME = 1,
   HSA_AGENT_INFO_FEATURE = 2,
+  HSA_AGENT_INFO_MACHINE_MODEL = 3,
   HSA_AGENT_INFO_PROFILE = 4,
   HSA_AGENT_INFO_WAVEFRONT_SIZE = 6,
   HSA_AGENT_INFO_WORKGROUP_MAX_DIM = 7,
diff --git a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h
index 3117763e3589..29cfe78082db 100644
--- a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h
+++ b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h
@@ -67,6 +67,7 @@ typedef enum hsa_amd_agent_info_s {
   HSA_AMD_AGENT_INFO_CACHELINE_SIZE = 0xA001,
   HSA_AMD_AGENT_INFO_COMPUTE_UNIT_COUNT = 0xA002,
   HSA_AMD_AGENT_INFO_MAX_CLOCK_FREQUENCY = 0xA003,
+  HSA_AMD_AGENT_INFO_MEMORY_MAX_FREQUENCY = 0xA008,
   HSA_AMD_AGENT_INFO_PRODUCT_NAME = 0xA009,
   HSA_AMD_AGENT_INFO_MAX_WAVES_PER_CU = 0xA00A,
   HSA_AMD_AGENT_INFO_NUM_SIMDS_PER_CU = 0xA00B,
diff --git a/offload/plugins-nextgen/amdgpu/src/rtl.cpp b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
index 83280fe0a49c..3143fe408563 100644
--- a/offload/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -2697,6 +2697,15 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
     if (Status == HSA_STATUS_SUCCESS)
       Info.add("Vendor Name", TmpChar, "", DeviceInfo::VENDOR);
 
+    Info.add("Vendor ID", uint64_t{4130}, "", DeviceInfo::VENDOR_ID);
+
+    hsa_machine_model_t MachineModel;
+    Status = getDeviceAttrRaw(HSA_AGENT_INFO_MACHINE_MODEL, MachineModel);
+    if (Status == HSA_STATUS_SUCCESS)
+      Info.add("Memory Address Size",
+               uint64_t{MachineModel == HSA_MACHINE_MODEL_SMALL ? 32u : 64u},
+               "bits", DeviceInfo::ADDRESS_BITS);
+
     hsa_device_type_t DevType;
     Status = getDeviceAttrRaw(HSA_AGENT_INFO_DEVICE, DevType);
     if (Status == HSA_STATUS_SUCCESS) {
@@ -2747,11 +2756,17 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
 
     Status = getDeviceAttrRaw(HSA_AMD_AGENT_INFO_MAX_CLOCK_FREQUENCY, TmpUInt);
     if (Status == HSA_STATUS_SUCCESS)
-      Info.add("Max Clock Freq", TmpUInt, "MHz");
+      Info.add("Max Clock Freq", TmpUInt, "MHz",
+               DeviceInfo::MAX_CLOCK_FREQUENCY);
+
+    Status = getDeviceAttrRaw(HSA_AMD_AGENT_INFO_MEMORY_MAX_FREQUENCY, TmpUInt);
+    if (Status == HSA_STATUS_SUCCESS)
+      Info.add("Max Memory Clock Freq", TmpUInt, "MHz",
+               DeviceInfo::MEMORY_CLOCK_RATE);
 
     Status = getDeviceAttrRaw(HSA_AMD_AGENT_INFO_COMPUTE_UNIT_COUNT, TmpUInt);
     if (Status == HSA_STATUS_SUCCESS)
-      Info.add("Compute Units", TmpUInt);
+      Info.add("Compute Units", TmpUInt, "", DeviceInfo::NUM_COMPUTE_UNITS);
 
     Status = getDeviceAttrRaw(HSA_AMD_AGENT_INFO_NUM_SIMDS_PER_CU, TmpUInt);
     if (Status == HSA_STATUS_SUCCESS)
@@ -2833,7 +2848,11 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
 
       Status = Pool->getAttrRaw(HSA_AMD_MEMORY_POOL_INFO_SIZE, TmpSt);
       if (Status == HSA_STATUS_SUCCESS)
-        PoolNode.add("Size", TmpSt, "bytes");
+        PoolNode.add(
+            "Size", TmpSt, "bytes",
+            (Pool->isGlobal() && Pool->isCoarseGrained())
+                ? std::optional<DeviceInfo>{DeviceInfo::GLOBAL_MEM_SIZE}
+                : std::nullopt);
 
       Status = Pool->getAttrRaw(HSA_AMD_MEMORY_POOL_INFO_RUNTIME_ALLOC_ALLOWED,
                                 TmpBool);
diff --git a/offload/plugins-nextgen/cuda/src/rtl.cpp b/offload/plugins-nextgen/cuda/src/rtl.cpp
index a99357a3adea..0a3720532e4e 100644
--- a/offload/plugins-nextgen/cuda/src/rtl.cpp
+++ b/offload/plugins-nextgen/cuda/src/rtl.cpp
@@ -979,13 +979,20 @@ struct CUDADeviceTy : public GenericDeviceTy {
 
     Info.add("Vendor Name", "NVIDIA", "", DeviceInfo::VENDOR);
 
+    Info.add("Vendor ID", uint64_t{4318}, "", DeviceInfo::VENDOR_ID);
+
+    Info.add("Memory Address Size", std::numeric_limits<CUdeviceptr>::digits,
+             "bits", DeviceInfo::ADDRESS_BITS);
+
     Res = cuDeviceTotalMem(&TmpSt, Device);
     if (Res == CUDA_SUCCESS)
-      Info.add("Global Memory Size", TmpSt, "bytes");
+      Info.add("Global Memory Size", TmpSt, "bytes",
+               DeviceInfo::GLOBAL_MEM_SIZE);
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT, TmpInt);
     if (Res == CUDA_SUCCESS)
-      Info.add("Number of Multiprocessors", TmpInt);
+      Info.add("Number of Multiprocessors", TmpInt, "",
+               DeviceInfo::NUM_COMPUTE_UNITS);
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_GPU_OVERLAP, TmpInt);
     if (Res == CUDA_SUCCESS)
@@ -1046,7 +1053,8 @@ struct CUDADeviceTy : public GenericDeviceTy {
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_CLOCK_RATE, TmpInt);
     if (Res == CUDA_SUCCESS)
-      Info.add("Clock Rate", TmpInt, "kHz");
+      Info.add("Clock Rate", TmpInt / 1000, "MHz",
+               DeviceInfo::MAX_CLOCK_FREQUENCY);
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT, TmpInt);
     if (Res == CUDA_SUCCESS)
@@ -1083,7 +1091,8 @@ struct CUDADeviceTy : public GenericDeviceTy {
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE, TmpInt);
     if (Res == CUDA_SUCCESS)
-      Info.add("Memory Clock Rate", TmpInt, "kHz");
+      Info.add("Memory Clock Rate", TmpInt / 1000, "MHz",
+               DeviceInfo::MEMORY_CLOCK_RATE);
 
     Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH, TmpInt);
     if (Res == CUDA_SUCCESS)