CUDA: batch out_prod inner loop with cublasSgemmStridedBatched (#22651)
* CUDA: batch out_prod inner loop with cublasSgemmStridedBatched * CUDA: batch out_prod inner loop with cublasSgemmStridedBatched * CUDA: add cublasSgemmStridedBatched mapping for HIP and MUSA backends
This commit is contained in:
Vendored
+1
@@ -48,6 +48,7 @@
|
||||
#define cublasSetMathMode(handle, mode) CUBLAS_STATUS_SUCCESS
|
||||
#define cublasSetStream hipblasSetStream
|
||||
#define cublasSgemm hipblasSgemm
|
||||
#define cublasSgemmStridedBatched hipblasSgemmStridedBatched
|
||||
#define cublasStatus_t hipblasStatus_t
|
||||
#define cublasOperation_t hipblasOperation_t
|
||||
#define cudaDevAttrCooperativeLaunch hipDeviceAttributeCooperativeLaunch
|
||||
|
||||
Vendored
+1
@@ -32,6 +32,7 @@
|
||||
#define cublasSetMathMode mublasSetMathMode
|
||||
#define cublasSetStream mublasSetStream
|
||||
#define cublasSgemm mublasSgemm
|
||||
#define cublasSgemmStridedBatched mublasSgemmStridedBatched
|
||||
#define cublasStatus_t mublasStatus_t
|
||||
#define cublasOperation_t mublasOperation_t
|
||||
#define cublasGetStatusString mublasGetStatusString
|
||||
|
||||
Reference in New Issue
Block a user