mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 17:26:00 +00:00
* Format * Format * Format * Remove const * Use the right template * Format * Format * add row/col instances * Add missing file * fixed * fixing block to etile error * Format * Updates * Format * fixed rrr layout * generating a sample JSON file: currently contains includes, prologue/epilogue and instances * version where the json is passed into the instances to generate a key * updated run function to just launch kernel * updated run function: only contains kernel object, json file is updated but still needs to be cleaned up, added front-end API to parse JSON into character buffer * adding in testing files * cleaned up comments, still need to work on including header files * removed unneeded files * removed/commented out JSON implementation * added fusion(prologue/epilogue) into instance generation * working on instance selection * added instance selection, need to fix instance validation * removed block2etile map validity check for testing purposes * test running: failing due to incorrect files/input * all grid descs/ptrs completed, but device file not found * Update test and embed modules * Restore older version * added convolution operation, written test, debugging generated code for compilation * attempting to include CK in host directory: _Float16 error * CK header file issues * slight fix * don't crash when hip can't report total memory * dump generated code to a file * changing sizes * creating tensor descriptors using CK methods: set up grid desc manually, also trying to set up an argument pointer - this needs to be fixed * some fixes to call the device code * separating test files for conv and gemm * completed arg ptr, now have linking errors * clang format fix * resolved linker issues in conv test * remove dependency on libutility from ck * resolved num dim error * properly passing arg ptr, errors with passing typenames: redefinition/redeclaration * undo the commenting of device function * hand created kernel code to find rtc issues * dump the full src to file * resolved redeclaration errors, cleaned up errors for Amber's kernel code * debugging purposes: redeclaration error * config files * resolved errors for NumTensor and redeclaration, formatted version.h * resolved most errors in manually added kernel and my own. error with calling kernel object: overloaded function type * WIP: close to getting kernel compiled * WIP: fixing rtc errors * fixed sequence errors, formatting, still one error with run fcn * yay: kernel compiles and runs * updated templated/generated version to run and compile * minor fixes * working generated example, resolved memory access error due to padding * adding in reference kernel, validation failing against reference * debugging: printing kernel argsz * reduced error in results * debugged reference kernel and output errors, added to generated version, currently debugging prologue function issues * working validation (using reference convolution) with prologue function for both hard-coded and generated version * WIP: create an alt version that creates Argument on the device * wip: added new duplicate files, fixed fusion templating errors from working example, setting up kernel arguments * wip: making necessary methods device code * added grid descs, working on grid pointers, errors with stl numerics * wip: updating kernel args - issue, replacing some std functions * replaced std::accumulate call with temp hardcoded version * wip: args causing memory issue * Construct Argument object inside the kernel and use it to call convolution device function. Code runs and verification passes * adding object file dump * temporary hardcoding of grid size, can remove device op inst + arg ptr * minor fix for grid size * added modified example where arg ptr is created on the device for generated version as well * removed device op instance and arg ptr from modified examples * moving device op file for testing purposes and to properly build CK * commenting out print-outs * adjust compiler args to produce a valid ELF file * temporary removal of validation * reverting compiler args back for working example * retrieve necessary arguments from generated template parameters in correct format * calculating grid size on host-side, still need to clean up process, pass parameters to host functions properly * scaled up factory functions/wrapper structs to implement host-side launch parameter calculations using CK host side functions - in hard-coded example * temporary change to generate ELF format binary object file * removed unecessary code, added comments * formatting fix * cleaned up code, added new tests, restructured library: move helper into CK * refactored launch parameter calculation to be more concise * renamed files and variables for more clarity/uniformity * more code cleaning, removed debug statements * moved majority of my files into codegen directory, running properly * updated Embed.cmake(string_view) in codegen directory * updated host directory to match Embed.cmake as well * added old tests in * updated instance generation methods to be more concise * removed layout from launch parameter calculation * working test * fixed issue with verification, all instances working * updated verification in other tests * removed duplicate matrix padder file, removed code dumps * removed old hard-coded tests * removed old host directory, all files in codegen directory now * fixed copyright in files * commenting out validation * renamed files * made changes for review: fixed copyright, renamed files for clarity, removed comments, refactored code * updated headers * removing duplicate file for fwd conv to gemm, merging with original file * fix building codegen with clang++ directly * resolving build error from conv_fwd_to_gemm * fix for previous error * renaming tests * created common test file * cleaned up code, added comments * renamed device op * fixed typos in comments * removed extra space * code cleanup: resolving Amber's comments * removed wrapper struct for matrix padder, fixed template * cleaned up if statements for better readability --------- Co-authored-by: Paul <pfultz2@yahoo.com> Co-authored-by: Jing Zhang <jizha@amd.com> Co-authored-by: M. Amber Hassaan <amber_474@yahoo.com> Co-authored-by: illsilin <Illia.Silin@amd.com> Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
107 lines
3.0 KiB
C++
107 lines
3.0 KiB
C++
#include <rtc/hip.hpp>
|
|
#include <rtc/manage_ptr.hpp>
|
|
#include <stdexcept>
|
|
#include <cassert>
|
|
#include <iostream>
|
|
|
|
namespace rtc {
|
|
|
|
using hip_ptr = RTC_MANAGE_PTR(void, hipFree);
|
|
|
|
std::string hip_error(int error) { return hipGetErrorString(static_cast<hipError_t>(error)); }
|
|
|
|
int get_device_id()
|
|
{
|
|
int device;
|
|
auto status = hipGetDevice(&device);
|
|
if(status != hipSuccess)
|
|
throw std::runtime_error("No device");
|
|
return device;
|
|
}
|
|
|
|
std::string get_device_name()
|
|
{
|
|
hipDeviceProp_t props{};
|
|
auto status = hipGetDeviceProperties(&props, get_device_id());
|
|
if(status != hipSuccess)
|
|
throw std::runtime_error("Failed to get device properties");
|
|
return props.gcnArchName;
|
|
}
|
|
|
|
bool is_device_ptr(const void* ptr)
|
|
{
|
|
hipPointerAttribute_t attr;
|
|
auto status = hipPointerGetAttributes(&attr, ptr);
|
|
if(status != hipSuccess)
|
|
return false;
|
|
return attr.type == hipMemoryTypeDevice;
|
|
}
|
|
|
|
void gpu_sync()
|
|
{
|
|
auto status = hipDeviceSynchronize();
|
|
if(status != hipSuccess)
|
|
throw std::runtime_error("hip device synchronization failed: " + hip_error(status));
|
|
}
|
|
|
|
std::size_t get_available_gpu_memory()
|
|
{
|
|
size_t free;
|
|
size_t total;
|
|
auto status = hipMemGetInfo(&free, &total);
|
|
if(status != hipSuccess)
|
|
{
|
|
std::cerr << "Failed getting available memory: " + hip_error(status) << std::endl;
|
|
return (8ull * 1024ull * 1024ull * 1024ull);
|
|
}
|
|
return free;
|
|
}
|
|
|
|
std::shared_ptr<void> allocate_gpu(std::size_t sz, bool host)
|
|
{
|
|
if(sz > get_available_gpu_memory())
|
|
throw std::runtime_error("Memory not available to allocate buffer: " + std::to_string(sz));
|
|
void* alloc_ptr = nullptr;
|
|
auto status = host ? hipHostMalloc(&alloc_ptr, sz) : hipMalloc(&alloc_ptr, sz);
|
|
if(status != hipSuccess)
|
|
{
|
|
if(host)
|
|
throw std::runtime_error("Gpu allocation failed: " + hip_error(status));
|
|
else
|
|
return allocate_gpu(sz, true);
|
|
}
|
|
assert(alloc_ptr != nullptr);
|
|
std::shared_ptr<void> result = share(hip_ptr{alloc_ptr});
|
|
return result;
|
|
}
|
|
|
|
std::shared_ptr<void> write_to_gpu(const void* x, std::size_t sz, bool host)
|
|
{
|
|
gpu_sync();
|
|
auto result = allocate_gpu(sz, host);
|
|
assert(is_device_ptr(result.get()));
|
|
assert(not is_device_ptr(x));
|
|
auto status = hipMemcpy(result.get(), x, sz, hipMemcpyHostToDevice);
|
|
if(status != hipSuccess)
|
|
throw std::runtime_error("Copy to gpu failed: " + hip_error(status));
|
|
return result;
|
|
}
|
|
|
|
std::shared_ptr<void> read_from_gpu(const void* x, std::size_t sz)
|
|
{
|
|
gpu_sync();
|
|
std::shared_ptr<char> result(new char[sz]);
|
|
assert(not is_device_ptr(result.get()));
|
|
if(not is_device_ptr(x))
|
|
{
|
|
throw std::runtime_error(
|
|
"read_from_gpu() requires Src buffer to be on the GPU, Copy from gpu failed\n");
|
|
}
|
|
auto status = hipMemcpy(result.get(), x, sz, hipMemcpyDeviceToHost);
|
|
if(status != hipSuccess)
|
|
throw std::runtime_error("Copy from gpu failed: " + hip_error(status)); // NOLINT
|
|
return std::static_pointer_cast<void>(result);
|
|
}
|
|
|
|
} // namespace rtc
|