[llvm] [Offload] Define additional device info properties (PR #152533)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 7 08:29:54 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-offload
Author: Rafal Bielski (rafbiels)
<details>
<summary>Changes</summary>
Add the following properties in Offload device info:
* VENDOR_ID
* NUM_COMPUTE_UNITS
* [SINGLE|DOUBLE|HALF]_FP_CONFIG
* PREFERRED_VECTOR_WIDTH_[CHAR|SHORT|INT|LONG|FLOAT|DOUBLE|HALF]
* 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
Introduce templated enumerators in Offload TableGen to reduce code duplication for the per-type definitions.
Use macros in unit test definitions to reduce code duplication.
---
Patch is 34.99 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/152533.diff
13 Files Affected:
- (modified) offload/liboffload/API/APIDefs.td (+16)
- (modified) offload/liboffload/API/Device.td (+32)
- (modified) offload/liboffload/src/OffloadImpl.cpp (+85-3)
- (modified) offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h (+6)
- (modified) offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa_ext_amd.h (+1)
- (modified) offload/plugins-nextgen/amdgpu/src/rtl.cpp (+22-3)
- (modified) offload/plugins-nextgen/cuda/src/rtl.cpp (+12-4)
- (modified) offload/tools/offload-tblgen/APIGen.cpp (+25-10)
- (modified) offload/tools/offload-tblgen/MiscGen.cpp (+22-5)
- (modified) offload/tools/offload-tblgen/PrintGen.cpp (+41-25)
- (modified) offload/tools/offload-tblgen/RecordTypes.hpp (+30-1)
- (modified) offload/unittests/OffloadAPI/device/olGetDeviceInfo.cpp (+64-6)
- (modified) offload/unittests/OffloadAPI/device/olGetDeviceInfoSize.cpp (+65-34)
``````````diff
diff --git a/offload/liboffload/API/APIDefs.td b/offload/liboffload/API/APIDefs.td
index 640932dcf8464..79f7242a35ecf 100644
--- a/offload/liboffload/API/APIDefs.td
+++ b/offload/liboffload/API/APIDefs.td
@@ -158,16 +158,32 @@ class Etor<string Name, string Desc> {
string tagged_type;
}
+class EtorTemplate<string Name, string Desc, list<string> TemplateValues> : Etor<Name, Desc> {
+ // Create Etor for every value in template_values by replacing the string
+ // "<TemplateEtor>" with the template value in the name and description
+ list<string> template_values = TemplateValues;
+}
+
class TaggedEtor<string Name, string Type, string Desc> : Etor<Name, Desc> {
let tagged_type = Type;
}
+class TaggedEtorTemplate<string Name, string Type, string Desc, list<string> TemplateValues> : TaggedEtor<Name, Type, Desc> {
+ // Create TaggedEtor for every value in template_values by replacing the
+ // string "<TemplateEtor>" with the template value in the name and description
+ list<string> template_values = TemplateValues;
+}
+
class Enum : APIObject {
// This refers to whether the enumerator descriptions specify a return
// type for functions where this enum may be used as an output type. If set,
// all Etor values must be TaggedEtor records
bit is_typed = 0;
+ // This refers to whether the enumerator is used to name bits of a bit field,
+ // where consecutive values are bit-shifted rather than incremented.
+ bit is_bit_field = 0;
+
list<Etor> etors = [];
}
diff --git a/offload/liboffload/API/Device.td b/offload/liboffload/API/Device.td
index 857c596124b27..062542364f08e 100644
--- a/offload/liboffload/API/Device.td
+++ b/offload/liboffload/API/Device.td
@@ -34,9 +34,41 @@ def DeviceInfo : Enum {
TaggedEtor<"DRIVER_VERSION", "char[]", "Driver version">,
TaggedEtor<"MAX_WORK_GROUP_SIZE", "uint32_t", "Maximum total work group size in work items">,
TaggedEtor<"MAX_WORK_GROUP_SIZE_PER_DIMENSION", "ol_dimensions_t", "Maximum work group size in each dimension">,
+ TaggedEtor<"VENDOR_ID", "uint32_t", "Device vendor ID">,
+ TaggedEtor<"NUM_COMPUTE_UNITS", "uint32_t", "Number of compute units">,
+ TaggedEtorTemplate<"<TemplateEtor>_FP_CONFIG", "ol_device_fp_capability_flags_t", "<TemplateEtor> precision floating point capability", ["Single","Half","Double"]>,
+ TaggedEtorTemplate<"PREFERRED_VECTOR_WIDTH_<TemplateEtor>", "uint32_t", "Preferred vector width for <TemplateEtor>", ["char","short","int","long","float","double","half"]>,
+ TaggedEtorTemplate<"NATIVE_VECTOR_WIDTH_<TemplateEtor>", "uint32_t", "Native vector width for <TemplateEtor>", ["char","short","int","long","float","double","half"]>,
+ TaggedEtor<"MAX_CLOCK_FREQUENCY", "uint32_t", "Max clock frequency in MHz">,
+ TaggedEtor<"MEMORY_CLOCK_RATE", "uint32_t", "Memory clock frequency in MHz">,
+ TaggedEtor<"ADDRESS_BITS", "uint32_t", "Number of bits used to represent an address in device memory">,
+ TaggedEtor<"MAX_MEM_ALLOC_SIZE", "uint64_t", "The maximum size of memory object allocation in bytes">,
+ TaggedEtor<"GLOBAL_MEM_SIZE", "uint64_t", "The size of global device memory in bytes">,
];
}
+def : Enum {
+ let name = "ol_device_fp_capability_flag_t";
+ let desc = "Device floating-point capability flags";
+ let is_bit_field = 1;
+ let etors =[
+ Etor<"CORRECTLY_ROUNDED_DIVIDE_SQRT", "Support correctly rounded divide and sqrt">,
+ Etor<"ROUND_TO_NEAREST", "Support round to nearest">,
+ Etor<"ROUND_TO_ZERO", "Support round to zero">,
+ Etor<"ROUND_TO_INF", "Support round to infinity">,
+ Etor<"INF_NAN", "Support INF to NAN">,
+ Etor<"DENORM", "Support denorm">,
+ Etor<"FMA", "Support fused multiply-add">,
+ Etor<"SOFT_FLOAT", "Basic floating point operations implemented in software">,
+ ];
+}
+
+def : Typedef {
+ let name = "ol_device_fp_capability_flags_t";
+ let desc = "Device floating-point capability flags";
+ let value = "uint32_t";
+}
+
def : FptrTypedef {
let name = "ol_device_iterate_cb_t";
let desc = "User-provided function to be used with `olIterateDevices`";
diff --git a/offload/liboffload/src/OffloadImpl.cpp b/offload/liboffload/src/OffloadImpl.cpp
index 272a12ab59a06..4ea587e29de4d 100644
--- a/offload/liboffload/src/OffloadImpl.cpp
+++ b/offload/liboffload/src/OffloadImpl.cpp
@@ -302,10 +302,57 @@ Error olGetDeviceInfoImplDetail(ol_device_handle_t Device,
};
// These are not implemented by the plugin interface
- if (PropName == OL_DEVICE_INFO_PLATFORM)
+ switch (PropName) {
+ case OL_DEVICE_INFO_PLATFORM:
return Info.write<void *>(Device->Platform);
- if (PropName == OL_DEVICE_INFO_TYPE)
+
+ case OL_DEVICE_INFO_TYPE:
return Info.write<ol_device_type_t>(OL_DEVICE_TYPE_GPU);
+
+ case OL_DEVICE_INFO_SINGLE_FP_CONFIG:
+ case OL_DEVICE_INFO_DOUBLE_FP_CONFIG: {
+ ol_device_fp_capability_flags_t flags{0};
+ flags |= OL_DEVICE_FP_CAPABILITY_FLAG_CORRECTLY_ROUNDED_DIVIDE_SQRT |
+ OL_DEVICE_FP_CAPABILITY_FLAG_ROUND_TO_NEAREST |
+ OL_DEVICE_FP_CAPABILITY_FLAG_ROUND_TO_ZERO |
+ OL_DEVICE_FP_CAPABILITY_FLAG_ROUND_TO_INF |
+ OL_DEVICE_FP_CAPABILITY_FLAG_INF_NAN |
+ OL_DEVICE_FP_CAPABILITY_FLAG_DENORM |
+ OL_DEVICE_FP_CAPABILITY_FLAG_FMA;
+ return Info.write(flags);
+ }
+
+ case OL_DEVICE_INFO_HALF_FP_CONFIG:
+ return Info.write<ol_device_fp_capability_flags_t>(0);
+
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_CHAR:
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_SHORT:
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_INT:
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_LONG:
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_FLOAT:
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_DOUBLE:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_CHAR:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_SHORT:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_INT:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_LONG:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_FLOAT:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_DOUBLE:
+ return Info.write<uint32_t>(1);
+
+ case OL_DEVICE_INFO_PREFERRED_VECTOR_WIDTH_HALF:
+ case OL_DEVICE_INFO_NATIVE_VECTOR_WIDTH_HALF:
+ return Info.write<uint32_t>(0);
+
+ // None of the existing plugins specify a limit on a single allocation,
+ // so return the global memory size instead
+ case OL_DEVICE_INFO_MAX_MEM_ALLOC_SIZE:
+ PropName = OL_DEVICE_INFO_GLOBAL_MEM_SIZE;
+ break;
+
+ default:
+ break;
+ }
+
if (PropName >= OL_DEVICE_INFO_LAST)
return createOffloadError(ErrorCode::INVALID_ENUMERATION,
"getDeviceInfo enum '%i' is invalid", PropName);
@@ -316,6 +363,7 @@ Error olGetDeviceInfoImplDetail(ol_device_handle_t Device,
"plugin did not provide a response for this information");
auto Entry = *EntryOpt;
+ // Retrieve properties from the plugin interface
switch (PropName) {
case OL_DEVICE_INFO_NAME:
case OL_DEVICE_INFO_VENDOR:
@@ -327,7 +375,18 @@ Error olGetDeviceInfoImplDetail(ol_device_handle_t Device,
return Info.writeString(std::get<std::string>(Entry->Value).c_str());
}
- case OL_DEVICE_INFO_MAX_WORK_GROUP_SIZE: {
+ case OL_DEVICE_INFO_GLOBAL_MEM_SIZE: {
+ // Uint64 values
+ if (!std::holds_alternative<uint64_t>(Entry->Value))
+ return makeError(ErrorCode::BACKEND_FAILURE,
+ "plugin returned incorrect type");
+ return Info.write(std::get<uint64_t>(Entry->Value));
+ }
+
+ case OL_DEVICE_INFO_MAX_WORK_GROUP_SIZE:
+ case OL_DEVICE_INFO_VENDOR_ID:
+ case OL_DEVICE_INFO_NUM_COMPUTE_UNITS:
+ case OL_DEVICE_INFO_ADDRESS_BITS: {
// Uint32 values
if (!std::holds_alternative<uint64_t>(Entry->Value))
return makeError(ErrorCode::BACKEND_FAILURE,
@@ -339,6 +398,29 @@ Error olGetDeviceInfoImplDetail(ol_device_handle_t Device,
return Info.write(static_cast<uint32_t>(Value));
}
+ case OL_DEVICE_INFO_MAX_CLOCK_FREQUENCY:
+ case OL_DEVICE_INFO_MEMORY_CLOCK_RATE: {
+ // Frequency might require unit conversion to MHz
+ if (!std::holds_alternative<uint64_t>(Entry->Value))
+ return makeError(ErrorCode::BACKEND_FAILURE,
+ "plugin returned incorrect type");
+ auto Value = std::get<uint64_t>(Entry->Value);
+ StringRef Units = Entry->Units;
+ if (!Units.empty() && Units != "MHz") {
+ // Conversion required
+ if (Units == "Hz")
+ Value /= 1000000;
+ else if (Units == "kHz")
+ Value /= 1000;
+ else if (Units == "GHz")
+ Value *= 1000;
+ }
+ if (Value > std::numeric_limits<uint32_t>::max())
+ return makeError(ErrorCode::BACKEND_FAILURE,
+ "plugin returned out of range device info");
+ return Info.write(static_cast<uint32_t>(Value));
+ }
+
case OL_DEVICE_INFO_MAX_WORK_GROUP_SIZE_PER_DIMENSION: {
// {x, y, z} triples
ol_dimensions_t Out{0, 0, 0};
diff --git a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
index 61f680bab3a07..ad135f72fff12 100644
--- a/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
+++ b/offload/plugins-nextgen/amdgpu/dynamic_hsa/hsa.h
@@ -70,10 +70,16 @@ typedef enum {
HSA_ISA_INFO_NAME = 1
} 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 3117763e35896..29cfe78082dbb 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 852c0e99b2266..20d8994f97a39 100644
--- a/offload/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -2643,6 +2643,15 @@ 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) {
@@ -2693,11 +2702,17 @@ 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)
@@ -2779,7 +2794,11 @@ 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 7649fd9285bb5..18a006f0b3992 100644
--- a/offload/plugins-nextgen/cuda/src/rtl.cpp
+++ b/offload/plugins-nextgen/cuda/src/rtl.cpp
@@ -951,13 +951,20 @@ 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)
@@ -1018,7 +1025,7 @@ 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, "kHz", DeviceInfo::MAX_CLOCK_FREQUENCY);
Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT, TmpInt);
if (Res == CUDA_SUCCESS)
@@ -1055,7 +1062,8 @@ 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, "kHz",
+ DeviceInfo::MEMORY_CLOCK_RATE);
Res = getDeviceAttrRaw(CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH, TmpInt);
if (Res == CUDA_SUCCESS)
diff --git a/offload/tools/offload-tblgen/APIGen.cpp b/offload/tools/offload-tblgen/APIGen.cpp
index 8c61d1f12de7a..ea62fa3cd9e91 100644
--- a/offload/tools/offload-tblgen/APIGen.cpp
+++ b/offload/tools/offload-tblgen/APIGen.cpp
@@ -131,17 +131,32 @@ static void ProcessEnum(const EnumRec &Enum, raw_ostream &OS) {
OS << formatv("/// @brief {0}\n", Enum.getDesc());
OS << formatv("typedef enum {0} {{\n", Enum.getName());
- uint32_t EtorVal = 0;
+ uint32_t EtorVal = Enum.isBitField();
for (const auto &EnumVal : Enum.getValues()) {
- if (Enum.isTyped()) {
- OS << MakeComment(
- formatv("[{0}] {1}", EnumVal.getTaggedType(), EnumVal.getDesc())
- .str());
- } else {
- OS << MakeComment(EnumVal.getDesc());
- }
- OS << formatv(TAB_1 "{0}_{1} = {2},\n", Enum.getEnumValNamePrefix(),
- EnumVal.getName(), EtorVal++);
+ size_t NumTemplateValues{EnumVal.getTemplateValues().size()};
+ size_t TemplateIndex{
+ NumTemplateValues > 0 ? 0 : std::numeric_limits<size_t>::max()};
+ do {
+ std::string Name{TemplateIndex < std::numeric_limits<size_t>::max()
+ ? EnumVal.getTemplateName(TemplateIndex)
+ : EnumVal.getName()};
+ std::string Desc{TemplateIndex < std::numeric_limits<size_t>::max()
+ ? EnumVal.getTemplateDesc(TemplateIndex)
+ : EnumVal.getDesc()};
+ if (Enum.isTyped()) {
+ OS << MakeComment(
+ formatv("[{0}] {1}", EnumVal.getTaggedType(), Desc).str());
+ } else {
+ OS << MakeComment(Desc);
+ }
+ OS << formatv(TAB_1 "{0}_{1} = {2},\n", Enum.getEnumValNamePrefix(), Name,
+ EtorVal);
+ if (Enum.isBitField()) {
+ EtorVal <<= 1u;
+ } else {
+ ++EtorVal;
+ }
+ } while (++TemplateIndex < NumTemplateValues);
}
// Add last_element/force uint32 val
diff --git a/offload/tools/offload-tblgen/MiscGen.cpp b/offload/tools/offload-tblgen/MiscGen.cpp
index b90e5cfdec8b2..afd76ba34ae06 100644
--- a/offload/tools/offload-tblgen/MiscGen.cpp
+++ b/offload/tools/offload-tblgen/MiscGen.cpp
@@ -107,10 +107,27 @@ void EmitOffloadInfo(const RecordKeeper &Records, raw_ostream &OS) {
)";
- auto ErrorCodeEnum = EnumRec{Records.getDef("DeviceInfo")};
- uint32_t EtorVal = 0;
- for (const auto &EnumVal : ErrorCodeEnum.getValues()) {
- OS << formatv(TAB_1 "OFFLOAD_DEVINFO({0}, \"{1}\", {2})\n",
- EnumVal.getName(), EnumVal.getDesc(), EtorVal++);
+ auto Enum = EnumRec{Records.getDef("DeviceInfo")};
+
+ uint32_t EtorVal = Enum.isBitField();
+ for (const auto &EnumVal : Enum.getValues()) {
+ size_t NumTemplateValues{EnumVal.getTemplateValues().size()};
+ size_t TemplateIndex{
+ NumTemplateValues > 0 ? 0 : std::numeric_limits<size_t>::max()};
+ do {
+ std::string Name{TemplateIndex < std::numeric_limits<size_t>::max()
+ ? EnumVal.getTemplateName(TemplateIndex)
+ : EnumVal.getName()};
+ std::string Desc{TemplateIndex < std::numeric_limits<size_t>::max()
+ ? EnumVal.getTemplateDesc(TemplateIndex)
+ : EnumVal.getDesc()};
+ OS << formatv(TAB_1 "OFFLOAD_DEVINFO({0}, \"{1}\", {2})\n", Name, Desc,
+ EtorVal);
+ if (Enum.isBitField()) {
+ EtorVal <<= 1u;
+ } else {
+ ++EtorVal;
+ }
+ } while (++TemplateIndex < NumTemplateValues);
}
}
diff --git a/offload/tools/offload-tblgen/PrintGen.cpp b/offload/tools/offload-tblgen/PrintGen.cpp
index 89d7c820426cf..1bfa388ada436 100644
--- a/offload/tools/offload-tblgen/PrintGen.cpp
+++ b/offload/tools/offload-tblgen/PrintGen.cpp
@@ -40,10 +40,18 @@ static void ProcessEnum(const EnumRec &Enum, raw_ostream &OS) {
Enum.getName());
for (const auto &Val : Enum.getValues()) {
- auto Name = Enum.getEnumValNamePrefix() + "_" + Val.getName();
- OS << formatv(TAB_1 "case {0}:\n", Name);
- OS << formatv(TAB_2 "os << \"{0}\";\n", Name);
- OS << formatv(TAB_2 "break;\n");
+ size_t NumTemplateValues{Val.getTemplateValues().size()};
+ size_t TemplateIndex{
+ NumTemplateValues > 0 ? 0 : std::numeric_limits<size_t>::max()};
+ do {
+ auto Name = Enum.getEnumValNamePrefix() + "_" +
+ (TemplateIndex < std::numeric_limits<size_t>::max()
+ ? Val.getTemplateName(TemplateIndex)
+ : Val.getName());
+ OS << formatv(TAB_1 "case {0}:\n", Name);
+ OS << formatv(TAB_2 "os << \"{0}\";\n", Name);
+ OS << formatv(TAB_2 "break;\n");
+ } while (++TemplateIndex < NumTemplateValues);
}
OS << TAB_1 "default:\n" TAB_2 "os << \"unknown enumerator\";\n" TAB_2
@@ -67,29 +75,37 @@ inline void printTagged(llvm::raw_ostream &os, const void *ptr, {0} value, size_
Enum.getName());
for (const auto &Val : Enum.getValues()) {
- auto Name = Enum.getEnumValNamePrefix() + "_" + Val.getName();
- auto Type = Val.getTaggedType();
- OS << formatv(TAB_1 "case {0}: {{\n", Name);
- // Special case for strings
- if (Type == "char[]") {
- OS << formatv(TAB_2 "printPtr(os, (const char*) ptr);\n");
- } else {
- if (Type == "void *")
- OS << formatv(TAB_2 "void * const * const tptr = (void * "
- "const * const)ptr;\n");
- else
- OS << formatv(
- TAB_2 "const {0} * const tptr = (const {0} * co...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/152533
More information about the llvm-commits
mailing list