AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SWDEV-427855 - hipamd change for profiler and TF fix

Browse Source 
This reverts commit 57cb840058.

Change-Id: Id69e47a1afd336ae1edb9c8e173be27e7b9dcc8d
This commit is contained in:
Rahul Garg
2023-11-29 15:50:10 -05:00
parent 3c6505c2d5
commit afc28b091e
10 changed files with 539 additions and 381 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hipamd/src/hip_device.cpp
+19 -92
View File
@@ -19,6 +19,7 @@
THE SOFTWARE. */
#include <hip/hip_runtime.h>
#include <hip/hip_deprecated.h>
#include "hip_internal.hpp"
#include "hip_mempool_impl.hpp"
@@ -273,7 +274,7 @@ hipError_t hipDeviceGetUuid(hipUUID* uuid, hipDevice_t device) {
HIP_RETURN(hipSuccess);
}
hipError_t ihipGetDeviceProperties(hipDeviceProp_tR0600* props, hipDevice_t device) {
hipError_t ihipGetDeviceProperties(hipDeviceProp_tR0600* props, int device) {
if (props == nullptr) {
return hipErrorInvalidValue;
}
@@ -457,107 +458,27 @@ hipError_t ihipGetDeviceProperties(hipDeviceProp_tR0600* props, hipDevice_t devi
return hipSuccess;
}
hipError_t hipGetDevicePropertiesR0600(hipDeviceProp_tR0600* props, hipDevice_t device) {
HIP_INIT_API(hipGetDevicePropertiesR0600, props, device);
hipError_t hipGetDevicePropertiesR0600(hipDeviceProp_tR0600* prop, int device) {
HIP_INIT_API(hipGetDevicePropertiesR0600, prop, device);
HIP_RETURN(ihipGetDeviceProperties(props, device));
HIP_RETURN(ihipGetDeviceProperties(prop, device));
}
extern "C" typedef struct hipDeviceProp_t {
char name[256]; ///< Device name.
size_t totalGlobalMem; ///< Size of global memory region (in bytes).
size_t sharedMemPerBlock; ///< Size of shared memory region (in bytes).
int regsPerBlock; ///< Registers per block.
int warpSize; ///< Warp size.
int maxThreadsPerBlock; ///< Max work items per work group or workgroup max size.
int maxThreadsDim[3]; ///< Max number of threads in each dimension (XYZ) of a block.
int maxGridSize[3]; ///< Max grid dimensions (XYZ).
int clockRate; ///< Max clock frequency of the multiProcessors in khz.
int memoryClockRate; ///< Max global memory clock frequency in khz.
int memoryBusWidth; ///< Global memory bus width in bits.
size_t totalConstMem; ///< Size of shared memory region (in bytes).
int major; ///< Major compute capability. On HCC, this is an approximation and features may
///< differ from CUDA CC. See the arch feature flags for portable ways to query
///< feature caps.
int minor; ///< Minor compute capability. On HCC, this is an approximation and features may
///< differ from CUDA CC. See the arch feature flags for portable ways to query
///< feature caps.
int multiProcessorCount; ///< Number of multi-processors (compute units).
int l2CacheSize; ///< L2 cache size.
int maxThreadsPerMultiProcessor; ///< Maximum resident threads per multi-processor.
int computeMode; ///< Compute mode.
int clockInstructionRate; ///< Frequency in khz of the timer used by the device-side "clock*"
///< instructions. New for HIP.
hipDeviceArch_t arch; ///< Architectural feature flags. New for HIP.
int concurrentKernels; ///< Device can possibly execute multiple kernels concurrently.
int pciDomainID; ///< PCI Domain ID
int pciBusID; ///< PCI Bus ID.
int pciDeviceID; ///< PCI Device ID.
size_t maxSharedMemoryPerMultiProcessor; ///< Maximum Shared Memory Per Multiprocessor.
int isMultiGpuBoard; ///< 1 if device is on a multi-GPU board, 0 if not.
int canMapHostMemory; ///< Check whether HIP can map host memory
int gcnArch; ///< DEPRECATED: use gcnArchName instead
char gcnArchName[256]; ///< AMD GCN Arch Name.
int integrated; ///< APU vs dGPU
int cooperativeLaunch; ///< HIP device supports cooperative launch
int cooperativeMultiDeviceLaunch; ///< HIP device supports cooperative launch on multiple
///< devices
int maxTexture1DLinear; ///< Maximum size for 1D textures bound to linear memory
int maxTexture1D; ///< Maximum number of elements in 1D images
int maxTexture2D[2]; ///< Maximum dimensions (width, height) of 2D images, in image elements
int maxTexture3D[3]; ///< Maximum dimensions (width, height, depth) of 3D images, in image
///< elements
unsigned int* hdpMemFlushCntl; ///< Addres of HDP_MEM_COHERENCY_FLUSH_CNTL register
unsigned int* hdpRegFlushCntl; ///< Addres of HDP_REG_COHERENCY_FLUSH_CNTL register
size_t memPitch; ///< Maximum pitch in bytes allowed by memory copies
size_t textureAlignment; ///< Alignment requirement for textures
size_t texturePitchAlignment; ///< Pitch alignment requirement for texture references bound to
///< pitched memory
int kernelExecTimeoutEnabled; ///< Run time limit for kernels executed on the device
int ECCEnabled; ///< Device has ECC support enabled
int tccDriver; ///< 1:If device is Tesla device using TCC driver, else 0
int cooperativeMultiDeviceUnmatchedFunc; ///< HIP device supports cooperative launch on
///< multiple
/// devices with unmatched functions
int cooperativeMultiDeviceUnmatchedGridDim; ///< HIP device supports cooperative launch on
///< multiple
/// devices with unmatched grid dimensions
int cooperativeMultiDeviceUnmatchedBlockDim; ///< HIP device supports cooperative launch on
///< multiple
/// devices with unmatched block dimensions
int cooperativeMultiDeviceUnmatchedSharedMem; ///< HIP device supports cooperative launch on
///< multiple
/// devices with unmatched shared memories
int isLargeBar; ///< 1: if it is a large PCI bar device, else 0
int asicRevision; ///< Revision of the GPU in this device
int managedMemory; ///< Device supports allocating managed memory on this system
int directManagedMemAccessFromHost; ///< Host can directly access managed memory on the device
///< without migration
int concurrentManagedAccess; ///< Device can coherently access managed memory concurrently with
///< the CPU
int pageableMemoryAccess; ///< Device supports coherently accessing pageable memory
///< without calling hipHostRegister on it
int pageableMemoryAccessUsesHostPageTables; ///< Device accesses pageable memory via the host's
///< page tables
} hipDeviceProp_t;
hipError_t hipGetDevicePropertiesR0000(hipDeviceProp_tR0000* prop, int device) {
HIP_INIT_API(hipGetDevicePropertiesR0000, prop, device);
extern "C" hipError_t hipGetDeviceProperties(hipDeviceProp_t* props, hipDevice_t device) {
// Removing this API from tracing.
// This API is now in backwards compatibility mode and is not callable from newly compiled apps.
HIP_INIT_VOID();
if (props == nullptr) {
return hipErrorInvalidValue;
if (prop == nullptr) {
HIP_RETURN(hipErrorInvalidValue);
}
if (unsigned(device) >= g_devices.size()) {
return hipErrorInvalidDevice;
HIP_RETURN(hipErrorInvalidDevice);
}
auto* deviceHandle = g_devices[device]->devices()[0];
constexpr auto int32_max = static_cast<uint64_t>(std::numeric_limits<int32_t>::max());
constexpr auto uint16_max = static_cast<uint64_t>(std::numeric_limits<uint16_t>::max()) + 1;
hipDeviceProp_t deviceProps = {0};
hipDeviceProp_tR0000 deviceProps = {0};
const auto& info = deviceHandle->info();
const auto& isa = deviceHandle->isa();
@@ -644,7 +565,13 @@ extern "C" hipError_t hipGetDeviceProperties(hipDeviceProp_t* props, hipDevice_t
deviceProps.pageableMemoryAccess = info.hmmCpuMemoryAccessible_;
deviceProps.pageableMemoryAccessUsesHostPageTables = info.hostUnifiedMemory_;
*props = deviceProps;
return hipSuccess;
*prop = deviceProps;
HIP_RETURN(hipSuccess);
}
extern "C" hipError_t hipGetDeviceProperties(hipDeviceProp_tR0000* props, hipDevice_t device);
hipError_t hipGetDeviceProperties(hipDeviceProp_tR0000* props, hipDevice_t device) {
return hipGetDevicePropertiesR0000(props, device);
}
} // namespace hip