InfiniTensor/include/cuda/cuda_common.h

115 lines
5.2 KiB
C
Raw Normal View History

#pragma once
#include "core/common.h"
#include <cublas_v2.h>
#include <cuda.h>
#include <cuda_profiler_api.h>
#include <cudnn.h>
#include <curand.h>
#define checkCudaError(call) \
tensor parallel for transformer (#125) * add cmake bits about NCCL * move example to examples/NNmodel * impl NCCL communicator * add comm related function to Runtime * export runtime interface * add launch.py * use unique name to distingush the the NCCL ID file * add timeout to communicator init * expose communicator obj from runtime obj, add unit test for nccl communicator * reformat files * Add allReduce operator and cuda nccl allReduce kernel * impl model parallel for resnet * add allGather nccl kernel and operator * Add allreduce allgather operator tests, change allgather kernel to output list of tensor, fix shape infer, handle nullptr output * fix format of onnx.py * use concat following AllGather * get tensor parallel for resnet * fix format of graph_handler.cc * change BUILD_DIST default to OFF * polish code of communicator * update .gitignore * export min/max to python * fix MatMul * modify launch.py to run opt * hack to treat ReduceSum as AllReduceSum * throw exception in cuda error * fix parallel_opt.py * improve the error prompt and cuda error check * fix GatherObj::GatherObj member init * fix size calculation for scalar (rank = 0) tensor * MatMul supports bias * fix add bias for row parallel gemm * add --gen_std to launch.py * fix AllReduceNCCL * update launch.py * less log * update parallel_opt * update launch.py * add __eq__ for Placement sub-classes * less benchmark run * fix placement infer for matmul * fix vacabuary size * fix Exception * Add shard tensor with group to support gpt2 * Add find successor function to find split op at different depth * recover CommunicatorObj * improve error mesasge * optimize parallel_opt.py * optimize launch.py * recover docs for all_reduce and all_gather * Fix API * fix format --------- Co-authored-by: panzezhong <panzezhong@qiyuanlab.com> Co-authored-by: Haojie Wang <haojie0429@gmail.com>
2023-09-14 14:19:45 +08:00
if (auto err = call; err != cudaSuccess) \
throw ::infini::Exception(std::string("[") + __FILE__ + ":" + \
std::to_string(__LINE__) + "] CUDA error (" + \
#call + "): " + cudaGetErrorString(err))
#define checkCUresult(call) \
{ \
auto err = call; \
const char *errName; \
if (CUDA_SUCCESS != err) { \
cuGetErrorString(err, &errName); \
IT_ASSERT(err == CUDA_SUCCESS, \
(string("CU error: ") + string(errName))); \
} \
}
#define checkCublasError(call) \
{ \
auto err = call; \
if (CUBLAS_STATUS_SUCCESS != err) { \
fprintf(stderr, "cuBLAS error in %s:%i : %s.\n", __FILE__, \
__LINE__, cublasGetErrorString(err)); \
exit(EXIT_FAILURE); \
} \
}
#define checkCudnnError(call) \
tensor parallel for transformer (#125) * add cmake bits about NCCL * move example to examples/NNmodel * impl NCCL communicator * add comm related function to Runtime * export runtime interface * add launch.py * use unique name to distingush the the NCCL ID file * add timeout to communicator init * expose communicator obj from runtime obj, add unit test for nccl communicator * reformat files * Add allReduce operator and cuda nccl allReduce kernel * impl model parallel for resnet * add allGather nccl kernel and operator * Add allreduce allgather operator tests, change allgather kernel to output list of tensor, fix shape infer, handle nullptr output * fix format of onnx.py * use concat following AllGather * get tensor parallel for resnet * fix format of graph_handler.cc * change BUILD_DIST default to OFF * polish code of communicator * update .gitignore * export min/max to python * fix MatMul * modify launch.py to run opt * hack to treat ReduceSum as AllReduceSum * throw exception in cuda error * fix parallel_opt.py * improve the error prompt and cuda error check * fix GatherObj::GatherObj member init * fix size calculation for scalar (rank = 0) tensor * MatMul supports bias * fix add bias for row parallel gemm * add --gen_std to launch.py * fix AllReduceNCCL * update launch.py * less log * update parallel_opt * update launch.py * add __eq__ for Placement sub-classes * less benchmark run * fix placement infer for matmul * fix vacabuary size * fix Exception * Add shard tensor with group to support gpt2 * Add find successor function to find split op at different depth * recover CommunicatorObj * improve error mesasge * optimize parallel_opt.py * optimize launch.py * recover docs for all_reduce and all_gather * Fix API * fix format --------- Co-authored-by: panzezhong <panzezhong@qiyuanlab.com> Co-authored-by: Haojie Wang <haojie0429@gmail.com>
2023-09-14 14:19:45 +08:00
if (auto err = call; err != CUDNN_STATUS_SUCCESS) \
throw ::infini::Exception(std::string("[") + __FILE__ + ":" + \
std::to_string(__LINE__) + "] cuDNN error (" + \
#call + "): " + cudnnGetErrorString(err))
#define checkCurandError(call) \
{ \
auto err = call; \
if (CURAND_STATUS_SUCCESS != err) { \
fprintf(stderr, "cuRAND error in %s:%i : %s.\n", __FILE__, \
__LINE__, curandGetErrorString(err)); \
exit(EXIT_FAILURE); \
} \
}
namespace infini {
inline const char *cublasGetErrorString(cublasStatus_t error) {
switch (error) {
case CUBLAS_STATUS_SUCCESS:
return "CUBLAS_STATUS_SUCCESS";
case CUBLAS_STATUS_NOT_INITIALIZED:
return "CUBLAS_STATUS_NOT_INITIALIZED";
case CUBLAS_STATUS_ALLOC_FAILED:
return "CUBLAS_STATUS_ALLOC_FAILED";
case CUBLAS_STATUS_INVALID_VALUE:
return "CUBLAS_STATUS_INVALID_VALUE";
case CUBLAS_STATUS_ARCH_MISMATCH:
return "CUBLAS_STATUS_ARCH_MISMATCH";
case CUBLAS_STATUS_MAPPING_ERROR:
return "CUBLAS_STATUS_MAPPING_ERROR";
case CUBLAS_STATUS_EXECUTION_FAILED:
return "CUBLAS_STATUS_EXECUTION_FAILED";
case CUBLAS_STATUS_INTERNAL_ERROR:
return "CUBLAS_STATUS_INTERNAL_ERROR";
case CUBLAS_STATUS_NOT_SUPPORTED:
return "CUBLAS_STATUS_NOT_SUPPORTED";
case CUBLAS_STATUS_LICENSE_ERROR:
return "CUBLAS_STATUS_LICENSE_ERROR";
}
return "<unknown>";
}
inline const char *curandGetErrorString(curandStatus_t error) {
switch (error) {
case CURAND_STATUS_SUCCESS:
return "CURAND_STATUS_SUCCESS";
case CURAND_STATUS_VERSION_MISMATCH:
return "CURAND_STATUS_VERSION_MISMATCH";
case CURAND_STATUS_NOT_INITIALIZED:
return "CURAND_STATUS_NOT_INITIALIZED";
case CURAND_STATUS_ALLOCATION_FAILED:
return "CURAND_STATUS_ALLOCATION_FAILED";
case CURAND_STATUS_TYPE_ERROR:
return "CURAND_STATUS_TYPE_ERROR";
case CURAND_STATUS_OUT_OF_RANGE:
return "CURAND_STATUS_OUT_OF_RANGE";
case CURAND_STATUS_LENGTH_NOT_MULTIPLE:
return "CURAND_STATUS_LENGTH_NOT_MULTIPLE";
case CURAND_STATUS_DOUBLE_PRECISION_REQUIRED:
return "CURAND_STATUS_DOUBLE_PRECISION_REQUIRED";
case CURAND_STATUS_LAUNCH_FAILURE:
return "CURAND_STATUS_LAUNCH_FAILURE";
case CURAND_STATUS_PREEXISTING_FAILURE:
return "CURAND_STATUS_PREEXISTING_FAILURE";
case CURAND_STATUS_INITIALIZATION_FAILED:
return "CURAND_STATUS_INITIALIZATION_FAILED";
case CURAND_STATUS_ARCH_MISMATCH:
return "CURAND_STATUS_ARCH_MISMATCH";
case CURAND_STATUS_INTERNAL_ERROR:
return "CURAND_STATUS_INTERNAL_ERROR";
}
return "<unknown>";
}
using CudaPtr = void *;
} // namespace infini